4 papers
FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception
Mingyuan Li, Tong Jia, Han Gu +7
Overlapping object perception aims to decouple the randomly overlapping foreground-background features, extracting foreground features while suppressing background features, which…
GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects
Yizhe Liu, Tong Jia, Da Cai +2
Transparent and specular objects are frequently encountered in daily life, factories, and laboratories. However, due to the unique optical properties, the depth information on thes…
CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors
Mingyuan Li, Tong Jia, Hao Wang +5
Prohibited item detection based on X-ray images is one of the most effective security inspection methods. However, the foreground-background feature coupling caused by the overlapp…
CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels
Shizhuo Deng, Bowen Han, Jiaqi Chen +3
Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain. CLIP, a large-scale vision-language model, performs well in FSL on imag…