Publications (45)
Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
De Cheng, Yihong Gong, Zhihui Li +3
Learning the distance metric between pairs of examples is of great importance for visual recognition, especially for person re-identification (Re-Id). Recently, the contrastive and…
Hybrid Routing Transformer for Zero-Shot Learning
De Cheng, Gerong Wang, Bo Wang +3
Zero-shot learning (ZSL) aims to learn models that can recognize unseen image semantics based on the training of data with seen semantics. Recent studies either leverage the global…
Robust Region Feature Synthesizer for Zero-Shot Object Detection
Peiliang Huang, Junwei Han, De Cheng +1
Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image. In this study,…
Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification
Haonan Shi, Yubin Wang, De Cheng +3
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to learn modality-invariant image features from unlabeled cross-modal person datasets by reducing the modali…
Support-Set Based Cross-Supervision for Video Grounding
Xinpeng Ding, Nannan Wang, Shiwei Zhang +5
Current approaches for video grounding propose kinds of complex architectures to capture the video-text relations, and have achieved impressive improvements. However, it is hard to…
Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning
Dingwen Zhang, Yan Li, De Cheng +2
To facilitate the evolution of edge intelligence in ever-changing environments, we study on-device incremental learning constrained in limited computation resource in this paper. C…
EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model
Guozhang Li, Xinpeng Ding, De Cheng +3
Early weakly supervised video grounding (WSVG) methods often struggle with incomplete boundary detection due to the absence of temporal boundary annotations. To bridge the gap betw…
Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization
De Cheng, Zhipeng Xu, Xinyang Jiang +3
Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains. Notably, recent advances in pre-trained Visual Foundation…
Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization
Zhipeng Xu, De Cheng, Xinyang Jiang +3
Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain available for training. One o…
Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure
De Cheng, Yanling Ji, Dong Gong +4
In real-world applications, image degeneration caused by adverse weather is always complex and changes with different weather conditions from days and seasons. Systems in real-worl…
Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach
Shizhou Zhang, Wenlong Luo, De Cheng +4
In this paper, we construct a large-scale benchmark dataset for Ground-to-Aerial Video-based person Re-Identification, named G2A-VReID, which comprises 185,907 images and 5,576 tra…
Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint
Guozhang Li, De Cheng, Xinpeng Ding +3
Weakly Supervised Temporal Action Localization (WTAL) aims to classify and localize temporal boundaries of actions for the video, given only video-level category labels in the trai…
Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning
Lingfeng He, De Cheng, Di Xu +2
Continual learning (CL) aims to equip models with the ability to learn from a stream of tasks without forgetting previous knowledge. With the progress of vision-language models lik…
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
Qirui Wu, Shizhou Zhang, De Cheng +4
Catastrophic forgetting is a critical chanllenge for incremental object detection (IOD). Most existing methods treat the detector monolithically, relying on instance replay or know…
Visual Prompt Tuning in Null Space for Continual Learning
Yue Lu, Shizhou Zhang, De Cheng +4
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On…
DermINO: Hybrid Pretraining for a Versatile Dermatology Foundation Model
Jingkai Xu, De Cheng, Xiangqian Zhao +27
Skin diseases impose a substantial burden on global healthcare systems, driven by their high prevalence (affecting up to 70% of the population), complex diagnostic processes, and a…
Boosting Weakly-Supervised Temporal Action Localization with Text Information
Guozhang Li, De Cheng, Xinpeng Ding +3
Due to the lack of temporal annotation, current Weakly-supervised Temporal Action Localization (WTAL) methods are generally stuck into over-complete or incomplete localization. In…
HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling
Yubin Wang, Xinyang Jiang, De Cheng +3
Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models…
ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding
Yubin Wang, Xinyang Jiang, De Cheng +2
Video temporal grounding is an emerging topic aiming to identify specific clips within videos. In addition to pre-trained video models, contemporary methods utilize pre-trained vis…
Multi-level Collaborative Distillation Meets Global Workspace Model: A Unified Framework for OCIL
Shibin Su, Guoqiang Liang, De Cheng +2
Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams can be seen only once, it is more suit…
Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID
Lingfeng He, De Cheng, Nannan Wang +1
Unsupervised visible-infrared person re-identification (USL-VI-ReID) endeavors to retrieve pedestrian images of the same identity from different modalities without annotations. Whi…
