Search Results for author:
Found 257 papers, 141 papers with code
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network
In particular, we 1) propose a bifurcated backbone strategy (BBS) to split the multi-level features into teacher and student features, and 2) utilize a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views.
Count- and Similarity-aware R-CNN for Pedestrian Detection
We further introduce a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity.
Learning Attentive and Hierarchical Representations for 3D Shape Recognition
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR).
CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers
To make full use of these sequence-specific samples, {we propose a compact latent network to quickly adjust the tracking model to adapt to new scenes.}
Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification
On the other hand, mutual instance selection further selects reliable and informative instances for training according to the peer-confidence and relationship disagreement of the networks.
Region Graph Embedding Network for Zero-Shot Learning
To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.
StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting
We introduce StyleGaussian, a novel 3D style transfer technique that allows instant transfer of any image's style to a 3D scene at 10 frames per second (fps).
Latent Semantic Consensus For Deterministic Geometric Model Fitting
The principle of LSC is to preserve the latent semantic consensus in both data points and model hypotheses.
Conditional Tuning Network for Few-Shot Adaptation of Segmentation Anything Model
CAT-SAM freezes the entire SAM and adapts its mask decoder and image encoder simultaneously with a small number of learnable parameters.
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives
Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems.
Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation
Finally, we propose a novel self-guided pre-training method for graph representation learning.
Generative Adversarial Network
Graph Representation Learning
+1
DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception
Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space.
Domain Adaptation for Large-Vocabulary Object Detectors
Large-vocabulary object detectors (LVDs) aim to detect objects of many categories, which learn super objectness features and can locate objects accurately while applied to various downstream data.
Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
Such semantic misalignment circulates in pre-training, leading to inferior zero-shot performance in dense predictions due to insufficient visual concepts captured in textual representations.
ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection
Extensive experiments on the PASCAL VOC and COCO datasets show that our ECEA module can assist the few-shot detector to completely predict the object despite some regions failing to appear in the training samples and achieve the new state of the art compared with existing FSOD methods.
Pose-Free Neural Radiance Fields via Implicit Pose Regularization
However, as the pose estimator is trained with only rendered images, the pose estimation is usually biased or inaccurate for real images due to the domain gap between real images and rendered images, leading to poor robustness for the pose estimation of real images and further local minima in joint optimization.
COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation
SF-UniDA methods eliminate the need for direct access to source samples when performing adaptation to the target domain.
WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields
Neural Radiance Field (NeRF) has shown impressive performance in novel view synthesis via implicit scene representation.
A Survey of Label-Efficient Deep Learning for 3D Point Clouds
We address three critical questions in this emerging research field: i) the importance and urgency of label-efficient learning in point cloud processing, ii) the subfields it encompasses, and iii) the progress achieved in this area.
Context-Aware Block Net for Small Object Detection
State-of-the-art object detectors usually progressively downsample the input image until it is represented by small feature maps, which loses the spatial information and compromises the representation of small objects.
Ranked #1 on
Traffic Sign Detection
on TT100K
Graph Transformer GANs for Graph-Constrained House Generation
We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task.
Adaptive Siamese Tracking with a Compact Latent Network
Under this viewing, we perform an in-depth analysis for them through visual simulations and real tracking examples, and find that the failure cases in some challenging situations can be regarded as the issue of missing decisive samples in offline training.
Evolutionary Generalized Zero-Shot Learning
In this work, we propose a novel Evolutionary Generalized Zero-Shot Learning setting, which (i) avoids the domain shift problem in inductive GZSL, and (ii) is more in line with the needs of real-world deployments than transductive GZSL.
Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions from seen states and objects.
Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis
To further capture the change in pose of each part more precisely, we propose a novel part-aware bipartite graph reasoning (PBGR) block to decompose the task of reasoning the global structure transformation with a bipartite graph into learning different local transformations for different semantic body/face parts.
Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
Spatial-Temporal Pyramid Graph Reasoning for Action Recognition
Spatial-temporal relation reasoning is a significant yet challenging problem for video action recognition.
