☆ 3.8 Proceedings Paper

AirDet: Few-Shot Detection Without Fine-Tuning for Autonomous Exploration

COMPUTER VISION, ECCV 2022, PT XXXIX (2022)

Universal-Prototype Enhancing for Few-Shot Object Detection

Aming Wu et al.

Summary: This paper proposes a new framework FSODup for Few-shot object detection, which enhances object features through universal prototypes to improve generalization towards novel objects. Experimental results demonstrate the effectiveness of the framework, particularly with significant performance improvements in the 1-shot case.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Accurate Few-shot Object Detection with Support-Query Mutual Guidance and Hybrid Loss

Lu Zhang et al.

Summary: The paper introduces a novel two-stage detector for few-shot object detection by utilizing a support-query mutual guidance mechanism to generate more relevant proposals and scoring and filtering proposals based on multi-level feature comparison. Experimental results demonstrate that the method substantially outperforms existing ones and elevates the performance of the FSOD task to a higher level.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection

Hanzhe Hu et al.

Summary: In this work, a Dense Relation Distillation with Context-aware Aggregation (DCNet) is proposed to address the few-shot object detection problem by fully exploiting support features and capturing fine-grained features. The model achieves state-of-the-art results on PASCAL VOC and MS COCO datasets, demonstrating the effectiveness of the proposed approach.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence