Latest in

total 28112took 0.12s
Superquadrics Revisited: Learning 3D Shape Parsing beyond CuboidsApr 22 2019Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting ... More
Synaptic Partner Assignment Using Attentional Voxel Association NetworksApr 22 2019Connectomics aims to recover a complete set of synaptic connections within a dataset imaged by electron microscopy. Most systems for locating synapses use voxelwise classifier models, and train these classifiers to reproduce binary masks of synaptic clefts. ... More
Tripping through time: Efficient Localization of Activities in VideosApr 22 2019Localizing moments in untrimmed videos via language queries is a new and interesting task that requires the ability to accurately ground language into video. Previous works have approached this task by processing the entire video, often more than once, ... More
Late or Earlier Information Fusion from Depth and Spectral Data? Large-Scale Digital Surface Model Refinement by Hybrid-cGANApr 22 2019We present the workflow of a DSM refinement methodology using a Hybrid-cGAN where the generative part consists of two encoders and a common decoder which blends the spectral and height information within one network. The inputs to the Hybrid-cGAN are ... More
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural NetworksApr 22 2019Recently, deep learning has become a de facto standard in machine learning with convolutional neural networks (CNNs) demonstrating spectacular success on a wide variety of tasks. However, CNNs are typically very demanding computationally at inference ... More
Stochastic Region Pooling: Make Attention More ExpressiveApr 22 2019Global Average Pooling (GAP) is used by default on the channel-wise attention mechanism to extract channel descriptors. However, the simple global aggregation method of GAP is easy to make the channel descriptors have homogeneity, which weakens the detail ... More
FoxNet: A Multi-face Alignment MethodApr 22 2019Multi-face alignment aims to identify geometry structures of multiple human face in a image, and its performance is important for the many practical tasks, such as face recognition, face tracking and face animation. In this work, we present a fast bottom-up ... More
2D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point CloudApr 22 2019Large-scale point cloud generated from 3D sensors is more accurate than its image-based counterpart. However, it is seldom used in visual pose estimation due to the difficulty in obtaining 2D-3D image to point cloud correspondences. In this paper, we ... More
An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object DetectionApr 22 2019As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features with a small ... More
FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofingApr 22 2019Face Anti-spoofing gains increased attentions recently in both academic and industrial fields. With the emergence of various CNN based solutions, the multi-modal(RGB, depth and IR) methods based CNN showed better performance than single modal classifiers. ... More
Deep Hough Voting for 3D Object Detection in Point CloudsApr 21 2019Current 3D object detection methods are heavily influenced by 2D detectors. In order to leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids (i.e., to voxel grids or to bird's eye view images), or rely on detection ... More
Probabilistic Face EmbeddingsApr 21 2019Embedding methods have achieved success in face recognition by comparing facial features in a latent semantic space. However, in a fully unconstrained face setting, the features learned by the embedding model could be ambiguous or may not even be present ... More
TiK-means: $K$-means clustering for skewed groupsApr 21 2019The $K$-means algorithm is extended to allow for partitioning of skewed groups. Our algorithm is called TiK-Means and contributes a $K$-means type algorithm that assigns observations to groups while estimating their skewness-transformation parameters. ... More
A Differential Approach for Gaze EstimationApr 20 2019Non-invasive gaze estimation methods usually regress gaze directions directly from a single face or eye image. However, due to important variabilities in eye shapes and inner eye structures amongst individuals, universal models obtain limited accuracies ... More
FACLSTM: ConvLSTM with Focused Attention for Scene Text RecognitionApr 20 2019Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role. Due to the limitation of FC-LSTM, existing methods have to convert 2-D feature ... More
XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities GenerationApr 19 2019This paper proposes a novel framework for lung segmentation in chest X-rays. It consists of two key contributions, a criss-cross attention based segmentation network and radiorealistic chest X-ray image synthesis (i.e. a synthesized radiograph that appears ... More
