Search Results for author:
Found 270 papers, 155 papers with code
Recover Canonical-View Faces in the Wild with Deep Neural Networks
Face images in the wild undergo large intra-personal variations, such as poses, illuminations, occlusions, and low resolutions, which cause great challenges to face-related applications.
Switchable Deep Network for Pedestrian Detection
In this paper, we propose a Switchable Deep Network (SDN) for pedestrian detection.
Deep Learning Multi-View Representation for Face Recognition
Intriguingly, even without accessing 3D data, human not only can recognize face identity, but can also imagine face images of a person under different viewpoints given a single 2D image, making face perception in the brain robust to view changes.
Learning Deep Representation for Face Alignment with Auxiliary Attributes
In this study, we show that landmark detection or face alignment task is not a single and independent problem.
Ranked #13 on
Unsupervised Facial Landmark Detection
on MAFL
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty.
Deep Learning Face Attributes in the Wild
LNet is pre-trained by massive general object categories for face localization, while ANet is pre-trained by massive face identities for attribute prediction.
Ranked #6 on
Facial Attribute Classification
on LFWA
Pedestrian Detection aided by Deep Learning Semantic Tasks
Rather than expensively annotating scene attributes, we transfer attributes information from existing scene segmentation datasets to the pedestrian dataset, by proposing a novel deep model to learn high-level features from multiple tasks and multiple data sources.
Ranked #30 on
Pedestrian Detection
on Caltech
Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations
Intriguingly, even without accessing 3D data, human not only can recognize face identity, but can also imagine face images of a person under different viewpoints given a single 2D image, making face perception in the brain robust to view changes.
DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
In this paper, we propose deformable deep convolutional neural networks for generic object detection.
Learning to Recognize Pedestrian Attribute
Learning to recognize pedestrian attributes at far distance is a challenging problem in visual surveillance since face and body close-shots are hardly available; instead, only far-view image frames of pedestrian are given.
Clothing Co-Parsing by Joint Image Segmentation and Labeling
This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations.
A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
Updated on 24/09/2015: This update provides preliminary experiment results for fine-grained classification on the surveillance data of CompCars.
Ranked #5 on
Fine-Grained Image Classification
on CompCars
Semantic Image Segmentation via Deep Parsing Network
This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts.
Ranked #89 on
Semantic Segmentation
on Cityscapes test
Learning Social Relation Traits from Face Images
Social relation defines the association, e. g, warm, friendliness, and dominance, between two or more people.
From Facial Parts Responses to Face Detection: A Deep Learning Approach
In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW.
WIDER FACE: A Face Detection Benchmark
Face detection is one of the most studied topics in the computer vision community.
Ranked #34 on
Face Detection
on WIDER Face (Medium)
Deep Learning Strong Parts for Pedestrian Detection
Third, each part detector in DeepParts is a strong detector that can detect pedestrian by observing only a part of a proposal.
DeepFashion: Powering Robust Clothes Recognition and Retrieval With Rich Annotations
To demonstrate the advantages of DeepFashion, we propose a new deep model, namely FashionNet, which learns clothing features by jointly predicting clothing attributes and landmarks.
Deep Learning Markov Random Field for Semantic Segmentation
Semantic segmentation tasks can be well modeled by Markov Random Field (MRF).
Fashion Landmark Detection in the Wild
Fashion landmark is also compared to clothing bounding boxes and human joints in two applications, fashion attribute prediction and clothes retrieval, showing that fashion landmark is a more discriminative representation to understand fashion images.
From Facial Expression Recognition to Interpersonal Relation Prediction
Unlike existing models that typically learn from facial expression labels alone, we devise an effective multitask network that is capable of learning from rich auxiliary attributes such as gender, age, and head pose, beyond just facial expression data.
Faceness-Net: Face Detection through Deep Facial Part Responses
We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision.
Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade
Third, in comparison to MC, LC is an end-to-end trainable framework, allowing joint learning of all sub-models.
