2 papers
cs.CV2026
TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations to Precise Segmentation
Jiabei Chen, Liping Zhang, Jiang-Bin Wu +6
The precise pixel-level localization of 2D material flakes is crucial for high-throughput screening. However, traditional fully supervised methods rely on dense annotations, which…
cs.CV2025
Cross-Layer Feature Self-Attention Module for Multi-Scale Object Detection
Dingzhou Xie, Rushi Lan, Cheng Pang +3
Recent object detection methods have made remarkable progress by leveraging attention mechanisms to improve feature discriminability. However, most existing approaches are confined…