1 citations · 1 across the 15 of their papers we have counts for
18 papers
Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning
Chiyuan He, Zihuan Qiu, Fanman Meng +5
Benefiting from transferable visual-textual alignment, CLIP has been widely adopted for class-incremental learning (CIL). However, existing learners either repeatedly update compon…
SAFE-Merge: Data-Free Continual Model Merging with General Knowledge Preservation
Zihuan Qiu, Zhiyang Liao, Chiyuan He +5
Data-free continual model merging must incorporate a stream of specialized models while retaining both pretrained general knowledge and previously acquired tasks, without access to…
Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency
Zhaofeng Shi, Heqian Qiu, Lanxiao Wang +4
Efficient adaptation between Egocentric (Ego) and Exocentric (Exo) views is crucial for applications such as human-robot cooperation. However, the success of most existing Ego-Exo…
Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
Chiyuan He, Zihuan Qiu, Fanman Meng +4
Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cros…
Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learning
Zihuan Qiu, Yi Xu, Fanman Meng +4
Class Incremental Learning (CIL) aims to sequentially acquire knowledge of new classes without forgetting previously learned ones. Despite recent progress, current CIL methods stil…
Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity
Zihuan Qiu, Lei Wang, Yang Cao +7
Data-free continual model merging (DFCMM) aims to fuse independently fine-tuned models into a single backbone that evolves with incoming tasks without accessing task data. This pap…
DFR: A Decompose-Fuse-Reconstruct Framework for Multi-Modal Few-Shot Segmentation
Shuai Chen, Fanman Meng, Xiwei Zhang +4
This paper presents DFR (Decompose, Fuse and Reconstruct), a novel framework that addresses the fundamental challenge of effectively utilizing multi-modal guidance in few-shot segm…
Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection
Taijin Zhao, Heqian Qiu, Yu Dai +4
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predomina…
Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion
Yukun Chen, Zihuan Qiu, Fanman Meng +3
Unlike traditional Multimodal Class-Incremental Learning (MCIL) methods that focus only on vision and text, this paper explores MCIL across vision, audio and text modalities, addre…
Your Demands Deserve More Bits: Referring Semantic Image Compression at Ultra-low Bitrate
Chenhao Wu, Qingbo Wu, Haoran Wei +5
With the help of powerful generative models, Semantic Image Compression (SIC) has achieved impressive performance at ultra-low bitrate. However, due to coarse-grained visual-semant…
MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
Zihuan Qiu, Yi Xu, Chiyuan He +4
Continual model merging integrates independently fine-tuned models sequentially without access to the original training data, offering a scalable and efficient solution for continu…
CMaP-SAM: Contraction Mapping Prior for SAM-driven Few-shot Segmentation
Shuai Chen, Fanman Meng, Liming Lei +5
Few-shot segmentation (FSS) aims to segment new classes using few annotated images. While recent FSS methods have shown considerable improvements by leveraging Segment Anything Mod…
Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation
Zhaofeng Shi, Heqian Qiu, Lanxiao Wang +3
Even from an early age, humans naturally adapt between exocentric (Exo) and egocentric (Ego) perspectives to understand daily procedural activities. Inspired by this cognitive abil…
DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition
Chiyuan He, Zihuan Qiu, Fanman Meng +3
Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while…
Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
Zhaofeng Shi, Heqian Qiu, Lanxiao Wang +3
In this paper, we explore a novel Text-supervised Egocentic Semantic Segmentation (TESS) task that aims to assign pixel-level categories to egocentric images weakly supervised by t…
Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Images
Yilei Qian, Kanglei Geng, Kailong Chen +5
The application of activity recognition in the "AI + Education" field is gaining increasing attention. However, current work mainly focuses on the recognition of activities in manu…
No Re-Train, More Gain: Upgrading Backbones with Diffusion model for Pixel-Wise and Weakly-Supervised Few-Shot Segmentation
Shuai Chen, Fanman Meng, Chenhao Wu +5
Few-Shot Segmentation (FSS) aims to segment novel classes using only a few annotated images. Despite considerable progress under pixel-wise support annotation, current FSS methods…
On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
Chenhao Wu, Qingbo Wu, Haoran Wei +5
Despite demonstrating superior rate-distortion (RD) performance, learning-based image compression (LIC) algorithms have been found to be vulnerable to malicious perturbations in re…