Search Results for author:
Found 4 papers, 3 papers with code
SimAda: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes
In this paper, we aim to investigate the impact of the general vision modules on finetuning SAM and enable them to generalize across all downstream tasks.
BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
To this end, we propose Scalable Bias-Mode Attention Mask (BA-SAM) to enhance SAM's adaptability to varying image resolutions while eliminating the need for structure modifications.
Rethinking Implicit Neural Representations for Vision Learners
Existing INRs methods suffer from two problems: 1) narrow theoretical definitions of INRs are inapplicable to high-level tasks; 2) lack of representation capabilities to deep networks.
See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval
To explore the fine-grained alignment, we further propose two implicit semantic alignment paradigms: multi-level alignment (MLA) and bidirectional mask modeling (BMM).
