6 papers · 1 filter
Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning
Yuyuan Liu, Can Peng, Yingyu Yang +3
Recent progress in deep learning has significantly advanced CT image analysis, particularly for segmentation tasks. However, these advances are largely confined to image-level patt…
From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding
Yuyuan Liu, Yiping Ji, Anjie Le +6
Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing met…
AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
Yuyuan Liu, Yuanhong Chen, Chong Wang +6
Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. E…
POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse
Anjie Le, Can Peng, Yuyuan Liu +1
In computer vision, machine unlearning aims to remove the influence of specific visual concepts or training images without retraining from scratch. Studies show that existing appro…
Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew
Can Peng, Yuyuan Liu, Yingyu Yang +3
Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, but remains challenging when client data are highly heterogen…
FOCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics
Pramit Saha, Felix Wagner, Divyanshu Mishra +5
Effective training of large Vision-Language Models (VLMs) on resource-constrained client devices in Federated Learning (FL) requires the usage of parameter-efficient fine-tuning (P…