Ranked #35 on
Action Recognition
on Something-Something V1
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
The first is scene-level swapping which exchanges point cloud sectors of two LiDAR scans that are cut along the azimuth axis.
Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit.
RePFormer: Refinement Pyramid Transformer for Robust Facial Landmark Detection
This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection.
Learning Non-target Knowledge for Few-shot Semantic Segmentation
Then, a BG Eliminating Module and a DO Eliminating Module are proposed to successively filter out the BG and DO information from the query feature, based on which we can obtain a BG and DO-free target object segmentation result.
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization
The tangent transfer creates initial augmented samples for improving corruption robustness.
Learning Enriched Features for Fast Image Restoration and Enhancement
In the former case, spatial details are preserved but the contextual information cannot be precisely encoded.
RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.
Audio-Adaptive Activity Recognition Across Video Domains
This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint.
RGBD Object Tracking: An In-depth Review
Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking.
High-resolution Iterative Feedback Network for Camouflaged Object Detection
Spotting camouflaged objects that are visually assimilated into the background is tricky for both object detection algorithms and humans who are usually confused or cheated by the perfectly intrinsic similarities between the foreground objects and the background surroundings.
Highly Accurate Dichotomous Image Segmentation
We present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images.
Ranked #4 on
Dichotomous Image Segmentation
on DIS-TE1
Local and Global GANs with Semantic-Aware Upsampling for Image Generation
To learn more discriminative class-specific feature representations for the local generation, we also propose a novel classification module.
Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data.
Learning to Generalize across Domains on Single Test Samples
We leverage a meta-learning paradigm to learn our model to acquire the ability of adaptation with single samples at training time so as to further adapt itself to each single test sample at test time.
Ranked #1 on
Domain Adaptation
on PACS
Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters
Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its closest filters.
Consistency and Diversity induced Human Motion Segmentation
Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance.
Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond
As for the data, we show that the autonomous driving benchmarks are monotonous in nature, that is, they are not diverse in scenarios and dense in pedestrians.
Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation
To address this, we propose a novel multi-level representation learning approach, which explores the inherent structure of the video content to provide a set of discriminative visual embedding, enabling more effective vision-language semantic alignment.
GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference
In this paper, we propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net, by leveraging labeled information to guide the learning of unlabeled instances.
Generative Kernel Continual learning
Kernel continual learning by \citet{derakhshani2021kernel} has recently emerged as a strong continual learner due to its non-parametric ability to tackle task interference and catastrophic forgetting.
TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning
Analogously, VAT uses the similar feature augmentation encoder to refine the visual features, which are further applied in visual$\rightarrow$attribute decoder to learn visual-based attribute features.
Hierarchical Variational Memory for Few-shot Learning Across Domains
To explore and exploit the importance of different semantic levels, we further propose to learn the weights associated with the prototype at each level in a data-driven way, which enables the model to adaptively choose the most generalizable features.
Specificity-Preserving Federated Learning for MR Image Reconstruction
The core idea is to divide the MR reconstruction model into two parts: a globally shared encoder to obtain a generalized representation at the global level, and a client-specific decoder to preserve the domain-specific properties of each client, which is important for collaborative reconstruction when the clients have unique distribution.
Group-Wise Learning for Weakly Supervised Semantic Segmentation
The framework explicitly encodes semantic dependencies in a group of images to discover rich semantic context for estimating more reliable pseudo ground-truths, which are subsequently employed to train more effective segmentation models.
Multi-Task Neural Processes
Our multi-task neural processes methodologically expand the scope of vanilla neural processes and provide a new way of exploring task relatedness in function spaces for multi-task learning.
Variational Multi-Task Learning with Gumbel-Softmax Priors
Multi-task learning aims to explore task relatedness to improve individual tasks, which is of particular significance in the challenging scenario that only limited data is available for each task.
Deep multi-modal aggregation network for MR image reconstruction with auxiliary modality
Magnetic resonance (MR) imaging produces detailed images of organs and tissues with better contrast, but it suffers from a long acquisition time, which makes the image quality vulnerable to say motion artifacts.
Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
On the other hand, instead of processing the twokinds of data separately, we build a novel dual graph modelto guide the focal stack fusion process using all-focus pat-terns.
Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection
In this paper, we propose a novel consensus-aware dynamic convolution model to explicitly and effectively perform the "summarize and search" process.
Ranked #3 on
Co-Salient Object Detection
on CoSal2015
HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
Specifically, HSVA aligns the semantic and visual domains by adopting a hierarchical two-step adaptation, i. e., structure adaptation and distribution adaptation.
RGB-D Saliency Detection via Cascaded Mutual Information Minimization
In this paper, we introduce a novel multi-stage cascaded learning framework via mutual information minimization to "explicitly" model the multi-modal information between RGB image and depth data.
Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution
Our SANet could explore the areas of high-intensity and low-intensity regions in the "forward" and "reverse" directions with the help of the auxiliary contrast, while learning clearer anatomical structure and edge information for the SR of a target-contrast MR image.
Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation
Annotation burden has become one of the biggest barriers to semantic segmentation.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Discriminative Region-based Multi-Label Zero-Shot Learning
We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes.
Ranked #2 on
Multi-label zero-shot learning
on Open Images V4
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to open surfaces, diverse topologies and complex geometric details.
Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers
Unlike existing CNN-based methods, we adopt a transformer encoder, which learns more powerful and robust representations.
Ranked #9 on
Medical Image Segmentation
on CVC-ColonDB
Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud
We propose an attentive module to fit the sparse feature maps to dense mostly on the object regions through the deformable convolution tower and the supervised mask-guided attention.
From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder
In this paper, we present an Intersection-over-Union (IoU) guided two-stage 3D object detector with a voxel-to-point decoder.
Full-Duplex Strategy for Video Object Segmentation
Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues.
Ranked #7 on
Video Polyp Segmentation
on SUN-SEG-Hard (Unseen)
FREE: Feature Refinement for Generalized Zero-Shot Learning
FREE employs a feature refinement (FR) module that incorporates \textit{semantic$\rightarrow$visual} mapping into a unified generative model to refine the visual features of seen and unseen class samples.
Variational Topic Inference for Chest X-Ray Report Generation
The topics are inferred in a conditional variational inference framework, with each topic governing the generation of a sentence in the report.
Kernel Continual Learning
We further introduce variational random features to learn a data-driven kernel for each task.
Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain generalization (DG), to separately address the issues of semantic shift and domain shift, respectively.
Local-to-Global Self-Attention in Vision Transformers
Transformers have demonstrated great potential in computer vision tasks.
Instance-Level Relative Saliency Ranking with Graph Reasoning
Conventional salient object detection models cannot differentiate the importance of different salient objects.
GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
To take advantage of the labeled examples and guide unlabeled data learning, we further propose a mask generation module to generate high-quality pseudo masks for the unlabeled data.
Multi-Modal Transformer for Accelerated MR Imaging
To this end, we propose a multi-modal transformer (MTrans), which is capable of transferring multi-scale features from the target modality to the auxiliary modality, for accelerated MR imaging.
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
Sparse Needlets for Lighting Estimation with Spherical Transport Loss
Accurate lighting estimation is challenging yet critical to many computer vision and computer graphics tasks such as high-dynamic-range (HDR) relighting.
Brain Image Synthesis With Unsupervised Multivariate Canonical CSCl4Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation
However, they fail to fully leverage the high-order appearance relationships between multi-scale features among the support-query image pairs, thus leading to an inaccurate localization of the query objects.
Exploring Visual Context for Weakly Supervised Person Search
This paper inventively considers weakly supervised person search with only bounding box annotations.
AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection
Last but not least, we introduce a region feature alignment and an instance discriminator to learn domain-invariant features for object proposals.
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks.
You Never Cluster Alone
On one hand, with the corresponding assignment variables being the weight, a weighted aggregation along the data points implements the set representation of a cluster.
TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification
In this work, we further investigate the possibility of applying Transformers for image matching and metric learning given pairs of images.
