Search Results for author:
Found 309 papers, 127 papers with code
Online Robust PCA via Stochastic Optimization
Robust PCA methods are typically based on batch optimization and have to load all the samples into memory.
Online PCA for Contaminated Data
We consider the online Principal Component Analysis (PCA) for contaminated samples (containing outliers) which are revealed sequentially to the Principal Components (PCs) estimator.
Robust Subspace Segmentation with Block-diagonal Prior
Most current state-of-the-art subspace segmentation methods (such as SSC and LRR) resort to alternative structural priors (such as sparseness and low-rankness) to construct the affinity matrix.
Learning Scalable Discriminative Dictionary with Sample Relatedness
We use sample relatedness information to improve the generalization of the learned dictionary.
Distributed Robust Learning
We propose a framework for distributed robust statistical learning on {\em big contaminated data}.
Robust Logistic Regression and Classification
We consider logistic regression with arbitrary outliers in the covariate matrix.
Correlation Adaptive Subspace Segmentation by Trace Lasso
In this work, we argue that both sparsity and the grouping effect are important for subspace segmentation.
Modality-dependent Cross-media Retrieval
Specifically, by jointly optimizing the correlation between images and text and the linear regression from one modal space (image or text) to the semantic space, two couples of mappings are learned to project images and text from their original feature spaces into two common latent subspaces (one for I2T and the other for T2I).
Sense Beyond Expressions: Cuteness
With the development of Internet culture, cuteness has become a popular concept.
STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
Then, a better network called Enhanced-DCNN is learned with supervision from the predicted segmentation masks of simple images based on the Initial-DCNN as well as the image-level annotations.
Learning with $\ell^{0}$-Graph: $\ell^{0}$-Induced Sparse Subspace Clustering
Sparse subspace clustering methods, such as Sparse Subspace Clustering (SSC) \cite{ElhamifarV13} and $\ell^{1}$-graph \cite{YanW09, ChengYYFH10}, are effective in partitioning the data that lie in a union of subspaces.
Scale-aware Fast R-CNN for Pedestrian Detection
Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework.
Ranked #23 on
Pedestrian Detection
on Caltech
Deep Recurrent Regression for Facial Landmark Detection
We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures.
Natural Language Object Retrieval
In this paper, we address the task of natural language object retrieval, to localize a target object within a given image based on a natural language query of the object.
Ranked #12 on
Referring Expression Comprehension
on Talk2Car
Semantic Object Parsing with Local-Global Long Short-Term Memory
The long chains of sequential computation by stacked LG-LSTM layers also enable each pixel to sense a much larger region for inference benefiting from the memorization of previous dependencies in all positions along all dimensions.
Return of Frustratingly Easy Domain Adaptation
Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions.
Ranked #4 on
Domain Adaptation
on Synth Digits-to-SVHN
Auxiliary Image Regularization for Deep CNNs with Noisy Labels
Precisely-labeled data sets with sufficient amount of samples are very important for training deep convolutional neural networks (CNNs).
Learning The Structure of Deep Convolutional Networks
In this work, we develop a novel method for automatically learning aspects of the structure of a deep model, in order to improve its performance, especially when labeled training data are scarce.
Deep Learning with S-shaped Rectified Linear Activation Units
Rectified linear activation units are important components for state-of-the-art deep convolutional networks.
DrMAD: Distilling Reverse-Mode Automatic Differentiation for Optimizing Hyperparameters of Deep Neural Networks
The performance of deep neural networks is well-known to be sensitive to the setting of their hyperparameters.
Scale-aware Pixel-wise Object Proposal Networks
In particular, in order to improve the localization accuracy, a fully convolutional network is employed which predicts locations of object proposals for each pixel.
Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms
As most deep learning algorithms are stochastic (e. g., Stochastic Gradient Descent, Dropout, and Bayes-by-backprop), we revisit the robustness arguments of Xu & Mannor, and introduce a new approach, ensemble robustness, that concerns the robustness of a population of hypotheses.
Semantic Object Parsing with Graph LSTM
By taking the semantic object parsing task as an exemplar application scenario, we propose the Graph Long Short-Term Memory (Graph LSTM) network, which is the generalization of LSTM from sequential data or multi-dimensional data to general graph-structured data.