Ranked #22 on
Semantic Segmentation
on PASCAL VOC 2012 test
Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output.
Learning Object Interactions and Descriptions for Semantic Image Segmentation
This work significantly increases segmentation accuracy of CNNs by learning from an Image Descriptions in the Wild (IDW) dataset.
Learning Deep Architectures via Generalized Whitened Neural Networks
Whitened Neural Network (WNN) is a recent advanced deep architecture, which improves convergence and generalization of canonical neural networks by whitening their internal hidden representation.
Video Object Segmentation with Re-identification
Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.
Unconstrained Fashion Landmark Detection via Hierarchical Recurrent Transformer Networks
This work addresses unconstrained fashion landmark detection, where clothing bounding boxes are not provided in both training and test.
Deep Dual Learning for Semantic Image Segmentation
The estimated labelmaps that capture accurate object classes and boundaries are used as ground truths in training to boost performance.
Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
The key of this new form of learning is to design a proxy task (e. g. image colorization), from which a discriminative loss can be formulated on unlabeled data.
Spatial As Deep: Spatial CNN for Traffic Scene Understanding
Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pixels across rows and columns of an image is not fully explored.
Ranked #50 on
Lane Detection
on CULane
On Batch Adaptive Training for Deep Learning: Lower Loss and Larger Step Size
Mini-batch gradient descent and its variants are commonly used in deep learning.
Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches
As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer.
FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
Existing methods typically formulate GAN as a two-player game, where a discriminator distinguishes face images from the real and synthesized domains, while a generator reduces its discriminativeness by synthesizing a face of photo-realistic quality.
Differentiable Learning-to-Normalize via Switchable Normalization
We hope SN will help ease the usage and understand the normalization techniques in deep learning.
SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
To address the above issues, we present a novel and practical deep architecture for video person re-identification termed Self-and-Collaborative Attention Network (SCAN).
Talking Face Generation by Adversarially Disentangled Audio-Visual Representation
Talking face generation aims to synthesize a sequence of face images that correspond to a clip of speech.
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
IBN-Net carefully integrates Instance Normalization (IN) and Batch Normalization (BN) as building blocks, and can be wrapped into many advanced deep networks to improve their performances.
Ranked #3 on
All-day Semantic Segmentation
on All-day CityScapes
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
Secondly, TSD significantly reduces the computations to run video action recognition with compressed frames on the cloud, while maintaining high recognition accuracies.
Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents
Additionally, a "low-level sharing, high-level splitting" structure of CNN is designed to handle the documents from different content domains.
Towards Understanding Regularization in Batch Normalization
Batch Normalization (BN) improves both convergence and generalization in training neural networks.
Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?
Our results suggest that (1) using distinct normalizers improves both learning and generalization of a ConvNet; (2) the choices of normalizers are more related to depth and batch size, but less relevant to parameter initialization, learning rate decay, and solver; (3) different tasks and datasets have different behaviors when learning to select normalizers.
Kalman Normalization: Normalizing Internal Representations Across Network Layers
In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of micro-batches.
FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis
In the second stage, they compete in the image domain to render photo-realistic images that contain high diversity but preserve identity.
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
A strong baseline is proposed, called Match R-CNN, which builds upon Mask R-CNN to solve the above four tasks in an end-to-end manner.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
SSN: Learning Sparse Switchable Normalization via SparsestMax
Unlike $\ell_1$ and $\ell_0$ constraints that impose difficulties in optimization, we turn this constrained optimization problem into feed-forward computation by proposing SparsestMax, which is a sparse version of softmax.
Switchable Whitening for Deep Representation Learning
Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying different whitening methods as well as standardization methods.
Ranked #6 on
Robust Object Detection
on DWD
Atom Responding Machine for Dialog Generation
To enrich the generated responses, ARM introduces a large number of molecule-mechanisms as various responding styles, which are conducted by taking different combinations from a few atom-mechanisms.