Ranked #1 on
Generalizable Person Re-identification
on Market-1501
(using extra training data)
Generalizable Person Re-identification
Image Classification
+2
Transformer-Based Source-Free Domain Adaptation
In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation.
When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model
To this end, we first propose a baseline model equipped with one transformer decoder as detection head.
Ranked #5 on
Face Alignment
on COFW
Auxiliary learning induced graph convolutional networks
In this article, we propose a novel auxiliary learning induced graph convolutional network in a multi-task fashion.
Progressively Normalized Self-Attention Network for Video Polyp Segmentation
Existing video polyp segmentation (VPS) models typically employ convolutional neural networks (CNNs) to extract features.
Ranked #6 on
Video Polyp Segmentation
on SUN-SEG-Easy (Unseen)
Attentional Prototype Inference for Few-Shot Segmentation
We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution.
DONet: Dual-Octave Network for Fast MR Image Reconstruction
In this paper, we propose the Dual-Octave Network (DONet), which is capable of learning multi-scale spatial-frequency features from both the real and imaginary components of MR data, for fast parallel MR image reconstruction.
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data.
MetaKernel: Learning Variational Random Features with Limited Labels
Specifically, we propose learning variational random features in a data-driven manner to obtain task-specific kernels by leveraging the shared knowledge provided by related tasks in a meta-learning setting.
Salient Objects in Clutter
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
ISTR: End-to-End Instance Segmentation with Transformers
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #21 on
Instance Segmentation
on COCO test-dev
Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i. e., part-based features) across different temporal ranges.
Ranked #6 on
Person Re-Identification
on iLIDS-VID
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
Visual Saliency Transformer
We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism.
Ranked #1 on
RGB-D Salient Object Detection
on NJUD
Dual-Octave Convolution for Accelerated Parallel MR Image Reconstruction
We evaluate the performance of the proposed model on the acceleration of multi-coil MR image reconstruction.
Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation
To address this, we introduce a novel approach for more accurate and efficient spatio-temporal segmentation.
Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification
Though online hard example mining has improved the learning efficiency to some extent, the mining in mini batches after random sampling is still limited.
Ranked #2 on
Generalizable Person Re-identification
on Market-1501
(using extra training data)
Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
We present a new vision-language (VL) pre-training model dubbed Kaleido-BERT, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers.
Distilling a Powerful Student Model via Online Knowledge Distillation
Besides, a self-distillation module is adopted to convert the feature map of deeper layers into a shallower one.
Repetitive Activity Counting by Sight and Sound
We also introduce a variant of this dataset for repetition counting under challenging vision conditions.
M3DSSD: Monocular 3D Single Stage Object Detector
In the first step, the shape alignment is performed to enable the receptive field of the feature map to focus on the pre-defined anchors with high confidence scores.
ReCU: Reviving the Dead Weights in Binary Neural Networks
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
Anchor-Free Person Search
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).
Ranked #10 on
Person Search
on CUHK-SYSU
Brain Image Synthesis with Unsupervised Multivariate Canonical CSC$\ell_4$Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Variational Knowledge Distillation for Disease Classification in Chest X-Rays
It is challenging to incorporate this information into disease classification due to the high reliance on clinician input in EHRs, limiting the possibility for automated diagnosis.
Group Collaborative Learning for Co-Salient Object Detection
We present a novel group collaborative learning framework (GCoNet) capable of detecting co-salient objects in real time (16ms), by simultaneously mining consensus representations at group level based on the two necessary criteria: 1) intra-group compactness to better formulate the consistency among co-salient objects by capturing their inherent shared attributes using our novel group affinity module; 2) inter-group separability to effectively suppress the influence of noisy objects on the output by introducing our new group collaborating module conditioning the inconsistent consensus.
Ranked #5 on
Co-Salient Object Detection
on CoCA
Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming.
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
GMLight: Lighting Estimation via Geometric Distribution Approximation
This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation.
Concealed Object Detection
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are "perfectly" embedded in their background.
