Search Results for author:
Found 109 papers, 56 papers with code
Momentum Batch Normalization for Deep Learning with Small Batch Size
To make a deeper understanding of BN, in this work we prove that BN actually introduces a certain level of noise into the sample mean and variance during the training process, while the noise level depends only on the batch size.
UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval
Second, Target Prompt Generation creates dynamic prompts by attending to masked source prompts, enabling seamless adaptation to unseen domains and classes.
POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search
(2) To enhance the pseudo-range accuracy of selected anchor points, a new loss function, named multilateration anchor loss, is proposed.
Towards Graph Prompt Learning: A Survey and Beyond
Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval.
DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learning
To ensure the meaningful transfer of knowledge from the unsupervised encoder to the supervised one, we further define an MI-based disentangled consistency regularization between two models and identify the corresponding rationale that aligns well with the current graph classification task.
Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric
Deep metric learning (DML) aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval.
DEMO: A Statistical Perspective for Efficient Image-Text Matching
Image-text matching has been a long-standing problem, which seeks to connect vision and language through semantic understanding.
An Evaluation of Large Language Models in Bioinformatics Research
Large language models (LLMs) such as ChatGPT have gained considerable interest across diverse research communities.
Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection
Specifically, we propose Class-Balance-based sample Selection (CBS) to prevent the tail class samples from being neglected during training.
Fine-grained Prototypical Voting with Heterogeneous Mixup for Semi-supervised 2D-3D Cross-modal Retrieval
In this paper we propose a semi-supervised approach named Fine-grained Prototypcical Voting with Heterogeneous Mixup (FIVE) which maps both 2D and 3D data into a common embedding space for cross-modal retrieval.
BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
To remedy this we propose a two-fold strategy: (1) We introduce an innovative approach that encodes bone connectivity by harnessing the power of graph distances to describe the physical topology; we further incorporate action-specific topological representation via persistent homology analysis to depict systemic dynamics.
Ranked #6 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Hierarchical Graph Pattern Understanding for Zero-Shot VOS
However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene.
Proposal-Level Unsupervised Domain Adaptation for Open World Unbiased Detector
This is because the predictor is inevitably biased to the known categories, and fails under the shift in the appearance of the unseen categories.
Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting
This paper studies the problem of traffic flow forecasting, which aims to predict future traffic conditions on the basis of road networks and traffic conditions in the past.
Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition
We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-trained 2D model.
Anatomy-Aware Lymph Node Detection in Chest CT using Implicit Station Stratification
Motivated by this observation, we propose a novel end-to-end framework to improve LN detection performance by leveraging their station information.
Random Boxes Are Open-world Object Detectors
First, as the randomization is independent of the distribution of the limited known objects, the random proposals become the instrumental variable that prevents the training from being confounded by the known objects.
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire.
PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction
In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation streams.
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation
Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student.
TGNN: A Joint Semi-supervised Framework for Graph-level Classification
The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data.
FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images.
Ranked #2 on
Few-Shot Semantic Segmentation
on COCO-20i (10-shot)
Prototypical Mixing and Retrieval-Based Refinement for Label Noise-Resistant Image Retrieval
This paper investigates a realistic but understudied problem of image retrieval under label noise, which could lead to severe overfitting or memorization of noisy samples during optimization.
Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
If the context in every class is evenly distributed, OOD would be trivial because the context can be easily removed due to an underlying principle: class is invariant to context.
Identifying Hard Noise in Long-Tailed Sample Distribution
Such imbalanced training data makes a classifier less discriminative for the tail classes, whose previously "easy" noises are now turned into "hard" ones -- they are almost as outliers as the clean tail samples.
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition
For 3D video-based tasks such as action recognition, however, directly applying spatiotemporal transformers on video data will bring heavy computation and memory burdens due to the largely increased number of patches and the quadratic complexity of self-attention computation.
Ranked #10 on
Action Recognition
on Diving-48
Rethinking IoU-based Optimization for Single-stage 3D Object Detection
Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors.