Ground-to-Aerial Person Search: Benchmark Dataset and Approach
Shizhou Zhang, Qingchun Yang, De Cheng +4
In this work, we construct a large-scale dataset for Ground-to-Aerial Person Search, named G2APS, which contains 31,770 images of 260,559 annotated bounding boxes for 2,644 identit…
EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning
Huaijie Wang, De Cheng, Lingfeng He +4
Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired k…
Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID
De Cheng, Lingfeng He, Nannan Wang +2
Unsupervised visible-infrared person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations f…
Text-based Person Search in Full Images via Semantic-Driven Proposal Generation
Shizhou Zhang, De Cheng, Wenlong Luo +6
Finding target persons in full scene images with a query of text description has important practical applications in intelligent video surveillance.However, different from the real…
Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts
Yubin Wang, Xinyang Jiang, De Cheng +4
Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the…
Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement
Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu +5
Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes, resulting in poor generalization on minority group…
Dual-domain Adaptation Networks for Realistic Image Super-resolution
Chaowei Fang, Bolin Fu, De Cheng +2
Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones, handling more complex degradation patterns than…
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
De Cheng, Tongliang Liu, Yixiong Ning +5
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifie…
Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID
De Cheng, Lingfeng He, Nannan Wang +3
Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims to match pedestrian images of the same identity from different modalities without annotations. Existing wo…
Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
Mingyue Zeng, De Cheng, Zhipeng Xu +3
The paper introduces Symbiosis-Inspired Knowledge Distillation (SIKD), a method for incremental object detection that leverages spatial and semantic relationships between old and n…
Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning
Lingfeng He, De Cheng, Huaijie Wang +3
Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Effici…
Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model
Yinghui Xing, Qirui Wu, De Cheng +4
With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tu…
Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement
De Cheng, Xiaojian Huang, Nannan Wang +3
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial f…
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
Ying Yang, De Cheng, Chaowei Fang +4
Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is crucial for dev…
Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction
De Cheng, Yan Li, Dingwen Zhang +3
Single image dehazing as a fundamental low-level vision task, is essential for the development of robust intelligent surveillance system. In this paper, we make an early effort to…
StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning
Huaijie Wang, De Cheng, Guozhang Li +5
Video Class-Incremental Learning (VCIL) seeks to develop models that continuously learn new action categories over time without forgetting previously acquired knowledge. Unlike tra…
Single Image Dehazing with An Independent Detail-Recovery Network
Yan Li, De Cheng, Jiande Sun +3
Single image dehazing is a prerequisite which affects the performance of many computer vision tasks and has attracted increasing attention in recent years. However, most existing d…
Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detection
Qirui Wu, Shizhou Zhang, De Cheng +4
Incremental Object Detection (IOD) aims to continuously learn new object classes without forgetting previously learned ones. A persistent challenge is catastrophic forgetting, prim…
CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning
Lingfeng He, De Cheng, Zhiheng Ma +4
Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered incre…
Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning
De Cheng, Yue Lu, Lingfeng He +4
Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge. Recently, State Space Mode…
Reasoning-Driven Multimodal LLM for Domain Generalization
Zhipeng Xu, Zilong Wang, Xinyang Jiang +3
This paper addresses the domain generalization (DG) problem in deep learning. While most DG methods focus on enforcing visual feature invariance, we leverage the reasoning capabili…
Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models
Yubin Wang, Xinyang Jiang, De Cheng +2
Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies hav…
Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification
De Cheng, Haichun Tai, Nannan Wang +2
Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by…
Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id
De Cheng, Jingyu Zhou, Nannan Wang +1
Unsupervised person re-identification (Re-Id) has attracted increasing attention due to its practical application in the read-world video surveillance system. The traditional unsup…