Switchable Normalization for Learning-to-Normalize Deep Representation
Analyses of SN are also presented to answer the following three questions: (a) Is it useful to allow each normalization layer to select its own normalizer?
MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
To overcome these drawbacks, we propose a novel framework termed MaskGAN, enabling diverse and interactive face manipulation.
Deep Self-Learning From Noisy Labels
Unlike previous works constrained by many conditions, making them infeasible to real noisy cases, this work presents a novel deep self-learning framework to train a robust network on the real noisy datasets without extra supervision.
Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once
Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods.
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
ResNeXt, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers.
Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid
To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales.
Ranked #4 on
Image Retrieval
on DeepFashion - Consumer-to-shop
(Rank-1 metric)
Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization
Experiment results show that SCT improves accuracy of single Resnet-50 on ImageNet by 1. 7% and 11. 5% accuracy when testing on image sizes of 224 and 128 respectively.
PDA: Progressive Data Augmentation for General Robustness of Deep Neural Networks
In other words, DNNs trained with PDA are able to obtain more robustness against both adversarial attacks as well as common corruptions than the recent state-of-the-art methods.
TextSR: Content-Aware Text Super-Resolution Guided by Recognition
Nonetheless, most of the previous methods may not work well in recognizing text with low resolution which is often seen in natural scene images.
Channel Equilibrium Networks
However, over-sparse CNNs have many collapsed channels (i. e. many channels with undesired zero values), impeding their learning ability.
PolarMask: Single Shot Instance Segmentation with Polar Representation
In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used as a mask prediction module for instance segmentation, by easily embedding it into most off-the-shelf detection methods.
Ranked #100 on
Instance Segmentation
on COCO test-dev
Vision-Infused Deep Audio Inpainting
Extensive experiments demonstrate that our framework is capable of inpainting realistic and varying audio segments with or without visual contexts.
Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow
Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference.
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information.
Ranked #17 on
Vehicle Pose Estimation
on KITTI Cars Hard
How Does BN Increase Collapsed Neural Network Filters?
This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.
Channel Equilibrium Networks for Learning Deep Representation
Unlike prior arts that simply removed the inhibited channels, we propose to "wake them up" during training by designing a novel neural building block, termed Channel Equilibrium (CE) block, which enables channels at the same layer to contribute equally to the learned representation.
Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\leftrightarrow$Preserving Image Content
First, a semantic layout generation module utilizes semantic segmentation of the reference image to progressively predict the desired semantic layout after try-on.
Ranked #4 on
Virtual Try-on
on VITON
(IS metric)
Domain-Adaptive Few-Shot Learning
Existing few-shot learning (FSL) methods make the implicit assumption that the few target class samples are from the same domain as the source class samples.
Exemplar Normalization for Learning Deep Representation
This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn different normalization methods for different convolutional layers and image samples of a deep network.
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Learning a good image prior is a long-term goal for image restoration and manipulation.
Segmenting Transparent Objects in the Wild
To address this important problem, this work proposes a large-scale dataset for transparent object segmentation, named Trans10K, consisting of 10, 428 images of real scenarios with carefully manual annotations, which are 10 times larger than the existing datasets.
Ranked #4 on
Semantic Segmentation
on Trans10K
AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, showing that Adam's fast convergence would possibly lead the algorithm to local minimums.
Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters.
Learning a Reinforced Agent for Flexible Exposure Bracketing Selection
Automatically selecting exposure bracketing (images exposed differently) is important to obtain a high dynamic range image by using multi-exposure fusion.
3D Human Mesh Regression with Dense Correspondence
This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space (i. e. a 2D space used for texture mapping of 3D mesh).
Ranked #1 on
3D Human Reconstruction
on Surreal
Whole-Body Human Pose Estimation in the Wild
This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet.
Ranked #8 on
2D Human Pose Estimation
on COCO-WholeBody
Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation
The modules of HGG can be trained end-to-end with the keypoint detection network and is able to supervise the grouping process in a hierarchical manner.