GestARLite: An On-Device Pointing Finger Based Gestural Interface for Smartphones and Video See-Through Head-MountsApr 19 2019Hand gestures form an intuitive means of interaction in Mixed Reality (MR) applications. However, accurate gesture recognition can be achieved only through state-of-the-art deep learning models or with the use of expensive sensors. Despite the robustness ... More
Visualizing the decision-making process in deep neural decision forestApr 19 2019Deep neural decision forest (NDF) achieved remarkable performance on various vision tasks via combining decision tree and deep representation learning. In this work, we first trace the decision-making process of this model and visualize saliency maps ... More
Video Object Segmentation and Tracking: A SurveyApr 19 2019Apr 22 2019Object segmentation and object tracking are fundamental research area in the computer vision community. These two topics are diffcult to handle some common challenges, such as occlusion, deformation, motion blur, and scale variation. The former contains ... More
Assessing the Sharpness of Satellite Images: Study of the PlanetScope ConstellationApr 19 2019New micro-satellite constellations enable unprecedented systematic monitoring applications thanks to their wide coverage and short revisit capabilities. However, the large volumes of images that they produce have uneven qualities, creating the need for ... More
Efficient Blind Deblurring under High Noise LevelsApr 19 2019The goal of blind image deblurring is to recover a sharp image from a motion blurred one without knowing the camera motion. Current state-of-the-art methods have a remarkably good performance on images with no noise or very low noise levels. However, ... More
A Scalable Handwritten Text Recognition SystemApr 19 2019Many studies on (Offline) Handwritten Text Recognition (HTR) systems have focused on building state-of-the-art models for line recognition on small corpora. However, adding HTR capability to a large scale multilingual OCR system poses new challenges. ... More
Knowledge Distillation via Route Constrained OptimizationApr 19 2019Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily learned by a miniaturized ... More
Salient Object Detection in the Deep Learning Era: An In-Depth SurveyApr 19 2019As an important problem in computer vision, salient object detection (SOD) from images has been attracting an increasing amount of research effort over the years. Recent advances in SOD, not surprisingly, are dominantly led by deep learning-based solutions ... More
Simple yet efficient real-time pose-based action recognitionApr 19 2019Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans. Systems must be able to recognize and assess human actions in real-time. In order to train corresponding data-driven algorithms, a ... More
Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-NetApr 19 2019Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features. To address these difficulties, we introduce a Deep Q Network(DQN) driven approach ... More
SelFlow: Self-Supervised Learning of Optical FlowApr 19 2019We present a self-supervised learning approach for optical flow. Our method distills reliable flow estimations from non-occluded pixels, and uses these predictions as ground truth to learn optical flow for hallucinated occlusions. We further design a ... More
Listen to the ImageApr 19 2019Visual-to-auditory sensory substitution devices can assist the blind in sensing the visual environment by translating the visual information into a sound pattern. To improve the translation quality, the task performances of the blind are usually employed ... More
Deformation and quasiregular extension of cubical Alexander mapsApr 19 2019In this article we prove that, for an oriented PL $n$-manifold $M$ with $m$ boundary components and $d_0\in \mathbb N$, there exist mutually disjoint closed Euclidean balls and a $\mathsf K$-quasiregular mapping $M \to \mathbb S^n \setminus \mathrm{int}(B_1\cup ... More
Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban ScenesApr 19 2019Semantic segmentation, a pixel-level vision task, is developed rapidly by using convolutional neural networks (CNNs). Training CNNs requires a large amount of labeled data, but manually annotating data is difficult. For emancipating manpower, in recent ... More
Advanced Deep Convolutional Neural Network Approaches for Digital Pathology Image Analysis: a comprehensive evaluation with different use casesApr 19 2019Deep Learning (DL) approaches have been providing state-of-the-art performance in different modalities in the field of medical imagining including Digital Pathology Image Analysis (DPIA). Out of many different DL approaches, Deep Convolutional Neural ... More
Integrating Text and Image: Determining Multimodal Document Intent in Instagram PostsApr 19 2019Computing author intent from multimodal data like Instagram posts requires modeling a complex relationship between text and image. For example a caption might reflect ironically on the image, so neither the caption nor the image is a mere transcript of ... More