Towards Counterfactual Image Manipulation via CLIP
In addition, we design a simple yet effective scheme that explicitly maps CLIP embeddings (of target text) to the latent space and fuses them with latent codes for effective latent code optimization and accurate editing.
On Non-Random Missing Labels in Semi-Supervised Learning
Our method is three-fold: 1) We propose Class-Aware Propensity (CAP) that exploits the unlabeled data to train an improved classifier using the biased labeled data.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Dense Learning based Semi-Supervised Object Detection
Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data.
Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection
The likelihood maps generated by the SLV module are used to supervise the feature learning of the backbone network, encouraging the network to attend to wider and more diverse areas of the image.
Homography Loss for Monocular 3D Object Detection
Monocular 3D object detection is an essential task in autonomous driving.
Dynamic Supervisor for Cross-dataset Object Detection
The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning.
Disentangled Representation Learning for Text-Video Retrieval
Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance.
Ranked #10 on
Video Retrieval
on MSR-VTT-1kA
(using extra training data)
Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation
Specifically, due to the sum-over-class pooling nature of BCE, each pixel in CAM may be responsive to multiple classes co-occurring in the same receptive field.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results.
Balanced and Hierarchical Relation Learning for One-Shot Object Detection
In this paper, we introduce the balanced and hierarchical learning for our detector.
Meta Convolutional Neural Networks for Single Domain Generalization
Taking meta features as reference, we propose compositional operations to eliminate irrelevant features of local convolutional features by an addressing process and then to reformulate the convolutional feature maps as a composition of related meta features.
Ranked #5 on
Single-Source Domain Generalization
on Digits-five
Unpaired Cartoon Image Synthesis via Gated Cycle Mapping
Experimental results demonstrate the superiority of the proposed method over the state of the art and validate its effectiveness in the brand-new task of general cartoon image synthesis.
Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification
We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail over head, as the test distribution is assumed to be balanced; however, when the test is as imbalanced as the long-tailed training data -- let the test respect Zipf's law of nature -- the tail bias is no longer beneficial overall because it hurts the head majorities.
Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms.
SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae
Spinal degeneration plagues many elders, office workers, and even the younger generations.
Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
Bounding box (bbox) regression is a fundamental task in computer vision.
Density-Based Clustering with Kernel Diffusion
Finding a suitable density function is essential for density-based clustering algorithms such as DBSCAN and DPC.
Unleash the Potential of Adaptation Models via Dynamic Domain Labels
In this paper, we propose an embarrassing simple yet highly effective adversarial domain adaptation (ADA) method for effectively training models for alignment.
Improving 3D Object Detection with Channel-wise Transformer
Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors.
Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information.
Transporting Causal Mechanisms for Unsupervised Domain Adaptation
However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the stratification and representation of the unobserved confounder that is the cause of the domain gap.
Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
The inheritance part is learned with a similarity loss to transfer the existing learned knowledge from the teacher model to the student model, while the exploration part is encouraged to learn representations different from the inherited ones with a dis-similarity loss.
Partial Person Re-Identification With Part-Part Correspondence Learning
Driven by the success of deep learning, the last decade has seen rapid advances in person re-identification (re-ID).
Interactive Self-Training With Mean Teachers for Semi-Supervised Object Detection
Specifically, to alleviate the instability among the detection results in different iterations, we propose using nonmaximum suppression to fuse the detection results from different iterations.
Criterion-based Heterogeneous Collaborative Filtering for Multi-behavior Implicit Recommendation
Besides, CHCF integrates criterion learning and user preference learning into a unified framework, which can be trained jointly for the interaction prediction of the target behavior.
Attention-guided Temporally Coherent Video Object Matting
Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.
$\alpha$-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
Bounding box (bbox) regression is a fundamental task in computer vision.
Graph Contrastive Clustering
On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.
Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation
Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial training data is not retained.
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID.
Ranked #5 on
Person Re-Identification
on VC-Clothes
Cloth-Changing Person Re-Identification
Computational Efficiency
+1
Dense Interaction Learning for Video-based Person Re-identification
The CNN encoder is responsible for efficiently extracting discriminative spatial features while the DI decoder is designed to densely model spatial-temporal inherent interaction across frames.