Ranked #3 on
Keypoint Detection
on OCHuman
Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction
Existing work addressed this challenge by either learning social spatial interactions represented by the positions of a group of pedestrians, while ignoring their temporal coherence (\textit{i. e.} dependencies between different long trajectories), or by understanding the complicated scene layout (\textit{e. g.} scene segmentation) to ensure safe navigation.
AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
Unlike previous works that merely employed visual features for text detection, this work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter), which learns both visual and linguistic features to significantly reduce ambiguity in text detection.
Compensation Tracker: Reprocessing Lost Object for Multi-Object Tracking
Based on simple and traditional methods, we propose a compensation tracker to further alleviate the lost tracking problem caused by missing detection.
Webly Supervised Image Classification with Self-Contained Confidence
Therefore, a simple yet effective WSL framework is proposed.
Ranked #7 on
Image Classification
on WebVision-1000
RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning
Despite the remarkable successes of Convolutional Neural Networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN.
UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation
Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network.
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Through our investigation, we found that such a pre-trained GAN indeed contains rich 3D knowledge and thus can be used to recover 3D shape from a single 2D image in an unsupervised manner.
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location.
Ranked #5 on
2D Object Detection
on CeyMo
Polygon-free: Unconstrained Scene Text Detection with Box Annotations
For example, without using polygon annotations, PSENet achieves an 80. 5% F-score on TotalText [3] (vs. 80. 9% of fully supervised counterpart), 31. 1% better than training directly with upright bounding box annotations, and saves 80%+ labeling costs.
What Makes for End-to-End Object Detection?
We identify that classification cost in matching cost is the main ingredient: (1) previous detectors only consider location cost, (2) by additionally introducing classification cost, previous detectors immediately produce one-to-one prediction during inference.
TransTrack: Multiple Object Tracking with Transformer
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems.
Ranked #7 on
Multi-Object Tracking
on SportsMOT
(using extra training data)
Multi-Object Tracking
Multiple Object Tracking with Transformer
+3
Bringing Events Into Video Deblurring With Non-Consecutively Blurry Frames
EFM can also be easily incorporated into existing deblurring networks, making event-driven deblurring task benefit from state-of-the-art deblurring methods.
Rethinking the Pruning Criteria for Convolutional Neural Network
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), and various pruning criteria have been proposed to remove the redundant filters of CNNs.
STAR: A Structure-Aware Lightweight Transformer for Real-Time Image Enhancement
STAR is a general architecture that can be easily adapted to different image enhancement tasks.
Watch Only Once: An End-to-End Video Action Detection Framework
WOO takes a unified video backbone to simultaneously extract features for actor location and action classification.
Self-Supervised Video Representation Learning with Constrained Spatiotemporal Jigsaw
With the constrained jigsaw puzzles, instead of solving them directly, which could still be extremely hard, we carefully design four surrogate tasks that are more solvable but meanwhile still ensure that the learned representation is sensitive to spatiotemporal continuity at both the local and global levels.
Segmenting Transparent Object in the Wild with Transformer
This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation dataset.
Ranked #3 on
Semantic Segmentation
on Trans10K
DetCo: Unsupervised Contrastive Learning for Object Detection
Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach, named DetCo, which fully explores the contrasts between global image and local image patches to learn discriminative representations for object detection.
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation
Prior arts often discretize the network weights by carefully tuning hyper-parameters of quantization (e. g. non-uniform stepsize and layer-wise bitwidths), which are complicated and sub-optimal because the full-precision and low-precision models have a large discrepancy.
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Unlike the recently-proposed Transformer model (e. g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks.
Ranked #5 on
Semantic Segmentation
on SynPASS
Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors
Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks.
Parser-Free Virtual Try-on via Distilling Appearance Flows
A recent pioneering work employed knowledge distillation to reduce the dependency of human parsing, where the try-on images produced by a parser-based method are used as supervisions to train a "student" network without relying on segmentation, making the student mimic the try-on ability of the parser-based model.