Attentive Contexts for Object Detection
We provide preliminary answers to these questions through developing a novel Attention to Context Convolution Neural Network (AC-CNN) based object detection model.
A Focused Dynamic Attention Model for Visual Question Answering
Solving VQA problems requires techniques from both computer vision for understanding the visual contents of a presented image or video, as well as the ones from natural language processing for understanding semantics of the question and generating the answers.
Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution
To address this essentially ill-posed problem, we introduce a Deep Edge Guided REcurrent rEsidual~(DEGREE) network to progressively recover the high-frequency details.
Accelerated Randomized Mirror Descent Algorithms For Composite Non-strongly Convex Optimization
Avoiding this devise, we propose an accelerated randomized mirror descent method for solving this problem without the strongly convex assumption.
Highway Vehicle Counting in Compressed Domain
HCR hierarchically divides the traffic scenes into different cases according to vehicle density, such that the broad-variation characteristics of traffic scenes can be better approximated.
Recurrent Face Aging
Modeling the aging process of human face is important for cross-age face verification and recognition.
Recurrently Target-Attending Tracking
The produced confidence maps from the RNNs are employed to adaptively regularize the learning of discriminative correlation filters by suppressing clutter background noises while making full use of the information from reliable parts.
End-to-End Comparative Attention Networks for Person Re-identification
The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person.
Diversified Visual Attention Networks for Fine-Grained Object Classification
Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation.
Collaborative Layer-wise Discriminative Learning in Deep Neural Networks
In this paper, we propose a layer-wise discriminative learning method to enhance the discriminative capability of a deep network by allowing its layers to work collaboratively for classification.
Training Skinny Deep Neural Networks with Iterative Hard Thresholding Methods
In this paper, we propose an iterative hard thresholding (IHT) approach to train Skinny Deep Neural Networks (SDNNs).
Efficient Hyperparameter Optimization of Deep Learning Algorithms Using Deterministic RBF Surrogates
Those methods adopt probabilistic surrogate models like Gaussian processes to approximate and minimize the validation error function of hyperparameter values.
Hyperparameter Transfer Learning through Surrogate Alignment for Efficient Deep Neural Network Training
Recently, several optimization methods have been successfully applied to the hyperparameter optimization of deep neural networks (DNNs).
Multi-stage Object Detection with Group Recursive Learning
Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately.
Multi-Path Feedback Recurrent Neural Network for Scene Parsing
In this paper, we consider the scene parsing problem and propose a novel Multi-Path Feedback recurrent neural network (MPF-RNN) for parsing scene images.
Deep Joint Rain Detection and Removal from a Single Image
Based on the first model, we develop a multi-task deep learning architecture that learns the binary rain streak map, the appearance of rain streaks, and the clean background, which is our ultimate output.
Video Scene Parsing with Predictive Feature Learning
In this way, the network can effectively learn to capture video dynamics and temporal context, which are critical clues for video scene parsing, without requiring extra manual annotations.
Correlation Alignment for Unsupervised Domain Adaptation
In contrast to subspace manifold methods, it aligns the original feature distributions of the source and target domains, rather than the bases of lower-dimensional subspaces.
Ranked #8 on
Domain Adaptation
on Office-Caltech
Robust LSTM-Autoencoders for Face De-Occlusion in the Wild
The first one, named multi-scale spatial LSTM encoder, reads facial patches of various scales sequentially to output a latent representation, and occlusion-robustness is achieved owing to the fact that the influence of occlusion is only upon some of the patches.
Outlier Robust Online Learning
We consider the problem of learning from noisy data in practical settings where the size of data is too large to store on a single machine.
Video-based Person Re-identification with Accumulative Motion Context
Video based person re-identification plays a central role in realistic security and video surveillance.
Training Group Orthogonal Neural Networks with Privileged Information
Learning rich and diverse representations is critical for the performance of deep convolutional neural networks (CNNs).
Tree-Structured Reinforcement Learning for Sequential Object Localization
Therefore, Tree-RL can better cover different objects with various scales which is quite appealing in the context of object proposal.
Interpretable Structure-Evolving LSTM
Instead of learning LSTM models over the pre-fixed structures, we propose to further learn the intermediate interpretable multi-level graph structures in a progressive and stochastic way from data during the LSTM network optimization.
Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach
We investigate a principle way to progressively mine discriminative object regions using classification networks to address the weakly-supervised semantic segmentation problems.