Ranked #5 on
Camouflaged Object Segmentation
on CHAMELEON
Camouflaged Object Segmentation
Dichotomous Image Segmentation
+2
ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks
In deformable registration, the geometric framework - large deformation diffeomorphic metric mapping or LDDMM, in short - has inspired numerous techniques for comparing, deforming, averaging and analyzing shapes or images.
SiMaN: Sign-to-Magnitude Network Binarization
In this paper, we show that our weight binarization provides an analytical solution by encoding high-magnitude weights into +1s, and 0s otherwise.
Multi-Stage Progressive Image Restoration
At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features.
Ranked #3 on
Spectral Reconstruction
on ARAD-1K
A Bayesian Federated Learning Framework with Online Laplace Approximation
On the client side, a prior loss that uses the global posterior probabilistic parameters delivered from the server is designed to guide the local training.
Generative Multi-Label Zero-Shot Learning
Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge.
Ranked #8 on
Multi-label zero-shot learning
on NUS-WIDE
Salient Object Detection via Integrity Learning
We define the concept of integrity at both a micro and macro level.
Boundary-Aware Segmentation Network for Mobile and Web Applications
In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation.
Low Light Image Enhancement via Global and Local Context Modeling
These contexts can be crucial towards inferring several image enhancement tasks, e. g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent.
Few-Shot Semantic Segmentation With Cyclic Memory Network
Specifically, we first generate N pairs (key and value) of multi-resolution query features guided by the support feature and its mask.
CCT-Net: Category-Invariant Cross-Domain Transfer for Medical Single-to-Multiple Disease Diagnosis
A category-invariant cross-domain transfer (CCT) method is proposed to address this single-to-multiple extension.
Light Field Saliency Detection With Dual Local Graph Learning and Reciprocative Guidance
In this paper, we model the information fusion within focal stack via graph networks.
Variational Invariant Learning for Bayesian Domain Generalization
In the probabilistic modeling framework, we introduce a domain-invariant principle to explore invariance across domains in a unified way.
MetaNorm: Learning to Normalize Few-Shot Batches Across Domains
Batch normalization plays a crucial role when training deep neural networks.
Variational Multi-Task Learning
Multi-task learning aims to improve the overall performance of a set of tasks by leveraging their relatedness.
Visual-Textual Attentive Semantic Consistency for Medical Report Generation
Second, the progressive report decoder consists of a sentence decoder and a word decoder, where we propose image-sentence matching and description accuracy losses to constrain the visual-textual semantic consistency.
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization.
Ranked #3 on
Weakly Supervised Action Localization
on THUMOS’14
Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
We propose a learnable module, called the asymmetric convolution (ACM), which learns to better capture the semantic correlation information in offline training on large-scale data.
Ranked #20 on
Visual Object Tracking
on TrackingNet
Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency
This paper proposes a human parsing based texture transfer model via cross-view consistency learning to generate the texture of 3D human body from a single image.
DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
In this way, human annotations are no longer required, and it is scalable to large and diverse real-world datasets.
Generalizable Person Re-identification
Unsupervised Domain Adaptation
Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation
The latter simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of our light-weight model.
Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization
In this article, we propose a novel invariant deep compressible covariance pooling (IDCCP) to solve nuisance variations in aerial scene categorization.
Learning to Learn Variational Semantic Memory
The variational semantic memory accrues and stores semantic information for the probabilistic inference of class prototypes in a hierarchical Bayesian framework.
Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection
Early fusion and the result fusion schemes fuse RGB and depth information at the input and output stages, respectively, hence incur the problem of distribution gap or information loss.
From Handcrafted to Deep Features for Pedestrian Detection: A Survey
In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance.
Group Whitening: Balancing Learning Efficiency and Representational Capacity
Results show that GW consistently improves the performance of different architectures, with absolute gains of $1. 02\%$ $\sim$ $1. 49\%$ in top-1 accuracy on ImageNet and $1. 82\%$ $\sim$ $3. 21\%$ in bounding box AP on COCO.
Normalization Techniques in Training DNNs: Methodology, Analysis and Application
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.
