← Search

Shenghao Yu

2 accepted papers

2024

Zero-Shot Object Detection with Partitioned Contrastive Feature Alignment

ICASSP 2024accepted

How to properly align the extracted visual features with certain semantic embeddings of unseen objects is crucial to the problem of Zero-Shot Object Detection (ZSD). To give a better guess of those unseen visual features, a partitioned contrast strategy is proposed in this paper to train the visual…

Cited by 0SourceScholar
2022

Novel Instance Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection

ICASSP 2022accepted

Few-shot object detection (FSOD) enables the detector to recognize novel objects only using limited training samples, which could greatly alleviate model’s dependency on data. Most existing methods include two training stages, namely base training and fine-tuning. However, the unlabeled novel instan…

Cited by 0SourceScholar