Feature Forwarding for Efficient Single Image DehazingApr 19 2019Haze degrades content and obscures information of images, which can negatively impact vision-based decision-making in real-time systems. In this paper, we propose an efficient fully convolutional neural network (CNN) image dehazing method designed to ... More
Automated Focal Loss for Image based Object DetectionApr 19 2019Current state-of-the-art object detection algorithms still suffer the problem of imbalanced distribution of training data over object classes and background. Recent work introduced a new loss function called focal loss to mitigate this problem, but at ... More
ProductNet: a Collection of High-Quality Datasets for Product Representation LearningApr 18 2019ProductNet is a collection of high-quality product datasets for better product understanding. Motivated by ImageNet, ProductNet aims at supporting product representation learning by curating product datasets of high quality with properly chosen taxonomy. ... More
A deep learning based solution for construction equipment detection: from development to deploymentApr 18 2019This paper aims at providing researchers and engineering professionals with a practical and comprehensive deep learning based solution to detect construction equipment from the very first step of its development to the last one which is deployment. This ... More
Self-Supervised Audio-Visual Co-SegmentationApr 18 2019Segmenting objects in images and separating sound sources in audio are challenging tasks, in part because traditional approaches require large amounts of labeled data. In this paper we develop a neural network model for visual object segmentation and ... More
Some Aspect of Certain two Subclass of Analytic Functions with Negative Coefficients Defined by Rafid OperatorApr 18 2019In this paper, we define the subclasses $R_{\mu,p}^{\delta}(\alpha;A,B)\ $ and $ P_{\mu,p}^{\delta}(\alpha;A,B)\ $ of analytic functions in the open unit disc of complex plain. Then the neighborhood properties, integral means inequalities and some results ... More
Exploring the Limitations of Behavior Cloning for Autonomous DrivingApr 18 2019Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven ... More
RepGN:Object Detection with Relational Proposal Graph NetworkApr 18 2019Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the graph learning ... More
Deep Parametric Shape Predictions using Distance FieldsApr 18 2019Many tasks in graphics and vision demand machinery for converting shapes into representations with sparse sets of parameters; these representations facilitate rendering, editing, and storage. When the source data is noisy or ambiguous, however, artists ... More
Towards VQA Models that can ReadApr 18 2019Studies have shown that a dominant class of questions asked by visually impaired users on images of their surroundings involves reading text in the image. But today's VQA models can not read! Our paper takes a first step towards addressing this problem. ... More
Attentive Single-Tasking of Multiple TasksApr 18 2019In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as "single-tasking multiple tasks". The network thus modifies its behaviour ... More
Early Detection of Injuries in MLB Pitchers from VideoApr 18 2019Injuries are a major cost in sports. Teams spend millions of dollars every year on players who are hurt and unable to play, resulting in lost games, decreased fan interest and additional wages for replacement players. Modern convolutional neural networks ... More
Deep Rigid Instance Scene FlowApr 18 2019In this paper we tackle the problem of scene flow estimation in the context of self-driving. We leverage deep learning techniques as well as strong priors as in our application domain the motion of the scene can be composed by the motion of the robot ... More
Combating the Elsagate phenomenon: Deep learning architectures for disturbing cartoonsApr 18 2019Watching cartoons can be useful for children's intellectual, social and emotional development. However, the most popular video sharing platform today provides many videos with Elsagate content. Elsagate is a phenomenon that depicts childhood characters ... More
CornerNet-Lite: Efficient Keypoint Based Object DetectionApr 18 2019Keypoint-based methods are a relatively new paradigm in object detection, eliminating the need for anchor boxes and offering a simplified detection framework. Keypoint-based CornerNet achieves state of the art accuracy among single-stage detectors. However, ... More
KPConv: Flexible and Deformable Convolution for Point CloudsApr 18 2019We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied ... More
No-Reference Quality Assessment of Contrast-Distorted Images using Contrast EnhancementApr 18 2019No-reference image quality assessment (NR-IQA) aims to measure the image quality without reference image. However, contrast distortion has been overlooked in the current research of NR-IQA. In this paper, we propose a very simple but effective metric ... More