Ranked #1 on
Person Re-Identification
on DukeMTMC-reID
Distilling Causal Effect of Data in Class-Incremental Learning
We propose a causal framework to explain the catastrophic forgetting in Class-Incremental Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing anti-forgetting techniques, such as data replay and feature/label distillation.
Counterfactual Zero-Shot and Open-Set Visual Recognition
We show that the key reason is that the generation is not Counterfactual Faithful, and thus we propose a faithful one, whose generation is from the sample-specific counterfactual question: What would the sample look like, if we set its class attribute to a certain class, while keeping its sample attribute unchanged?
3D Local Convolutional Neural Networks for Gait Recognition
Second, different body parts possess different scales, and even the same part in different frames can appear at different locations and scales.
Ranked #4 on
Gait Recognition
on OUMVLP
VideoFlow: A Framework for Building Visual Analysis Pipelines
The past years have witnessed an explosion of deep learning frameworks like PyTorch and TensorFlow since the success of deep neural networks.
Video Object Segmentation With Dynamic Memory Networks and Adaptive Object Alignment
In this paper, we propose a novel solution for object-matching based semi-supervised video object segmentation, where the target object masks in the first frame are provided.
Camera-aware Proxies for Unsupervised Person Re-Identification
These camera-aware proxies enable us to deal with large intra-ID variance and generate more reliable pseudo labels for learning.
Learning to Generate Content-Aware Dynamic Detectors
To the best of our knowledge, our CADDet is the first work to introduce dynamic routing mechanism in object detection.
Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
The topology of the adjacency graph is a key factor for modeling the correlations of the input skeletons.
Tracklets Predicting Based Adaptive Graph Tracking
It re-extracts the features of the tracklets in the current frame based on motion predicting, which is the key to solve the problem of features inconsistent.
CIMON: Towards High-quality Hash Codes
However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning.
Interventional Few-Shot Learning
Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view.
Causal Intervention for Weakly-Supervised Semantic Segmentation
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS).
Ranked #37 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation
Today, scene graph generation(SGG) task is largely limited in realistic scenarios, mainly due to the extremely long-tailed bias of predicate annotation distribution.
Ranked #5 on
Unbiased Scene Graph Generation
on Visual Genome
Apparel-invariant Feature Learning for Apparel-changed Person Re-identification
Therefore, it is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes.
Deep Robust Clustering by Contrastive Learning
Different from existing methods, DRC looks into deep clustering from two perspectives of both semantic clustering assignment and representation feature, which can increase inter-class diversities and decrease intra-class diversities simultaneously.
Ranked #3 on
Online Clustering
on cifar10
Salvage Reusable Samples from Noisy Data for Robust Learning
To this end, we propose a certainty-based reusable sample selection and correction approach, termed as CRSSC, for coping with label noise in training deep FG models with web images.
Out-of-distribution Generalization via Partial Feature Decorrelation
Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting.
Joint Auction-Coalition Formation Framework for Communication-Efficient Federated Learning in UAV-Enabled Internet of Vehicles
The simulation results show that the grand coalition, where all UAVs join a single coalition, is not always stable due to the profit-maximizing behavior of the UAVs.
Networking and Internet Architecture Signal Processing
Adversarial Mutual Information for Text Generation
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation.
SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection
In this paper, we propose a spatial likelihood voting (SLV) module to converge the proposal localizing process without any bounding box annotations.
Counterfactual VQA: A Cause-Effect Look at Language Bias
VQA models may tend to rely on language bias as a shortcut and thus fail to sufficiently learn the multi-modal knowledge from both vision and language.
Towards Fine-grained Human Pose Transfer with Detail Replenishing Network
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality.
PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks
Despite significant progress of applying deep learning methods to the field of content-based image retrieval, there has not been a software library that covers these methods in a unified manner.
Boosting Semantic Human Matting with Coarse Annotations
In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input.
Ranked #9 on
Image Matting
on AM-2K
Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approach
Coupled with the rise of Deep Learning, the wealth of data and enhanced computation capabilities of Internet of Vehicles (IoV) components enable effective Artificial Intelligence (AI) based models to be built.