On Fundamental Limits of Robust Learning
We consider the problems of robust PAC learning from distributed and streaming data, which may contain malicious errors and outliers, and analyze their fundamental complexity questions.
A Good Practice Towards Top Performance of Face Recognition: Transferred Deep Feature Fusion
In this paper, we propose a unified learning framework named Transferred Deep Feature Fusion (TDFF) targeting at the new IARPA Janus Benchmark A (IJB-A) face recognition dataset released by NIST face challenge.
Learning Detection with Diverse Proposals
To predict a set of diverse and informative proposals with enriched representations, this paper introduces a differentiable Determinantal Point Process (DPP) layer that is able to augment the object detection architectures.
Multi-View Image Generation from a Single-View
This paper addresses a challenging problem -- how to generate multi-view cloth images from only a single view input.
Deep Self-Taught Learning for Weakly Supervised Object Localization
To overcome this issue, we propose a deep self-taught learning approach, which makes the detector learn the object-level features reliable for acquiring tight positive samples and afterwards re-train itself based on them.
IAN: The Individual Aggregation Network for Person Search
In addition, to relieve the negative effect caused by varying visual appearances of the same individual, IAN introduces a novel center loss that can increase the intra-class compactness of feature representations.
Multiple-Human Parsing in the Wild
To address the multi-human parsing problem, we introduce a new multi-human parsing (MHP) dataset and a novel multi-human parsing model named MH-Parser.
Ranked #3 on
Multi-Human Parsing
on MHP v1.0
The Landscape of Deep Learning Algorithms
For an $l$-layer linear neural network, we prove its empirical risk uniformly converges to its population risk at the rate of $\mathcal{O}(r^{2l}\sqrt{d\log(l)}/\sqrt{n})$ with training sample size of $n$, the total weight dimension of $d$ and the magnitude bound $r$ of weight of each layer.
A Unified Framework for Stochastic Matrix Factorization via Variance Reduction
We propose a unified framework to speed up the existing stochastic matrix factorization (SMF) algorithms via variance reduction.
Generative Partition Networks for Multi-Person Pose Estimation
This paper proposes a new Generative Partition Network (GPN) to address the challenging multi-person pose estimation problem.
Ranked #1 on
Multi-Person Pose Estimation
on WAF
(AP metric)
Video-based Person Re-identification with Accumulative Motion Context
Video based person re-identification plays a central role in realistic security and video surveillance.
Perceptual Generative Adversarial Networks for Small Object Detection
In this work, we address the small object detection problem by developing a single architecture that internally lifts representations of small objects to "super-resolved" ones, achieving similar characteristics as large objects and thus more discriminative for detection.
Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search
We introduce a new fashion search protocol where attribute manipulation is allowed within the interaction between users and search engines, e. g. manipulating the color attribute of the clothing from red to blue.
Outlier-Robust Tensor PCA
Low-rank tensor analysis is important for various real applications in computer vision.
Deep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks
Through competition with discriminator, the generator progressively improves quality of the future frames and thus anticipates future gaze better.
Dual Path Networks
In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally.
Neural Person Search Machines
We investigate the problem of person search in the wild in this work.
Ranked #4 on
Person Re-Identification
on CUHK-SYSU
A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models
On the other hand, very little focus has been put on the models' loss function, arguably one of the most important aspects of training deep learning models.
FoveaNet: Perspective-aware Urban Scene Parsing
Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors.
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
In this work, we prove that under certain suitable assumptions, we can recover both the low-rank and the sparse components exactly by simply solving a convex program whose objective is a weighted combination of the tensor nuclear norm and the $\ell_1$-norm, i. e., $\min_{{\mathcal{L}},\ {\mathcal{E}}} \ \|{{\mathcal{L}}}\|_*+\lambda\|{{\mathcal{E}}}\|_1, \ \text{s. t.}
Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback
However, most of the existing CNN models only learn features through a feedforward structure and no feedback information from top to bottom layers is exploited to enable the networks to refine themselves.
Self-explanatory Deep Salient Object Detection
Through visualizing the differences, we can interpret the capability of different deep neural networks based saliency detection models and demonstrate that our proposed model indeed uses more reasonable structure for salient object detection.