Salient Object Detection: A Distinctive Feature Integration ModelApr 18 2019We propose a novel method for salient object detection in different images. Our method integrates spatial features for efficient and robust representation to capture meaningful information about the salient objects. We then train a conditional random ... More
Enhanced Center Coding for Cell Detection with Convolutional Neural NetworksApr 18 2019Cell imaging and analysis are fundamental to biomedical research because cells are the basic functional units of life. Among different cell-related analysis, cell counting and detection are widely used. In this paper, we focus on one common step of learning-based ... More
Generating Training Data for Denoising Real RGB Images via Camera Pipeline SimulationApr 18 2019Image reconstruction techniques such as denoising often need to be applied to the RGB output of cameras and cellphones. Unfortunately, the commonly used additive white noise (AWGN) models do not accurately reproduce the noise and the degradation encountered ... More
(De)Constructing Bias on Skin Lesion DatasetsApr 18 2019Melanoma is the deadliest form of skin cancer. Automated skin lesion analysis plays an important role for early detection. Nowadays, the ISIC Archive and the Atlas of Dermoscopy dataset are the most employed skin lesion sources to benchmark deep-learning ... More
On The Classification-Distortion-Perception TradeoffApr 18 2019Signal degradation is ubiquitous and computational restoration of degraded signal has been investigated for many years. Recently, it is reported that the capability of signal restoration is fundamentally limited by the perception-distortion tradeoff, ... More
Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV RacingApr 18 2019Autonomous UAV racing has recently emerged as an interesting research problem. The dream is to beat humans in this new fast-paced sport. A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an ... More
DDNet: Cartesian-polar Dual-domain Network for the Joint Optic Disc and Cup SegmentationApr 18 2019Existing joint optic disc and cup segmentation approaches are developed either in Cartesian or polar coordinate system. However, due to the subtle optic cup, the contextual information exploited from the single domain even by the prevailing CNNs is still ... More
Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagationApr 18 2019Machine learning-based imaging diagnostics has recently reached or even superseded the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major ... More
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural NetworksApr 18 2019In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are processed frame-by-frame either through 2D convnets or 3D perception algorithms. ... More
Targetless Rotational Auto-Calibration of Radar and Camera for Intelligent Transportation SystemsApr 18 2019Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception. The calibration of these heterogeneous sensor types in an automatic fashion during system operation is challenging due to differing physical ... More
Cascaded Partial Decoder for Fast and Accurate Salient Object DetectionApr 18 2019Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs). Compared to high-level features, low-level features contribute less to performance but cost more ... More
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric LearningApr 18 2019We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a naive optimization of the triplet loss function has a ... More
Knowledge-rich Image Gist Understanding Beyond Literal MeaningApr 18 2019We investigate the problem of understanding the message (gist) conveyed by images and their captions as found, for instance, on websites or news articles. To this end, we propose a methodology to capture the meaning of image-caption pairs on the basis ... More
Out-of-Distribution Detection for Generalized Zero-Shot Action RecognitionApr 18 2019Generalized zero-shot action recognition is a challenging problem, where the task is to recognize new action categories that are unavailable during the training stage, in addition to the seen action categories. Existing approaches suffer from the inherent ... More
Examining the Capability of GANs to Replace Real Biomedical Images in Classification Models TrainingApr 18 2019In this paper, we explore the possibility of generating artificial biomedical images that can be used as a substitute for real image datasets in applied machine learning tasks. We are focusing on generation of realistic chest X-ray images as well as on ... More
Global Hashing System for Fast Image SearchApr 18 2019Hashing methods have been widely investigated for fast approximate nearest neighbor searching in large data sets. Most existing methods use binary vectors in lower dimensional spaces to represent data points that are usually real vectors of higher dimensionality. ... More
Coupled Learning for Facial DeblurApr 18 2019Blur in facial images significantly impedes the efficiency of recognition approaches. However, most existing blind deconvolution methods cannot generate satisfactory results due to their dependence on strong edges, which are sufficient in natural images ... More