Signal Processing Networking and Internet Architecture
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
It has been shown that using the first and second order statistics (e. g., mean and variance) to perform Z-score standardization on network activations or weight vectors, such as batch normalization (BN) and weight standardization (WS), can improve the training performance.
CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries
On the technical side, the Partial-Residual GCN takes the position features of the branches, with the 3D spatial image features as conditions, to predict the label for each branches.
A Survey on Deep Hashing Methods
Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining.
Towards Precise Intra-camera Supervised Person Re-identification
Our approach performs even comparable to state-of-the-art fully supervised methods in two of the datasets.
Towards a Fast Steady-State Visual Evoked Potentials (SSVEP) Brain-Computer Interface (BCI)
We observed that CSTA achieves the maximum mean accuracy of 97. 43$\pm$2. 26 % and 85. 71$\pm$13. 41 % with four-class and forty-class SSVEP data-sets respectively in sub-second response time in offline analysis.
HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
In particular, our proposed HoMM can perform arbitrary-order moment tensor matching, we show that the first-order HoMM is equivalent to Maximum Mean Discrepancy (MMD) and the second-order HoMM is equivalent to Correlation Alignment (CORAL).
Quantization Networks
The proposed quantization function can be learned in a lossless and end-to-end manner and works for any weights and activations of neural networks in a simple and uniform way.
SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation
In this paper, we propose a novel Semi-supervised Self-pace Adversarial Hashing method, named SSAH to solve the above problems in a unified framework.
A Multi-Task Learning Framework for Extracting Bacteria Biotope Information
This paper presents a novel transfer multi-task learning method for Bacteria Biotope rel+ner task at BioNLP-OST 2019.
Progressive Transfer Learning
Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch.
Extracting Visual Knowledge from the Internet: Making Sense of Image Data
Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data.
Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks
The proposed model is trained and evaluated on a few publicly available datasets and has achieved the state-of-the-art accuracy with a mean Dice coefficient index of 0. 947 $\pm$ 0. 044.
Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains.
Deep Active Learning for Video-based Person Re-identification
With the gained annotations of the actively selected candidates, the tracklets' pesudo labels are updated by label merging and further used to re-train our re-ID model.
Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream.
An Adversarial Approach to Hard Triplet Generation
While deep neural networks have demonstrated competitive results for many visual recognition and image retrieval tasks, the major challenge lies in distinguishing similar images from different categories (i. e., hard negative examples) while clustering images with large variations from the same category (i. e., hard positive examples).
Deep Saliency Hashing
As the core of DSaH, the saliency loss guides the attention network to mine discriminative regions from pairs of images.
Sharp Attention Network via Adaptive Sampling for Person Re-identification
In this paper, we present novel sharp attention networks by adaptively sampling feature maps from convolutional neural networks (CNNs) for person re-identification (re-ID) problem.
Homocentric Hypersphere Feature Embedding for Person Re-identification
Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose.
Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images
For the video side, deep visual features are extracted from detected object regions in each frame, and further fed into a Long Short-Term Memory (LSTM) framework for sequence modeling, which captures the temporal dynamics in videos.
Global versus Localized Generative Adversarial Nets
In this paper, we present a novel localized Generative Adversarial Net (GAN) to learn on the manifold of real data.
Refining Image Categorization by Exploiting Web Images and General Corpus
To tackle these problems, in this work, we exploit general corpus information to automatically select and subsequently classify web images into semantic rich (sub-)categories.
Exploiting Web Images for Dataset Construction: A Domain Robust Approach
To reduce the cost of manual labelling, there has been increased research interest in automatically constructing image datasets by exploiting web images.
Deep CTR Prediction in Display Advertising
Click through rate (CTR) prediction of image ads is the core task of online display advertising systems, and logistic regression (LR) has been frequently applied as the prediction model.
Hybrid Affinity Propagation
We formulate this problem as finding a few image exemplars to represent the image set semantically and visually, and solve it in a hybrid way by exploiting both visual and textual information associated with images.
