471 citations · 1.5k across the 21 of their papers we have counts for
19 papers · 1 filter
Language Guided Concept Bottleneck Models for Interpretable Continual Learning
Lu Yu, Haoyu Han, Zhe Tao +2
Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating…
Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning
Lu Yu, Zhe Tao, Dipam Goswami +4
Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing…
SEP: Self-Enhanced Prompt Tuning for Visual-Language Model
Hantao Yao, Rui Zhang, Lu Yu +2
Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, th…
Hierarchical Prompts for Rehearsal-free Continual Learning
Yukun Zuo, Hantao Yao, Lu Yu +2
Continual learning endeavors to equip the model with the capability to integrate current task knowledge while mitigating the forgetting of past task knowledge. Inspired by prompt t…
Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition
Yukun Zuo, Hantao Yao, Liansheng Zhuang +1
Audio-visual video recognition (AVVR) aims to integrate audio and visual clues to categorize videos accurately. While existing methods train AVVR models using provided datasets and…
TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model
Hantao Yao, Rui Zhang, Changsheng Xu
Prompt tuning represents a valuable technique for adapting pre-trained visual-language models (VLM) to various downstream tasks. Recent advancements in CoOp-based methods propose a…
Learning Domain-Aware Detection Head with Prompt Tuning
Haochen Li, Rui Zhang, Hantao Yao +5
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reduci…
Camera-Incremental Object Re-Identification with Identity Knowledge Evolution
Hantao Yao, Lu Yu, Jifei Luo +1
Object Re-identification (ReID) aims to retrieve the probe object from many gallery images with the ReID model inferred based on a stationary camera-free dataset by associating and…
Visual-Language Prompt Tuning with Knowledge-guided Context Optimization
Hantao Yao, Rui Zhang, Changsheng Xu
Prompt tuning is an effective way to adapt the pre-trained visual-language model (VLM) to the downstream task using task-related textual tokens. Representative CoOp-based work comb…
Dual Cluster Contrastive learning for Object Re-Identification
Hantao Yao, Changsheng Xu
Recently, cluster contrastive learning has been proven effective for object ReID by computing the contrastive loss between the individual features and the cluster memory. However,…
Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
Hantao Yao, Shaobo Min, Yongdong Zhang +1
Transductive Zero-shot learning (ZSL) targets to recognize the unseen categories by aligning the visual and semantic information in a joint embedding space. There exist four kinds…
Joint Person Objectness and Repulsion for Person Search
Hantao Yao, Changsheng Xu
Person search targets to search the probe person from the unconstrainted scene images, which can be treated as the combination of person detection and person matching. However, the…
Multi-Objective Matrix Normalization for Fine-grained Visual Recognition
Shaobo Min, Hantao Yao, Hongtao Xie +2
Bilinear pooling achieves great success in fine-grained visual recognition (FGVC). Recent methods have shown that the matrix power normalization can stabilize the second-order info…
Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning
Shaobo Min, Hantao Yao, Hongtao Xie +3
Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the effect of semantic-free visual repre…
Domain-Specific Embedding Network for Zero-Shot Recognition
Shaobo Min, Hantao Yao, Hongtao Xie +2
Zero-Shot Learning (ZSL) seeks to recognize a sample from either seen or unseen domain by projecting the image data and semantic labels into a joint embedding space. However, most…
GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
Longhui Wei, Shiliang Zhang, Hantao Yao +2
The huge variance of human pose and the misalignment of detected human images significantly increase the difficulty of person Re-Identification (Re-ID). Moreover, efficient Re-ID s…
One-Shot Fine-Grained Instance Retrieval
Hantao Yao, Shiliang Zhang, Yongdong Zhang +2
Fine-Grained Visual Categorization (FGVC) has achieved significant progress recently. However, the number of fine-grained species could be huge and dynamically increasing in real s…
Deep Representation Learning with Part Loss for Person Re-Identification
Hantao Yao, Shiliang Zhang, Yongdong Zhang +2
Learning discriminative representations for unseen person images is critical for person Re-Identification (ReID). Most of current approaches learn deep representations in classific…
DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing
Hantao Yao, Feng Dai, Dongming Zhang +4
Most traditional algorithms for compressive sensing image reconstruction suffer from the intensive computation. Recently, deep learning-based reconstruction algorithms have been re…