An Efficient Approximate kNN Graph Method for Diffusion on Image RetrievalApr 18 2019The application of the diffusion in many computer vision and artificial intelligence projects has been shown to give excellent improvements in performance. One of the main bottlenecks of this technique is the quadratic growth of the kNN graph size due ... More
Fully Automatic Segmentation of 3D Brain Ultrasound: Learning from Coarse AnnotationsApr 18 2019Intra-operative ultrasound is an increasingly important imaging modality in neurosurgery. However, manual interaction with imaging data during the procedures, for example to select landmarks or perform segmentation, is difficult and can be time consuming. ... More
Fooling automated surveillance cameras: adversarial patches to attack person detectionApr 18 2019Adversarial attacks on machine learning models have seen increasing interest in the past years. By making only subtle changes to the input of a convolutional neural network, the output of the network can be swayed to output a completely different result. ... More
Tex2Shape: Detailed Full Human Body Geometry from a Single ImageApr 18 2019We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details ... More
Real-Time Style Transfer With Strength ControlApr 18 2019Style transfer is a problem of rendering a content image in the style of another style image. A natural and common practical task in applications of style transfer is to adjust the strength of stylization. Algorithm of Gatys et al. (2016) provides this ... More
DDLSTM: Dual-Domain LSTM for Cross-Dataset Action RecognitionApr 18 2019Domain alignment in convolutional networks aims to learn the degree of layer-specific feature alignment beneficial to the joint learning of source and target datasets. While increasingly popular in convolutional networks, there have been no previous attempts ... More
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big DataApr 18 2019In this paper we investigate into the problem of image quality assessment (IQA) and enhancement via machine learning. This issue has long attracted a wide range of attention in computational intelligence and image processing communities, since, for many ... More
Unsupervised Open Domain Recognition by Semantic Discrepancy MinimizationApr 18 2019We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. The task is to correctly classify all samples in T including known and unknown categories. ... More
Discriminative Online Learning for Fast Video Object SegmentationApr 18 2019We address the highly challenging problem of video object segmentation. Given only the initial mask, the task is to segment the target in the subsequent frames. In order to effectively handle appearance changes and similar background objects, a robust ... More
Disentangled Representation Learning with Information Maximizing AutoencoderApr 18 2019Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing the mutual information ... More
Client/Server Based Online Environment for Manual Segmentation of Medical ImagesApr 18 2019Segmentation is a key step in analyzing and processing medical images. Due to the low fault tolerance in medical imaging, manual segmentation remains the de facto standard in this domain. Besides, efforts to automate the segmentation process often rely ... More
Learning to Collocate Neural Modules for Image CaptioningApr 18 2019We do not speak word by word from scratch; our brain quickly structures a pattern like \textsc{sth do sth at someplace} and then fill in the detailed descriptions. To render existing encoder-decoder image captioners such human-like reasoning, we propose ... More
Progressive Attention Memory Network for Movie Story Question AnsweringApr 18 2019This paper proposes the progressive attention memory network (PAMN) for movie story question answering (QA). Movie story QA is challenging compared to VQA in two aspects: (1) pinpointing the temporal parts relevant to answer the question is difficult ... More
Deep Optics for Monocular Depth Estimation and 3D Object DetectionApr 18 2019Depth estimation and 3D object detection are critical for scene understanding but remain challenging to perform with a single image due to the loss of 3D information during image capture. Recent models using deep neural networks have improved monocular ... More
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive ThresholdingApr 18 2019Crack is one of the most common road distresses which may pose road safety hazards. Generally, crack detection is performed by either certified inspectors or structural engineers. This task is, however, time-consuming, subjective and labor-intensive. ... More
Fast Single Image Dehazing via Multilevel Wavelet Transform based OptimizationApr 18 2019The quality of images captured in outdoor environments can be affected by poor weather conditions such as fog, dust, and atmospheric scattering of other particles. This problem can bring extra challenges to high-level computer vision tasks like image ... More
Generative Model for Zero-Shot Sketch-Based Image RetrievalApr 18 2019We present a probabilistic model for Sketch-Based Image Retrieval (SBIR) where, at retrieval time, we are given sketches from novel classes, that were not present at training time. Existing SBIR methods, most of which rely on learning class-wise correspondences ... More
Material Segmentation of Multi-View Satellite ImageryApr 17 2019Material recognition methods use image context and local cues for pixel-wise classification. In many cases only a single image is available to make a material prediction. Image sequences, routinely acquired in applications such as mutliview stereo, can ... More
Do Lateral Views Help Automated Chest X-ray Predictions?Apr 17 2019Most convolutional neural networks in chest radiology use only the frontal posteroanterior (PA) view to make a prediction. However the lateral view is known to help the diagnosis of certain diseases and conditions. The recently released PadChest dataset ... More
Graph based Dynamic Segmentation of Generic Objects in 3DApr 17 2019We propose a novel 3D segmentation method for RBGD stream data to deal with 3D object segmentation task in a generic scenario with frequent object interactions. It mainly contributes in two aspects, while being generic and not requiring initialization: ... More
ZK-GanDef: A GAN based Zero Knowledge Adversarial Training Defense for Neural NetworksApr 17 2019Neural Network classifiers have been used successfully in a wide range of applications. However, their underlying assumption of attack free environment has been defied by adversarial examples. Researchers tried to develop defenses; however, existing approaches ... More
Semantic Adversarial Attacks: Parametric Transformations That Fool Deep ClassifiersApr 17 2019Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the image pixel space. ... More
Variational Prototyping-Encoder: One-Shot Learning with Prototypical ImagesApr 17 2019In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot classification with ... More
LCC: Learning to Customize and Combine Neural Networks for Few-Shot LearningApr 17 2019Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to leverage a large number of similar few-shot tasks in order to meta-learn how to best initiate a (single) base-learner for novel few-shot tasks. While meta-learning ... More
Image Resizing by Reconstruction from Deep FeaturesApr 17 2019Traditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature space where the ... More
DeepAtlas: Joint Semi-Supervised Learning of Image Registration and SegmentationApr 17 2019Deep convolutional neural networks (CNNs) are state-of-the-art for semantic image segmentation, but typically require many labeled training samples. Obtaining 3D segmentations of medical images for supervised training is difficult and labor intensive. ... More
Online Adaptation through Meta-Learning for Stereo Depth EstimationApr 17 2019In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To address this problem, ... More
Defensive Quantization: When Efficiency Meets RobustnessApr 17 2019Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are vulnerable to adversarial ... More
Event-based Vision: A SurveyApr 17 2019Event cameras are bio-inspired sensors that work radically different from traditional cameras. Instead of capturing images at a fixed rate, they measure per-pixel brightness changes asynchronously. This results in a stream of events, which encode the ... More
Process of image super-resolutionApr 17 2019In this paper we explain a process of super-resolution reconstruction allowing to increase the resolution of an image.The need for high-resolution digital images exists in diverse domains, for example the medical and spatial domains. The obtaining of ... More
Vid2Game: Controllable Characters Extracted from Real-World VideosApr 17 2019We are given a video of a person performing a certain activity, from which we extract a controllable model. The model generates novel image sequences of that person, according to arbitrary user-defined control signals, typically marking the displacement ... More
Gaze Training by Modulated Dropout Improves Imitation LearningApr 17 2019Imitation learning by behavioral cloning is a prevalent method which has achieved some success in vision-based autonomous driving. The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior. Typically, ... More
Render4Completion: Synthesizing Multi-view Depth Maps for 3D Shape CompletionApr 17 2019We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or point clouds, we propose to use multi-view depth maps from a set of fixed ... More
Aggregation Cross-Entropy for Sequence RecognitionApr 17 2019In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective. The ACE loss function exhibits competitive performance to CTC and the attention mechanism, with much quicker implementation ... More