Ranked #1 on
Virtual Try-on
on MPV
Disentangled Cycle Consistency for Highly-realistic Virtual Try-On
To this end, DCTON can be naturally trained in a self-supervised manner following cycle consistency learning.
Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization
(1) We divide input image into small patches and adopt TIN, successfully transferring image style with arbitrary high-resolution.
Learning Versatile Neural Architectures by Propagating Network Codes
(4) Thorough studies of NCP on inter-, cross-, and intra-tasks highlight the importance of cross-task neural architecture design, i. e., multitask neural architectures and architecture transferring between different tasks.
Going Deeper Into Face Detection: A Survey
In this work, we provide a detailed overview of some of the most representative deep learning based face detection methods by grouping them into a few major categories, and present their core architectural designs and accuracies on popular benchmarks.
PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond
Extensive experiments demonstrate the effectiveness of both PolarMask and PolarMask++, which achieve competitive results on instance segmentation in the challenging COCO dataset with single-model and single-scale training and testing, as well as new state-of-the-art results on rotate text detection and cell segmentation.
Ranked #81 on
Instance Segmentation
on COCO test-dev
(using extra training data)
When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks
However, unlike human vision that is robust to various data corruptions such as blur and pixelation, current pose estimators are easily confused by these corruptions.
BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
To address this problem, we develop a probability-based pruning algorithm, called batch whitening channel pruning (BWCP), which can stochastically discard unimportant channels by modeling the probability of a channel being activated.
Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application
In this paper, we study the problem of extracting variable-depth "logical document hierarchy" from long documents, namely organizing the recognized "physical document objects" into hierarchical structures.
ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
Human pose estimation has achieved significant progress in recent years.
Ranked #23 on
Pose Estimation
on COCO test-dev
(using extra training data)
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders.
Ranked #1 on
Semantic Segmentation
on COCO-Stuff full
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
Last, we proposed an efficient fine-grained search strategy to train HR-NAS, which effectively explores the search space, and finds optimal architectures given various tasks and computation resources.
PVT v2: Improved Baselines with Pyramid Vision Transformer
We hope this work will facilitate state-of-the-art Transformer researches in computer vision.
Ranked #23 on
Object Detection
on COCO-O
Multi-Compound Transformer for Accurate Biomedical Image Segmentation
The recent vision transformer(i. e. for image classification) learns non-local attentive interaction of different patch tokens.
Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformation
For example, STFT improves the still image baseline FCOS by 10. 6% and 20. 6% on the comprehensive F1-score of the polyp localization task in CVC-Clinic and ASUMayo datasets, respectively, and outperforms the state-of-the-art video-based method by 3. 6% and 8. 0%, respectively.
CycleMLP: A MLP-like Architecture for Dense Prediction
We build a family of models which surpass existing MLPs and even state-of-the-art Transformer-based models, e. g., Swin Transformer, while using fewer parameters and FLOPs.
Ranked #15 on
Semantic Segmentation
on DensePASS
End-to-End Dense Video Captioning with Parallel Decoding
Dense video captioning aims to generate multiple associated captions with their temporal locations from the video.
Ranked #5 on
Dense Video Captioning
on YouCook2
Adversarial Robustness for Unsupervised Domain Adaptation
Extensive Unsupervised Domain Adaptation (UDA) studies have shown great success in practice by learning transferable representations across a labeled source domain and an unlabeled target domain with deep models.
Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers
Specifically, we supervise the attention modules in the mask decoder in a layer-wise manner.
Ranked #4 on
Panoptic Segmentation
on COCO test-dev
Towards High-Quality Temporal Action Detection with Sparse Proposals
Towards high-quality temporal action detection, we introduce Sparse Proposals to interact with the hierarchical features.