Exploring global diverse attention via pairwise temporal relation for video summarization
In this paper, we propose an efficient convolutional neural network architecture for video SUMmarization via Global Diverse Attention called SUM-GDA, which adapts attention mechanism in a global perspective to consider pairwise temporal relations of video frames.
A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability
This dataset has 1, 842 images with pixel-level DR-related lesion annotations, and 1, 000 images with image-level labels graded by six board-certified ophthalmologists with intra-rater consistency.
Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidance
Although generative adversarial network (GAN) based style transfer is state of the art in histopathology color-stain normalization, they do not explicitly integrate structural information of tissues.
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
In terms of real-time capabilities, SipMask outperforms YOLACT with an absolute gain of 3. 0% (mask AP) under similar settings, while operating at comparable speed on a Titan Xp.
Ranked #12 on
Real-time Instance Segmentation
on MSCOCO
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification
In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
Learning to Learn with Variational Information Bottleneck for Domain Generalization
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift.
Bifurcated backbone strategy for RGB-D salient object detection
In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS).
Ranked #2 on
RGB-D Salient Object Detection
on RGBD135
Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification
To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model.
Domain Generalization
Generalizable Person Re-identification
+1
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales.
Ranked #69 on
Semantic Segmentation
on ADE20K val
PraNet: Parallel Reverse Attention Network for Polyp Segmentation
To address these challenges, we propose a parallel reverse attention network (PraNet) for accurate polyp segmentation in colonoscopy images.
Ranked #7 on
Video Polyp Segmentation
on SUN-SEG-Easy (Unseen)
Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond
This paper proposes a novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels.
Ranked #2 on
Unsupervised Domain Adaptation
on Duke to MSMT
Learning to Learn Kernels with Variational Random Features
We propose meta variational random features (MetaVRF) to learn adaptive kernels for the base-learner, which is developed in a latent variable model by treating the random feature basis as the latent variable.
M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients
Then, we use a modality-specific network to extract implicit and high-level features from different MR scans.
Modeling and Enhancing Low-quality Retinal Fundus Images
Retinal fundus images are widely used for the clinical screening and diagnosis of eye diseases.
Conditional Variational Image Deraining
In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image.
Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images
Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis.
Improved Residual Networks for Image and Video Recognition
We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths.
3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds
In order to obtain a more accurate IoU prediction, we propose a 3D IoU-Net with IoU sensitive feature learning and an IoU alignment operation.
FAIRS -- Soft Focus Generator and Attention for Robust Object Segmentation from Extreme Points
We propose a novel approach for effectively encoding the user input from extreme points and corrective clicks, in a novel and scalable manner that allows the network to work with a variable number of clicks, including corrective clicks for output refinement.
Controllable Orthogonalization in Training DNNs
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation.
Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation
The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
Architecture Disentanglement for Deep Neural Networks
Based on the experimental results, we present three new findings that provide fresh insights into the inner logic of DNNs.
An Investigation into the Stochasticity of Batch Whitening
Our work originates from the observation that while various whitening transformations equivalently improve the conditioning, they show significantly different behaviors in discriminative scenarios and training Generative Adversarial Networks (GANs).
Generalizable Pedestrian Detection: The Elephant In The Room
Furthermore, we illustrate that diverse and dense datasets, collected by crawling the web, serve to be an efficient source of pre-training for pedestrian detection.
Ranked #3 on
Pedestrian Detection
on CityPersons
(using extra training data)
CycleISP: Real Image Restoration via Improved Data Synthesis
This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline.
Ranked #9 on
Image Denoising
on DND
(using extra training data)
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature synthesis and classification.
Ranked #2 on
Generalized Zero-Shot Learning
on CUB-200-2011
Learning Enriched Features for Real Image Restoration and Enhancement
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing.
Ranked #4 on
Image Denoising
on DND
Hierarchical Human Parsing with Typed Part-Relation Reasoning
As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task.
Motion-Attentive Transition for Zero-Shot Video Object Segmentation
In this paper, we present a novel Motion-Attentive Transition Network (MATNet) for zero-shot video object segmentation, which provides a new way of leveraging motion information to reinforce spatio-temporal object representation.
