Search Results for author:
Found 62 papers, 39 papers with code
CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective
Note that constraints on intra-sample similarities and inter-sample dissimilarities can be efficiently and effectively reformulated into a contrastive learning framework with newly designed positive and negative pairs.
Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems
In response to these issues, this paper introduces socialized learning (SL) as a promising solution, further propelling the advancement of EI.
AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
To this end, we disassemble three key components involved in computation of logit bias (i. e., logit features, logit predictor, and logit fusion) and empirically analyze the effect on performance of few-shot classification.
Task-Customized Mixture of Adapters for General Image Fusion
These adapters are shared across different tasks and constrained by mutual information regularization, ensuring compatibility with different tasks while complementarity for multi-source images.
Invariant Test-Time Adaptation for Vision-Language Model Generalization
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired datasets.
Selective Learning: Towards Robust Calibration with Dynamic Regularization
The objective can be understood as seeking a model that fits the ground-truth labels by increasing the confidence while also maximizing the entropy of predicted probabilities by decreasing the confidence.
Exploring Diverse Representations for Open Set Recognition
We show that the differences in attention maps can lead to diverse representations so that the fused representations can well handle the open space.
Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering
In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance.
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories.
Bi-directional Adapter for Multi-modal Tracking
To handle this problem, we propose a novel multi-modal visual prompt tracking model based on a universal bi-directional adapter, cross-prompting multiple modalities mutually.
Ranked #6 on
Rgb-T Tracking
on LasHeR
Ahpatron: A New Budgeted Online Kernel Learning Machine with Tighter Mistake Bound
In this paper, we study the mistake bound of online kernel learning on a budget.
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection.
Semantic Equivariant Mixup
Then a generic mixup regularization at the representation level is proposed, which can further regularize the model with the semantic information in mixed samples.
Tuning Pre-trained Model via Moment Probing
Distinguished from LP which builds a linear classification head based on the mean of final features (e. g., word tokens for ViT) or classification tokens, our MP performs a linear classifier on feature distribution, which provides the stronger representation ability by exploiting richer statistical information inherent in features.
Proceedings of the 40th International Conference on Machine Learning
Specifically, we find that the confidence estimated by current models could even increase when some modalities are corrupted.
Cross-Drone Transformer Network for Robust Single Object Tracking
During the tracking process, a cross-drone mapping mechanism is proposed by using the surrounding information of the drone with promising tracking status as reference, assisting drones that lost targets to re-calibrate, which implements real-time cross-drone information interaction.
Provable Dynamic Fusion for Low-Quality Multimodal Data
The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction.
Calibrating Multimodal Learning
Specifically, we find that the confidence estimated by current models could even increase when some modalities are corrupted.
OpenMix+: Revisiting Data Augmentation for Open Set Recognition
In this paper, we point out that balancing between structural risk and open space risk is crucial for open set recognition, and re-formalize it as open set structural risk.
Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification
Second, the quality of the imputed data itself is of high uncertainty.
Reweighted Mixup for Subpopulation Shift
Subpopulation shift exists widely in many real-world applications, which refers to the training and test distributions that contain the same subpopulation groups but with different subpopulation proportions.
Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion
The MoLE performs specialized learning of multi-modal local features, prompting the fused images to retain the local information in a sample-adaptive manner, while the MoGE focuses on the global information that complements the fused image with overall texture detail and contrast.
DropCov: A Simple yet Effective Method for Improving Deep Architectures
Particularly, we for the first time show that \textit{effective post-normalization can make a good trade-off between representation decorrelation and information preservation for GCP, which are crucial to alleviate over-fitting and increase representation ability of deep GCP networks, respectively}.
AREA: Adaptive Reweighting via Effective Area for Long-Tailed Classification
Consequently, we estimate the size of the spanned space for each category, namely effective area, by detailedly analyzing its samples' distribution.
Reliable and Interpretable Personalized Federated Learning
When there are large differences in data distribution among clients, it is crucial for federated learning to design a reliable client selection strategy and an interpretable client communication framework to better utilize group knowledge.
HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping
We blend the semantic layouts of source head and source body, and then inpaint the transition region by the semantic layout generator, achieving a coarse-grained head swapping.
DetFusion: A Detection-driven Infrared and Visible Image Fusion Network
We cascade the image fusion network with the detection networks of both modalities and use the detection loss of the fused images to provide guidance on task-related information for the optimization of the image fusion network.
