Few-shot Object Detection with Refined Contrastive Learning

2022-11-24 · Zeyu Shangguan, Lian Huai, Tong Liu, Xingqun Jiang

Due to the scarcity of sampling data in reality, few-shot object detection (FSOD) has drawn more and more attention because of its ability to quickly train new detection concepts with less data. However, there are still failure identifications due to the difficulty in distinguishing confusable classes. We also notice that the high standard deviation of average precision reveals the inconsistent detection performance. To this end, we propose a novel FSOD method with Refined Contrastive Learning (FSRC). A pre-determination component is introduced to find out the Resemblance Group from novel classes which contains confusable classes. Afterwards, Refined Contrastive Learning (RCL) is pointedly performed on this group of classes in order to increase the inter-class distances among them. In the meantime, the detection results distribute more uniformly which further improve the performance. Experimental results based on PASCAL VOC and COCO datasets demonstrate our proposed method outperforms the current state-of-the-art research.

📄 PDF Abstract BibTeX arXiv:2211.13495

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning Few-Shot Object DetectionObjectobject-detection Object Detection

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection

2024-08-30 · Xuejing Li, Weijia Zhang, Chao Ma

Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and novel classes with very few annotations. Th…

3D Object Detection object-detection Object Detection

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

2021-03-10 · CVPR 2021 1 · Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan 외

Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the ke…

Contrastive Learning Cross-Domain Few-Shot Object Detection Few-Shot Learning Few-Shot Object Detection+4

Single-Shot Refinement Neural Network for Object Detection

2017-11-18 · CVPR 2018 6 · Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei 외

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both wh…

Object object-detection Object Detection

FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning

2026-03-24 · Jingchen Ni, Quan Zhang, Dan Jiang, Keyu Lv 외 arxiv

Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supe…

Representation Learning Contrastive Learning Object Detection

Few-shot Oriented Object Detection with Memorable Contrastive Learning in Remote Sensing Images

2024-03-20 · Jiawei Zhou, Wuzhou Li, Yi Cao, Hongtao Cai 외

Few-shot object detection (FSOD) has garnered significant research attention in the field of remote sensing due to its ability to reduce the dependency on large amounts of annotated data. However, two challenges persist …

Contrastive Learning Few-Shot Object Detection Object object-detection+2