Stochastic Primal-Dual Proximal ExtraGradient Descent for Compositely Regularized Optimization
This optimization model abstracts a number of important applications in artificial intelligence and machine learning, such as fused Lasso, fused logistic regression, and a class of graph-guided regularized minimization.
On the Suboptimality of Proximal Gradient Descent for $\ell^{0}$ Sparse Approximation
We study the proximal gradient descent (PGD) method for $\ell^{0}$ sparse approximation problem as well as its accelerated optimization with randomized algorithms in this paper.
Discriminative Similarity for Clustering and Semi-Supervised Learning
By generalization analysis via Rademacher complexity, the generalization error bound for the kernel classifier learned from hypothetical labeling is expressed as the sum of pairwise similarity between the data from different classes, parameterized by the weights of the kernel classifier.
Deep Sparse Subspace Clustering
In this paper, we present a deep extension of Sparse Subspace Clustering, termed Deep Sparse Subspace Clustering (DSSC).
Regional Interactive Image Segmentation Networks
The interactive image segmentation model allows users to iteratively add new inputs for refinement until a satisfactory result is finally obtained.
Ranked #10 on
Interactive Segmentation
on SBD
(NoC@85 metric)
Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection
To address these challenging issues, we introduce a novel recurrent 3D-2D dual learning model that alternatively performs 2D-based 3D face model refinement and 3D-to-2D projection based 2D landmark refinement to reliably reason about self-occluded landmarks, precisely capture the subtle landmark displacement and accurately detect landmarks even in presence of extremely large poses.
Predicting Scene Parsing and Motion Dynamics in the Future
The ability of predicting the future is important for intelligent systems, e. g. autonomous vehicles and robots to plan early and make decisions accordingly.
Integrated Face Analytics Networks through Cross-Dataset Hybrid Training
Specifically, iFAN achieves an overall F-score of 91. 15% on the Helen dataset for face parsing, a normalized mean error of 5. 81% on the MTFL dataset for facial landmark localization and an accuracy of 45. 73% on the BNU dataset for emotion recognition with a single model.
Transferable Semi-supervised Semantic Segmentation
The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations.
Personalized and Occupational-aware Age Progression by Generative Adversarial Networks
Second, we propose a new occupational-aware adversarial face aging network, which learns human aging process under different occupations.
HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
The proposed new adversarial network, HashGAN, consists of three building blocks: 1) the feature learning module to obtain feature representations, 2) the generative attention module to generate an attention mask, which is used to obtain the attended (foreground) and the unattended (background) feature representations, 3) the discriminative hash coding module to learn hash functions that preserve the similarities between different modalities.
WSNet: Compact and Efficient Networks Through Weight Sampling
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks.
Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis
In particular, we employ an off-the-shelf 3D face model as a simulator to generate profile face images with varying poses.
Ranked #1 on
Face Verification
on IJB-A
Multimodal Learning and Reasoning for Visual Question Answering
In this work we introduce a modular neural network model that learns a multimodal and multifaceted representation of the image and the question.
Nonconvex Sparse Spectral Clustering by Alternating Direction Method of Multipliers and Its Convergence Analysis
Experimental analysis on several real data sets verifies the effectiveness of our method.
Weaving Multi-scale Context for Single Shot Detector
For 320x320 input of batch size = 8, WeaveNet reaches 79. 5% mAP on PASCAL VOC 2007 test in 101 fps with only 4 fps extra cost, and further improves to 79. 7% mAP with more iterations.
Egocentric Spatial Memory Network
During the exploration, our proposed ESM network model updates belief of the global map based on local observations using a recurrent neural network.
WSNet: Learning Compact and Efficient Networks with Weight Sampling
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks.
Interpreting Deep Classification Models With Bayesian Inference
The results demonstrate that the proposed interpreter successfully finds the core hidden units most responsible for prediction making.
Empirical Risk Landscape Analysis for Understanding Deep Neural Networks
This work aims to provide comprehensive landscape analysis of empirical risk in deep neural networks (DNNs), including the convergence behavior of its gradient, its stationary points and the empirical risk itself to their corresponding population counterparts, which reveals how various network parameters determine the convergence performance.
Cross-domain Human Parsing via Adversarial Feature and Label Adaptation
Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences.
Left-Right Comparative Recurrent Model for Stereo Matching
Left-right consistency check is an effective way to enhance the disparity estimation by referring to the information from the opposite view.
Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing
Despite the noticeable progress in perceptual tasks like detection, instance segmentation and human parsing, computers still perform unsatisfactorily on visually understanding humans in crowded scenes, such as group behavior analysis, person re-identification and autonomous driving, etc.
Ranked #1 on
Multi-Human Parsing
on PASCAL-Part
Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm
Equipped with the new tensor nuclear norm, we then solve the TRPCA problem by solving a convex program and provide the theoretical guarantee for the exact recovery.
Adversarial Complementary Learning for Weakly Supervised Object Localization
With such an adversarial learning, the two parallel-classifiers are forced to leverage complementary object regions for classification and can finally generate integral object localization together.
Ranked #2 on
Weakly-Supervised Object Localization
on ILSVRC 2016
Zigzag Learning for Weakly Supervised Object Detection
Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds.
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
It can produce dense and reliable object localization maps and effectively benefit both weakly- and semi- supervised semantic segmentation.
Learning Pixel-wise Labeling from the Internet without Human Interaction
Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation.
Learning Markov Clustering Networks for Scene Text Detection
MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing Markov Clustering on this graph.
Subspace Clustering by Block Diagonal Representation
Second, we observe that many existing methods approximate the block diagonal representation matrix by using different structure priors, e. g., sparsity and low-rankness, which are indirect.
Understanding Generalization and Optimization Performance of Deep CNNs
Besides, we prove that for an arbitrary gradient descent algorithm, the computed approximate stationary point by minimizing empirical risk is also an approximate stationary point to the population risk.
Deep Adversarial Subspace Clustering
To solve this issue, we propose a novel deep adversarial subspace clustering (DASC) model, which learns more favorable sample representations by deep learning for subspace clustering, and more importantly introduces adversarial learning to supervise sample representation learning and subspace clustering.
Ranked #2 on
Image Clustering
on coil-40
Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network
In this paper, we propose a novel weakly supervised model, Multi-scale Anchored Transformer Network (MATN), to accurately localize free-form textual phrases with only image-level supervision.
MoNet: Deep Motion Exploitation for Video Object Segmentation
In this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i. e., frame representation learning and segmentation refinement.
Towards Pose Invariant Face Recognition in the Wild
To this end, we propose a Pose Invariant Model (PIM) for face recognition in the wild, with three distinct novelties.
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
Despite remarkable progress, weakly supervised segmentation methods are still inferior to their fully supervised counterparts.
Human Pose Estimation With Parsing Induced Learner
Comprehensive experiments on benchmarks LIP and extended PASCAL-Person-Part show that the proposed Parsing Induced Learner can improve performance of both single- and multi-person pose estimation to new state-of-the-art.
Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements
Specifically, we show that by solving a TNN minimization problem, the underlying tensor of size $n_1\times n_2\times n_3$ with tubal rank $r$ can be exactly recovered when the given number of Gaussian measurements is $O(r(n_1+n_2-r)n_3)$.
Policy Optimization with Demonstrations
Exploration remains a significant challenge to reinforcement learning methods, especially in environments where reward signals are sparse.
TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection
This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C).
Object Relation Detection Based on One-shot Learning
Detecting the relations among objects, such as "cat on sofa" and "person ride horse", is a crucial task in image understanding, and beneficial to bridging the semantic gap between images and natural language.
Multi-Fiber Networks for Video Recognition
In this paper, we aim to reduce the computational cost of spatio-temporal deep neural networks, making them run as fast as their 2D counterparts while preserving state-of-the-art accuracy on video recognition benchmarks.
Ranked #36 on
Action Recognition
on UCF101
(using extra training data)
Egocentric Spatial Memory
Egocentric spatial memory (ESM) defines a memory system with encoding, storing, recognizing and recalling the spatial information about the environment from an egocentric perspective.
Dynamic Conditional Networks for Few-Shot Learning
This paper proposes a novel Dynamic Conditional Convolutional Network (DCCN) to handle conditional few-shot learning, i. e, only a few training samples are available for each condition.
Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation
This paper presents a novel Mutual Learning to Adapt model (MuLA) for joint human parsing and pose estimation.
Ranked #11 on
Semantic Segmentation
on LIP val
Pose Partition Networks for Multi-Person Pose Estimation
This paper proposes a novel Pose Partition Network (PPN) to address the challenging multi-person pose estimation problem.
ML-LocNet: Improving Object Localization with Multi-view Learning Network
This paper addresses Weakly Supervised Object Localization (WSOL) with only image-level supervision.
Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition
Benchmarking our model on one of the most popular unconstrained face recognition datasets IJB-C additionally verifies the promising generalizability of AIM in recognizing faces in the wild.
Ranked #1 on
Age-Invariant Face Recognition
on MORPH Album2
Sample Efficient Deep Neuroevolution in Low Dimensional Latent Space
Current deep neuroevolution models are usually trained in a large parameter search space for complex learning tasks, e. g. playing video games, which needs billions of samples and thousands of search steps to obtain significant performance.
$A^2$-Nets: Double Attention Networks
Learning to capture long-range relations is fundamental to image/video recognition.
Ranked #35 on
Action Recognition
on UCF101
Graph-Based Global Reasoning Networks
In this work, we propose a new approach for reasoning globally in which a set of features are globally aggregated over the coordinate space and then projected to an interaction space where relational reasoning can be efficiently computed.
Efficient Stochastic Gradient Hard Thresholding
To address these deficiencies, we propose an efficient hybrid stochastic gradient hard thresholding (HSG-HT) method that can be provably shown to have sample-size-independent gradient evaluation and hard thresholding complexity bounds.
A^2-Nets: Double Attention Networks
Learning to capture long-range relations is fundamental to image/video recognition.
New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity
In this paper, we affirmatively answer this open question by showing that under WoRS and for both convex and non-convex problems, it is still possible for HSGD (with constant step-size) to match full gradient descent in rate of convergence, while maintaining comparable sample-size-independent incremental first-order oracle complexity to stochastic gradient descent.
Few-shot Object Detection via Feature Reweighting
The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples.
Ranked #21 on
Few-Shot Object Detection
on MS-COCO (30-shot)
Similarity R-C3D for Few-shot Temporal Activity Detection
In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection which detects the start and end time of the few-shot input activities in an untrimmed video.
Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks
In this paper, we propose a novel GAN based on inter-frame difference to circumvent the difficulties.
Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing
Face anti-spoofing (a. k. a presentation attack detection) has drawn growing attention due to the high-security demand in face authentication systems.
Ranked #2 on
Face Anti-Spoofing
on MSU-MFSD
Deep Reasoning with Multi-Scale Context for Salient Object Detection
However, the saliency inference module that performs saliency prediction from the fused features receives much less attention on its architecture design and typically adopts only a few fully convolutional layers.
Multi-Prototype Networks for Unconstrained Set-based Face Recognition
In this paper, we study the challenging unconstrained set-based face recognition problem where each subject face is instantiated by a set of media (images and videos) instead of a single image.
Dynamic Feature Fusion for Semantic Edge Detection
In this work, we propose a novel dynamic feature fusion strategy that assigns different fusion weights for different input images and locations adaptively.
Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off.
3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the Wild
3D face reconstruction from a single 2D image is a challenging problem with broad applications.
Ranked #7 on
Face Alignment
on AFLW2000-3D
Few-shot Adaptive Faster R-CNN
To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples.
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies.
Ranked #147 on
Action Classification
on Kinetics-400
Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification
FPR uses the error from robust reconstruction over spatial pyramid features to measure similarities between two persons.
Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization
The evaluator defines a learnable information preserving metric between original video and summary video and "supervises" the selector to identify the most informative frames to form the summary video.
Ranked #7 on
Unsupervised Video Summarization
on TvSum
Hierarchical Meta Learning
Extensive experiments on few-shot classification and regression problems clearly demonstrate the superiority of HML over fine-tuning and state-of-the-art meta learning approaches in terms of generalization across heterogeneous tasks.
A Simple Pooling-Based Design for Real-Time Salient Object Detection
We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway.
Ranked #1 on
RGB Salient Object Detection
on SOD
Variational Prototype Replays for Continual Learning
In each classification task, our method learns a set of variational prototypes with their means and variances, where embedding of the samples from the same class can be represented in a prototypical distribution and class-representative prototypes are separated apart.
Cross-Resolution Face Recognition via Prior-Aided Face Hallucination and Residual Knowledge Distillation
Recent deep learning based face recognition methods have achieved great performance, but it still remains challenging to recognize very low-resolution query face like 28x28 pixels when CCTV camera is far from the captured subject.
Panoptic Edge Detection
In this work, we address a new finer-grained task, termed panoptic edge detection (PED), which aims at predicting semantic-level boundaries for stuff categories and instance-level boundaries for instance categories, in order to provide more comprehensive and unified scene understanding from the perspective of edges. We then propose a versatile framework, Panoptic Edge Network (PEN), which aggregates different tasks of object detection, semantic and instance edge detection into a single holistic network with multiple branches.
Deep Face Recognition Model Compression via Knowledge Transfer and Distillation
However, deploying such high performing models to resource constraint devices or real-time applications is challenging.
Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric
Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood.
Query-efficient Meta Attack to Deep Neural Networks
Black-box attack methods aim to infer suitable attack patterns to targeted DNN models by only using output feedback of the models and the corresponding input queries.
Distilling Object Detectors with Fine-grained Feature Imitation
To address the challenge of distilling knowledge in detection model, we propose a fine-grained feature imitation method exploiting the cross-location discrepancy of feature response.
Unsupervised Image Noise Modeling with Self-Consistent GAN
They jointly facilitate unsupervised learning of a noise model for various noise types.
PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
We therefore propose a novel Position-Velocity Recurrent Encoder-Decoder (PVRED) for human motion prediction, which makes full use of pose velocities and temporal positional information.
Delving into 3D Action Anticipation from Streaming Videos
Action anticipation, which aims to recognize the action with a partial observation, becomes increasingly popular due to a wide range of applications.
Neural Epitome Search for Architecture-Agnostic Network Compression
The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs).
Central Similarity Quantization for Efficient Image and Video Retrieval
In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy.
PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set.
Ranked #70 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Single-Stage Multi-Person Pose Machines
Based on SPR, we develop the SPM model that can directly predict structured poses for multiple persons in a single stage, and thus offer a more compact pipeline and attractive efficiency advantage over two-stage methods.
Ranked #3 on
Keypoint Detection
on MPII Multi-Person
Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
Existing video-based human pose estimation methods extensively apply large networks onto every frame in the video to localize body joints, which suffer high computational cost and hardly meet the low-latency requirement in realistic applications.
Ranked #3 on
2D Human Pose Estimation
on JHMDB (2D poses only)
Hierarchic Neighbors Embedding
Manifold learning now plays a very important role in machine learning and many relevant applications.
PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
In this paper, we address the makeup transfer task, which aims to transfer the makeup from a reference image to a source image.
PROTOTYPE-ASSISTED ADVERSARIAL LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION
Previous adversarial learning methods condition domain alignment only on pseudo labels, but noisy and inaccurate pseudo labels may perturb the multi-class distribution embedded in probabilistic predictions, hence bringing insufficient alleviation to the latent mismatch problem.
Revisiting Knowledge Distillation via Label Smoothing Regularization
Without any extra computation cost, Tf-KD achieves up to 0. 65\% improvement on ImageNet over well-established baseline models, which is superior to label smoothing regularization.
Towards Disentangling Non-Robust and Robust Components in Performance Metric
Then, we show by experiments that DNNs under standard training rely heavily on optimizing the non-robust component in achieving decent performance.
Prototype Recalls for Continual Learning
Without tampering with the performance on initial tasks, our method learns novel concepts given a few training examples of each class in new tasks.
Hierarchical Neural Architecture Search via Operator Clustering
Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS.
Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning
In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided.
Compressed Video Action Recognition with Refined Motion Vector
Although CNN has reached satisfactory performance in image-related tasks, using CNN to process videos is much more challenging due to the enormous size of raw video streams.
On Robustness of Neural Ordinary Differential Equations
We then provide an insightful understanding of this phenomenon by exploiting a certain desirable property of the flow of a continuous-time ODE, namely that integral curves are non-intersecting.
Decoupling Representation and Classifier for Long-Tailed Recognition
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem.
Ranked #3 on
Long-tail learning with class descriptors
on CUB-LT
Classification Calibration for Long-tail Instance Segmentation
In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals.
Efficient Meta Learning via Minibatch Proximal Update
We address the problem of meta-learning which learns a prior over hypothesis from a sample of meta-training tasks for fast adaptation on meta-testing tasks.
Efficient Differentiable Neural Architecture Search with Meta Kernels
We demonstrate the effectiveness of our search strategy by conducting extensive experiments.