Latent Heterogeneous Graph Network for Incomplete Multi-View Learning
Multi-view learning has progressed rapidly in recent years.
Class-Specific Semantic Reconstruction for Open Set Recognition
In this study, we propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of AE and prototype learning.
Multi-Granularity Regularized Re-Balancing for Class Incremental Learning
Re-balancing methods are used to alleviate the influence of data imbalance; however, we empirically discover that they would under-fit new classes.
Single Object Tracking Research: A Survey
Visual object tracking is an important task in computer vision, which has many real-world applications, e. g., video surveillance, visual navigation.
Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently.
Ranked #34 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Uncertainty-Aware Multi-View Representation Learning
Under the help of uncertainty, DUA-Nets weigh each view of individual sample according to data quality so that the high-quality samples (or views) can be fully exploited while the effects from the noisy samples (or views) will be alleviated.
Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking
To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.
Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions
Multimodal regression is a fundamental task, which integrates the information from different sources to improve the performance of follow-up applications.
Temporal-attentive Covariance Pooling Networks for Video Recognition
Then, a temporal covariance pooling performs temporal pooling of the attentive covariance representations to characterize both intra-frame correlations and inter-frame cross-correlations of the calibrated features.
T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation
Most existing domain adaptation methods focus on adaptation from only one source domain, however, in practice there are a number of relevant sources that could be leveraged to help improve performance on target domain.
Ranked #2 on
Unsupervised Domain Adaptation
on PACS
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark
To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33, 600 HD frames in various scenarios.
Multi-View Disentangled Representation
Learning effective representations for data with multiple views is crucial in machine learning and pattern recognition.
Deep Partial Multi-View Learning
Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing.
SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning
Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels.
Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.
Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency.
What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task.
Multi-Drone based Single Object Tracking with Agent Sharing Network
Moreover, an agent sharing network (ASNet) is proposed by self-supervised template sharing and view-aware fusion of the target from multiple drones, which can improve the tracking accuracy significantly compared with single drone tracking.
Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning
To address this dilemma, we further propose an uncertainty-aware cross-modality vehicle detection (UA-CMDet) framework to extract complementary information from cross-modal images, which can significantly improve the detection performance in low light conditions.
Detection and Tracking Meet Drones Challenge
We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i. e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking.
Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones with arbitrary crowd density, perspective, and flight altitude.
CPM-Nets: Cross Partial Multi-View Networks
Despite multi-view learning progressed fast in past decades, it is still challenging due to the difficulty in modeling complex correlation among different views, especially under the context of view missing.
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity.
Ranked #735 on
Image Classification
on ImageNet
Multi-view Deep Subspace Clustering Networks
Dnet learns view-specific self-representation matrices, whereas Unet learns a common self-representation matrix for all views.
Ranked #1 on
Multi-view Subspace Clustering
on ORL
Neural Blind Deconvolution Using Deep Priors
To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution.
Progressive Image Deraining Networks: A Better and Simpler Baseline
To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions.
Ranked #1 on
Single Image Deraining
on Rain1400
Semi-interactive Attention Network for Answer Understanding in Reverse-QA
Question answering (QA) is an important natural language processing (NLP) task and has received much attention in academic research and industry communities.
Unsupervised Degradation Learning for Single Image Super-Resolution
Specifically, we propose a degradation network to model the real-world degradation process from HR to LR via generative adversarial networks, and these generated realistic LR images paired with real-world HR images are exploited for training the SR reconstruction network, forming the first cycle.
SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detection
To this end, we propose a novel and efficient video eye fixation detection model to improve the saliency detection performance.
Detecting Adversarial Examples via Key-based Network
In contrast to existing defense methods, the proposed method does not require knowledge of the process for generating adversarial examples and can be applied to defend against different types of attacks.
Vision Meets Drones: A Challenge
In this paper we present a large-scale visual object detection and tracking benchmark, named VisDrone2018, aiming at advancing visual understanding tasks on the drone platform.
Latent Multi-View Subspace Clustering
In this paper, we propose a novel Latent Multi-view Subspace Clustering (LMSC) method, which clusters data points with latent representation and simultaneously explores underlying complementary information from multiple views.
Efficient Background Modeling Based on Sparse Representation and Outlier Iterative Removal
A cyclic iteration process is then proposed to extract the background from the discriminative frame set.
