Search Results for author:
Found 54 papers, 37 papers with code
Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients
This paper studies a challenging robust federated learning task with model heterogeneous and data corrupted clients, where the clients have different local model structures.
Privacy-Enhancing Paradigms within Federated Multi-Agent Systems
LLM-based Multi-Agent Systems (MAS) have proven highly effective in solving complex problems by integrating multiple agents, each performing different roles.
Synthetic Data is an Elegant GIFT for Continual Vision-Language Models
Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratch.
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research.
Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions, based on frozen pre-trained weight magnitude and accumulated fine-tuning gradient values.
FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
Personalized Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural Networks (GNNs) without compromising privacy while accommodating personalized requirements for non-IID participants.
Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification
Wildlife ReID involves utilizing visual technology to identify specific individuals of wild animals in different scenarios, holding significant importance for wildlife conservation, ecological research, and environmental monitoring.
Federated Graph Semantic and Structural Learning
First, for node-level semantics, we find that contrasting nodes from distinct classes is beneficial to provide a well-performing discrimination.
EmoLLM: Multimodal Emotional Understanding Meets Large Language Models
Experimental results demonstrate that EmoLLM significantly elevates multimodal emotional understanding performance, with an average improvement of 12. 1% across multiple foundation models on EmoBench.
CorrMAE: Pre-training Correspondence Transformers with Masked Autoencoder
To tackle these challenges, we propose a pre-training method to acquire a generic inliers-consistent representation by reconstructing masked correspondences, providing a strong initial representation for downstream tasks.
Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey
Vertical Federated Learning (VFL) is a privacy-preserving distributed learning paradigm where different parties collaboratively learn models using partitioned features of shared samples, without leaking private data.
All in One Framework for Multimodal Re-identification in the Wild
In Re-identification (ReID), recent advancements yield noteworthy progress in both unimodal and cross-modal retrieval tasks.
Semi-supervised Text-based Person Search
Text-based person search (TBPS) aims to retrieve images of a specific person from a large image gallery based on a natural language description.
Transformer for Object Re-Identification: A Survey
Object Re-identification (Re-ID) aims to identify specific objects across different times and scenes, which is a widely researched task in computer vision.
Contextual Augmented Global Contrast for Multimodal Intent Recognition
Multimodal intent recognition (MIR) aims to perceive the human intent polarity via language visual and acoustic modalities.
FedAS: Bridging Inconsistency in Personalized Federated Learning
In PFL clients update their shared parameters to communicate and learn from others while keeping personalized parts unchanged leading to poor coordination between these two components.
Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification
Unsupervised visible-infrared person re-identification (US-VI-ReID) centers on learning a cross-modality retrieval model without labels reducing the reliance on expensive cross-modality manual annotation.
Negative Pre-aware for Noisy Cross-modal Matching
Since clean samples are easier distinguished by GMM with increasing noise, the memory bank can still maintain high quality at a high noise ratio.
Cross-modal retrieval with noisy correspondence
Image-text matching
+3
Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark
In this survey, we provide a systematic overview of the important and recent developments of research on federated learning.
Rotation Invariant Transformer for Recognizing Object in UAVs
Existing methods are usually designed for city cameras, incapable of handing the rotation issue in UAV scenarios.
Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning
Federated learning is an important privacy-preserving multi-party learning paradigm, involving collaborative learning with others and local updating on private data.
Rethinking Client Drift in Federated Learning: A Logit Perspective
Concretely, FedCSD introduces a class prototype similarity distillation to align the local logits with the refined global logits that are weighted by the similarity between local logits and the global prototype.
An Empirical Study of CLIP for Text-based Person Search
TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS.
Ranked #6 on
Text based Person Retrieval
on RSTPReid
Heterogeneous Federated Learning: State-of-the-art and Research Challenges
Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential.
Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution
(2) For the cross-modality gap, we propose a novel Symmetric Uncertainty scheme to remove parts of RGB information harmful to the recovery of HR depth maps.
Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval
To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision.
Ranked #3 on
Text-based Person Retrieval with Noisy Correspondence
on RSTPReid
(using extra training data)
Towards Modality-Agnostic Person Re-Identification With Descriptive Query
Person re-identification (ReID) with descriptive query (text or sketch) provides an important supplement for general image-image paradigms, which is usually studied in a single cross-modality matching manner, e. g., text-to-image or sketch-to-photo.
Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification
The grand unified representation lies in two aspects: 1) GUR adopts a bottom-up domain learning strategy with a cross-memory association embedding module to explore the information of hierarchical domains, i. e., intra-camera, inter-camera, and inter-modality domains, learning a unified and robust representation against hierarchical discrepancy.
Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning
However, since the model continuously learns new knowledge, the stored prototypical representations cannot correctly model the properties of old classes in the existence of knowledge updates.
Rethinking Federated Learning With Domain Shift: A Prototype View
The private model presents degenerative performance on other domains (with domain shift).
Robust Heterogeneous Federated Learning under Data Corruption
Model heterogeneous federated learning is a realistic and challenging problem.
Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning
In response, we devise a Progressive Graph Matching method to globally mine cross-modality correspondences under cluster imbalance scenarios.
Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning
In this paper, we introduce a novel Refined Semantic enhancement method towards Frequency Diffusion (RSFD), a captioning model that constantly perceives the linguistic representation of the infrequent tokens.
Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-Identification
Visible infrared person re-identification (VI-ReID) aims at searching out the corresponding infrared (visible) images from a gallery set captured by other spectrum cameras.
Pyramidal Transformer with Conv-Patchify for Person Re-identification
The robust and discriminative feature extraction is the key component in person re-identification (Re-ID).
Few-Shot Model Agnostic Federated Learning
To address these issues, this paper presents a novel framework with two main parts: 1) model agnostic federated learning, it performs public-private communication by unifying the model prediction outputs on the shared public datasets; 2) latent embedding adaptation, it addresses the domain gap with an adversarial learning scheme to discriminate the public and private domains.
Learnable Privacy-Preserving Anonymization for Pedestrian Images
We further propose a progressive training strategy to improve the performance, which iteratively upgrades the initial anonymization supervision.
Learn From Others and Be Yourself in Heterogeneous Federated Learning
Federated learning has emerged as an important distributed learning paradigm, which normally involves collaborative updating with others and local updating on private data.
Robust Federated Learning With Noisy and Heterogeneous Clients
Model heterogeneous federated learning is a challenging task since each client independently designs its own model.
AVA-AVD: Audio-Visual Speaker Diarization in the Wild
Audio-visual speaker diarization aims at detecting "who spoke when" using both auditory and visual signals.
The Multi-Modal Video Reasoning and Analyzing Competition
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) workshop in conjunction with ICCV 2021.
TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval
Until now, the deep hashing for the image retrieval community has been dominated by convolutional neural network architectures, e. g. \texttt{Resnet}\cite{he2016deep}.
Person Re-Identification by Context-aware Part Attention and Multi-Head Collaborative Learning
In addition, we propose a novel multi-head collaborative training scheme to improve the performance, which is collaboratively supervised by multiple heads with the same structure but different parameters.
Channel Augmented Joint Learning for Visible-Infrared Recognition
This paper introduces a powerful channel augmented joint learning strategy for the visible-infrared recognition problem.
Cross-Modality Person Re-Identification via Modality Confusion and Center Aggregation
Cross-modality person re-identification is a challenging task due to large cross-modality discrepancy and intra-modality variations.
Multi-Scale Cascading Network with Compact Feature Learning for RGB-Infrared Person Re-Identification
RGB-Infrared person re-identification (RGB-IR Re-ID) aims to match persons from heterogeneous images captured by visible and thermal cameras, which is of great significance in the surveillance system under poor light conditions.
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.
Probabilistic Structural Latent Representation for Unsupervised Embedding
Unsupervised embedding learning aims at extracting low-dimensional visually meaningful representations from large-scale unlabeled images, which can then be directly used for similarity-based search.
Probabilistic Structural Latent Representation for Unsupervised Embedding
Unsupervised embedding learning aims at extracting low-dimensional visually meaningful representations from large-scale unlabeled images, which can then be directly used for similarity-based search.
Ranked #56 on
Image Classification
on STL-10
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
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space.
Robust Anchor Embedding for Unsupervised Video Person Re-Identification in the Wild
After that, a robust and efficient top-k counts label prediction strategy is proposed to predict the labels of unlabeled image sequences.
Ranked #11 on
Person Re-Identification
on PRID2011
Representation Learning
Video-Based Person Re-Identification
Dynamic Label Graph Matching for Unsupervised Video Re-Identification
Label estimation is an important component in an unsupervised person re-identification (re-ID) system.
Ranked #8 on
Person Re-Identification
on PRID2011