Zoom in to where it matters: a hierarchical graph based model for mammogram analysis
In clinical practice, human radiologists actually review medical images with high resolution monitors and zoom into region of interests (ROIs) for a close-up examination.
PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection
Human and object points are the center of the detection boxes, and the interaction point is the midpoint of the human and object points.
Ranked #25 on
Human-Object Interaction Detection
on V-COCO
RC-DARTS: Resource Constrained Differentiable Architecture Search
In this paper, we propose the resource constrained differentiable architecture search (RC-DARTS) method to learn architectures that are significantly smaller and faster while achieving comparable accuracy.
MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection
Recommender systems often face heterogeneous datasets containing highly personalized historical data of users, where no single model could give the best recommendation for every user.
The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up
TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease.
ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
Empirical results show that state-of-the-art models have an outstanding ability to capture biases contained in the dataset with high accuracy on EASY set.
Ranked #1 on
Logical Reasoning Question Answering
on ReClor
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain.
Ranked #1 on
Source-Free Domain Adaptation
on VisDA-2017
Cross-layer Feature Pyramid Network for Salient Object Detection
Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection.
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
On one hand, negative transfer results in misclassification of target samples to the classes only present in the source domain.
Ranked #2 on
Partial Domain Adaptation
on ImageNet-Caltech
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing.
Ranked #32 on
Semantic Segmentation
on Cityscapes test
Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation
To successfully align the multi-modal data structures across domains, the following works exploit discriminative information in the adversarial training process, e. g., using multiple class-wise discriminators and introducing conditional information in input or output of the domain discriminator.
RAIN: A Simple Approach for Robust and Accurate Image Classification Networks
However, similar to existing preprocessing-based methods, the randomized process will degrade the prediction accuracy.
Boosting Few-Shot Learning With Adaptive Margin Loss
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples.
Ranked #1 on
Few-Shot Image Classification
on ImageNet (1-shot)
Understanding and Resolving Performance Degradation in Graph Convolutional Networks
In this work, we study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.
Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
In this paper, we propose a novel multi-miner framework to perform a region mining process that adapts to diverse object sizes and is thus able to mine more integral and finer object regions.
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.
Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation
In this work, we propose a novel framework, Inference Stage Optimization (ISO), for improving the generalizability of 3D pose models when source and target data come from different pose distributions.
Ranked #118 on
3D Human Pose Estimation
on 3DPW
(PA-MPJPE metric)
Local Grid Rendering Networks for 3D Object Detection in Point Clouds
The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns.
Rethinking Bottleneck Structure for Efficient Mobile Network Design
In this paper, we rethink the necessity of such design changes and find it may bring risks of information loss and gradient confusion.
Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
ATDOC alleviates the classifier bias by introducing an auxiliary classifier for target data only, to improve the quality of pseudo labels.
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
Self-supervised learning (SSL) has been proved very effective at learning representations from unlabeled data in the image domain.
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals.
Few-shot Classification via Adaptive Attention
To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and generate soft attention to refine the representation such that the relevant features from the query and support samples can be extracted for a better few-shot classification.
ConvBERT: Improving BERT with Span-based Dynamic Convolution
The novel convolution heads, together with the rest self-attention heads, form a new mixed attention block that is more efficient at both global and local context learning.
Dual Adversarial Auto-Encoders for Clustering
By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of Auto-encoders.
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years.
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
The result shows that (1) the escaping time of both SGD and ADAM~depends on the Radon measure of the basin positively and the heaviness of gradient noise negatively; (2) for the same basin, SGD enjoys smaller escaping time than ADAM, mainly because (a) the geometry adaptation in ADAM~via adaptively scaling each gradient coordinate well diminishes the anisotropic structure in gradient noise and results in larger Radon measure of a basin; (b) the exponential gradient average in ADAM~smooths its gradient and leads to lighter gradient noise tails than SGD.
A Simple Baseline for Pose Tracking in Videos of Crowded Scenes
This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events.
Towards Accurate Human Pose Estimation in Videos of Crowded Scenes
In this paper, we focus on improving human pose estimation in videos of crowded scenes from the perspectives of exploiting temporal context and collecting new data.
Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes
Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes.
Improving Generalization in Reinforcement Learning with Mixture Regularization
Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments.