Scale-Invariant Teaching for Semi-Supervised Object Detection
Furthermore, the limited annotations in semi-supervised learning scale up the challenges: large variance of object sizes and class imbalance (i. e., the extreme ratio between background and object), hindering the performance of prior arts.
Objects in Semantic Topology
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.
Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks.
Ranked #1 on
Multiple Object Tracking
on BDD100K val
Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language
This is achieved by seamlessly integrating three components: a visual perception module, a concept learner, and a differentiable physics engine.
FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
We propose an accurate and efficient scene text detection framework, termed FAST (i. e., faster arbitrarily-shaped text detector).
Ranked #2 on
Scene Text Detection
on MSRA-TD500
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion
A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID) for object association.
Model-Based Reinforcement Learning via Imagination with Derived Memory
Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment.
Model-based Reinforcement Learning
reinforcement-learning
+1
Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
Compressed Video Contrastive Learning
To enhance the representation ability of the motion vectors, hence the effectiveness of our method, we design a cross guidance contrastive learning algorithm based on multi-instance InfoNCE loss, where motion vectors can take supervision signals from RGB frames and vice versa.
Dynamic Token Normalization Improves Vision Transformers
It is difficult for Transformers to capture inductive bias such as the positional context in an image with LN.
MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples
This work proposes a novel framework named MetaCloth via meta-learning, which is able to learn unseen tasks of dense fashion landmark detection with only a few annotated samples.
Language as Queries for Referring Video Object Segmentation
Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames.
Ranked #3 on
Referring Expression Segmentation
on A2D Sentences
(using extra training data)
MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning
Dancing video retargeting aims to synthesize a video that transfers the dance movements from a source video to a target person.
Bridging Video-text Retrieval with Multiple Choice Questions
As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e. g., action recognition with linear evaluation.
Ranked #8 on
Zero-Shot Video Retrieval
on MSVD
RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs
Blind face restoration is to recover a high-quality face image from unknown degradations.
Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization
PL approaches apply pseudo-labels to unlabeled data, and then train the model with a combination of the labeled and pseudo-labeled data iteratively.
DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations
AI-aided drug discovery (AIDD) is gaining increasing popularity due to its promise of making the search for new pharmaceuticals quicker, cheaper and more efficient.
Context Autoencoder for Self-Supervised Representation Learning
The pretraining tasks include two tasks: masked representation prediction - predict the representations for the masked patches, and masked patch reconstruction - reconstruct the masked patches.
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning
One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments.
WegFormer: Transformers for Weakly Supervised Semantic Segmentation
Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to sub-optimal results.
End-to-End Video Text Spotting with Transformer
Recent video text spotting methods usually require the three-staged pipeline, i. e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results.
Compression of Generative Pre-trained Language Models via Quantization
We find that previous quantization methods fail on generative tasks due to the \textit{homogeneous word embeddings} caused by reduced capacity, and \textit{varied distribution of weights}.
Scale-Equivalent Distillation for Semi-Supervised Object Detection
Further, we overcome these challenges by introducing a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
DaViT: Dual Attention Vision Transformers
We show that these two self-attentions complement each other: (i) since each channel token contains an abstract representation of the entire image, the channel attention naturally captures global interactions and representations by taking all spatial positions into account when computing attention scores between channels; (ii) the spatial attention refines the local representations by performing fine-grained interactions across spatial locations, which in turn helps the global information modeling in channel attention.
M$^2$BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation
In this paper, we propose M$^2$BEV, a unified framework that jointly performs 3D object detection and map segmentation in the Birds Eye View~(BEV) space with multi-camera image inputs.
Semantic-Aware Pretraining for Dense Video Captioning
This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021.
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
Vision transformers have achieved great successes in many computer vision tasks.
Ranked #4 on
2D Human Pose Estimation
on COCO-WholeBody
MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval
Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed local semantics.
Ranked #7 on
Zero-Shot Video Retrieval
on MSVD
An Empirical Investigation of Representation Learning for Imitation
We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation across several environment suites.
Flow-based Recurrent Belief State Learning for POMDPs
Furthermore, we show that the learned belief states can be plugged into downstream RL algorithms to improve performance.
AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
To address this challenge, we propose an effective adaptation approach for Transformer, namely AdaptFormer, which can adapt the pre-trained ViTs into many different image and video tasks efficiently.
CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
In this paper, we propose CO^3, namely Cooperative Contrastive Learning and Contextual Shape Prediction, to learn 3D representation for outdoor-scene point clouds in an unsupervised manner.
AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation
Constraint by the high cost of collecting and labeling 3D medical data, most of the deep learning models to date are driven by datasets with a limited number of organs of interest or samples, which still limits the power of modern deep models and makes it difficult to provide a fully comprehensive and fair estimate of various methods.
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
In visual control, learning transferable state representation that can transfer between different control tasks is important to reduce the training sample size.
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors, or crawled from the internet followed by elaborate data cleaning techniques.
Exploiting Context Information for Generic Event Boundary Captioning
Previous methods only process the information of a single boundary at a time, which lacks utilization of video context information.
Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive.
Ranked #2 on
Transferability
on classification benchmark
Towards Grand Unification of Object Tracking
We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters.
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+3
Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e. g., text detection, tracking, recognition) in a real-time end-to-end trainable framework.
Pose for Everything: Towards Category-Agnostic Pose Estimation
In this paper, we introduce the task of Category-Agnostic Pose Estimation (CAPE), which aims to create a pose estimation model capable of detecting the pose of any class of object given only a few samples with keypoint definition.
Ranked #4 on
2D Pose Estimation
on MP-100
3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal
Unlike most previous works that directly predict the 3D poses of two interacting hands simultaneously, we propose to decompose the challenging interacting hand pose estimation task and estimate the pose of each hand separately.
PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation
Human pose estimation aims to accurately estimate a wide variety of human poses.
ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts.
Ranked #2 on
2D Human Pose Estimation
on COCO-WholeBody
Rethinking Resolution in the Context of Efficient Video Recognition
Our key finding is that the major cause of degradation is not information loss in the down-sampling process, but rather the mismatch between network architecture and input scale.
FedVeca: Federated Vectorized Averaging on Non-IID Data with Adaptive Bi-directional Global Objective
However, the clients' Non-Independent and Identically Distributed (Non-IID) data negatively affect the trained model, and clients with different numbers of local updates may cause significant gaps to the local gradients in each communication round.
Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years.
Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
End-to-end autonomous driving provides a feasible way to automatically maximize overall driving system performance by directly mapping the raw pixels from a front-facing camera to control signals.
Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
This paper addresses such a challenge by Decomposed Mutual INformation Optimization (DOMINO) for context learning, which explicitly learns a disentangled context to maximize the mutual information between the context and historical trajectories, while minimizing the state transition prediction error.
Large-batch Optimization for Dense Visual Predictions
To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (AGVM), which can train dense visual predictors with very large batch size, enabling several benefits more appealing than prior arts.
Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning
The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging.
Model-based Reinforcement Learning
reinforcement-learning
+1
MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning
Firstly, MaskPlace recasts placement as a problem of learning pixel-level visual representation to comprehensively describe millions of modules on a chip, enabling placement in a high-resolution canvas and a large action space.
Learning Object-Language Alignments for Open-Vocabulary Object Detection
In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data.
Policy Adaptation from Foundation Model Feedback
When deploying the trained policy to a new task or a new environment, we first let the policy play with randomly generated instructions to record the demonstrations.
EC2: Emergent Communication for Embodied Control
We learn embodied representations of video trajectories, emergent language, and natural language using a language model, which is then used to finetune a lightweight policy network for downstream control.
Segment Every Reference Object in Spatial and Temporal Spaces
In this work, we end the current fragmented situation and propose UniRef to unify the three reference-based object segmentation tasks with a single architecture.
RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation
These queries are then processed iteratively by a BEV-Evolving decoder, which selectively aggregates deep features from either LiDAR, cameras, or both modalities.
Fast-BEV: Towards Real-time On-vehicle Bird's-Eye View Perception
Recently, the pure camera-based Bird's-Eye-View (BEV) perception removes expensive Lidar sensors, making it a feasible solution for economical autonomous driving.
Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts.
AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
For example, AdaptDiffuser not only outperforms the previous art Diffuser by 20. 8% on Maze2D and 7. 5% on MuJoCo locomotion, but also adapts better to new tasks, e. g., KUKA pick-and-place, by 27. 9% without requiring additional expert data.
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
Our framework is easily extensible to tasks covering visually-grounded language understanding and generation.
Universal Instance Perception as Object Discovery and Retrieval
All instance perception tasks aim at finding certain objects specified by some queries such as category names, language expressions, and target annotations, but this complete field has been split into multiple independent subtasks.
Ranked #1 on
Referring Expression Segmentation
on RefCoCo val
(using extra training data)
Described Object Detection
Generalized Referring Expression Comprehension
+15
Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Prediction
Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities.
Dense Distinct Query for End-to-End Object Detection
Concretely, we first lay dense queries like traditional detectors and then select distinct ones for one-to-one assignments.
Ranked #3 on
Object Detection
on CrowdHuman (full body)
Accelerating Vision-Language Pretraining with Free Language Modeling
FLM successfully frees the prediction rate from the tie-up with the corruption rate while allowing the corruption spans to be customized for each token to be predicted.
Real-time Controllable Denoising for Image and Video
Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness.
DDP: Diffusion Model for Dense Visual Prediction
We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline.
Ranked #2 on
Monocular Depth Estimation
on SUN-RGBD
Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning
We evaluate our soft neighbor contrastive learning method (SNCLR) on standard visual recognition benchmarks, including image classification, object detection, and instance segmentation.
DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving
In addition, we propose a new task, end-to-end motion and accident prediction, which can be used to directly evaluate the accident prediction ability for different autonomous driving algorithms.
EGC: Image Generation and Classification via a Diffusion Energy-Based Model
Learning image classification and image generation using the same set of network parameters is a challenging problem.
Multi-Level Contrastive Learning for Dense Prediction Task
We extend our pretext task to supervised pre-training, which achieves a similar performance to self-supervised learning.
Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention
When looking at an image, we can decompose the scene into entities and their parts as well as obtain the dependencies between them.
Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following
ECL consists of: (i) an instruction parser that translates the natural languages into executable programs; (ii) an embodied concept learner that grounds visual concepts based on language descriptions; (iii) a map constructor that estimates depth and constructs semantic maps by leveraging the learned concepts; and (iv) a program executor with deterministic policies to execute each program.
Graph-based Topology Reasoning for Driving Scenes
Understanding the road genome is essential to realize autonomous driving.
Ranked #5 on
3D Lane Detection
on OpenLane-V2 val
RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer
Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy.
MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation
These queries are then processed iteratively by a BEV-Evolving decoder, which selectively aggregates deep features from either LiDAR, cameras, or both modalities.
EC^2: Emergent Communication for Embodied Control
We learn embodied representations of video trajectories, emergent language, and natural language using a language model, which is then used to finetune a lightweight policy network for downstream control.
OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments.
$π$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
Foundation models have achieved great advances in multi-task learning with a unified interface of unimodal and multimodal tasks.
MultiModal-GPT: A Vision and Language Model for Dialogue with Humans
To further enhance the ability to chat with humans of the MultiModal-GPT, we utilize language-only instruction-following data to train the MultiModal-GPT jointly.
InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language
Different from existing interactive systems that rely on pure language, by incorporating pointing instructions, the proposed iGPT significantly improves the efficiency of communication between users and chatbots, as well as the accuracy of chatbots in vision-centric tasks, especially in complicated visual scenarios where the number of objects is greater than 2.