Ranked #9 on
Unsupervised Video Object Segmentation
on FBMS test
Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild
The proposed model is equipped with a novel detection head based on heatmap regression, which conducts score and offset predictions simultaneously on low-resolution feature maps.
Ranked #4 on
Face Alignment
on COFW
Auto-Encoding Twin-Bottleneck Hashing
One bottleneck (i. e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i. e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes.
Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes
Graph convolutional neural networks~(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification, but little work has been done to explore their theoretical properties.
Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs
To this end, we propose layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently.
HRank: Filter Pruning using High-Rank Feature Map
The principle behind our pruning is that low-rank feature maps contain less information, and thus pruned results can be easily reproduced.
Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis
Medical image synthesis has been proposed as an effective solution to this, where any missing modalities are synthesized from the existing ones.
PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4. 0\% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision.
Learning Compositional Neural Information Fusion for Human Parsing
The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively.
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation.
Human-Aware Motion Deblurring
This paper proposes a human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG).
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view.
Semantic Segmentation
Unsupervised Video Object Segmentation
+2
NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
With this observation, we propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features.
Deep Learning for Person Re-identification: A Survey and Outlook
The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets.
Ranked #1 on
Cross-Modal Person Re-Identification
on RegDB-C
Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes
The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other.
Ranked #15 on
Fine-Grained Image Classification
on Stanford Dogs
Towards Partial Supervision for Generic Object Counting in Natural Scenes
Our RLC framework further reduces the annotation cost arising from large numbers of object categories in a dataset by only using lower-count supervision for a subset of categories and class-labels for the remaining ones.
Image Classification
Image-level Supervised Instance Segmentation
+3
DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images
In this paper, we propose a diabetic retinopathy generative adversarial network (DR-GAN) to synthesize high-resolution fundus images which can be manipulated with arbitrary grading and lesion information.
Random Path Selection for Continual Learning
In order to maintain an equilibrium between previous and newly acquired knowledge, we propose a simple controller to dynamically balance the model plasticity.
Ranked #7 on
Continual Learning
on F-CelebA (10 tasks)
Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test
DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.
Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition
We intuitively find that M$^2$Net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy.
Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval
How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR.
Deep Contextual Attention for Human-Object Interaction Detection
Our approach outperforms the state-of-the-art on all datasets.
Mask-Guided Attention Network for Occluded Pedestrian Detection
Our approach obtains an absolute gain of 9. 5% in log-average miss rate, compared to the best reported results on the heavily occluded (HO) pedestrian set of CityPersons test set.
Fast Large-Scale Discrete Optimization Based on Principal Coordinate Descent
Binary optimization, a representative subclass of discrete optimization, plays an important role in mathematical optimization and has various applications in computer vision and machine learning.
AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces
Several studies show that animal needs are often expressed through their faces.
3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization.
Ranked #1 on
Action Classification
on THUMOS'14
Action Classification
Weakly Supervised Action Localization
+2
RANet: Ranking Attention Network for Fast Video Object Segmentation
Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner.
Dual-reference Age Synthesis
Age synthesis methods typically take a single image as input and use a specific number to control the age of the generated image.
ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation
Segmentation is a fundamental task in medical image analysis.
Ranked #1 on
Optic Disc Segmentation
on REFUGE
Coupled-Projection Residual Network for MRI Super-Resolution
The deep sub-network learns from the residuals of the high-frequency image information, where multiple residual blocks are cascaded to magnify the MRI images at the last network layer.
Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces
Retinal image quality assessment (RIQA) is essential for controlling the quality of retinal imaging and guaranteeing the reliability of diagnoses by ophthalmologists or automated analysis systems.
Understanding More about Human and Machine Attention in Deep Neural Networks
With three example computer vision tasks, diverse representative backbones, and famous architectures, corresponding real human gaze data, and systematically conducted large-scale quantitative studies, we quantify the consistency between artificial attention and human visual attention and offer novel insights into existing artificial attention mechanisms by giving preliminary answers to several key questions related to human and artificial attention mechanisms.
Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image
A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images.
