LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection

2023-03-10 · Phi Vu Tran

Few-shot object detection (FSOD) is a challenging problem aimed at detecting novel concepts from few exemplars. Existing approaches to FSOD all assume abundant base labels to adapt to novel objects. This paper studies the new task of semi-supervised FSOD by considering a realistic scenario in which both base and novel labels are simultaneously scarce. We explore the utility of unlabeled data within our proposed label-efficient detection framework and discover its remarkable ability to boost semi-supervised FSOD by way of region proposals. Motivated by this finding, we introduce SoftER Teacher, a robust detector combining pseudo-labeling with consistency learning on region proposals, to harness unlabeled data for improved FSOD without relying on abundant labels. Rigorous experiments show that SoftER Teacher surpasses the novel performance of a strong supervised detector using only 10% of required base labels, without catastrophic forgetting observed in prior approaches. Our work also sheds light on a potential relationship between semi-supervised and few-shot detection suggesting that a stronger semi-supervised detector leads to a more effective few-shot detector.

📄 PDF Abstract BibTeX arXiv:2303.05739

Code (1)

lexisnexis-risk-open-source/ledetection 공식 구현 pytorch

Tasks

Few-Shot Object DetectionNovel Conceptsobject-detection Object Detection Representation Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Semi-DETR: Semi-Supervised Object Detection with Detection Transformers

2023-07-16 · CVPR 2023 1 · Jiacheng Zhang, Xiangru Lin, Wei zhang, Kuo Wang 외

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate,…

Object object-detection Object Detection Pseudo Label+1

Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

2023-03-27 · CVPR 2023 1 · Chang Liu, Weiming Zhang, Xiangru Lin, Wei zhang 외

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguiti…

Dense Object Detection Object object-detection Object Detection+2

Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations

2025-03-04 · Zhengyao Gu, Henry Peng Zou, Yankai Chen, Aiwei Liu 외

The high cost of obtaining high-quality annotated data for in-context learning (ICL) has motivated the development of methods that use self-generated annotations in place of ground-truth labels. While these approaches ha…

In-Context Learning

MetaGAN: An Adversarial Approach to Few-Shot Learning

2018-12-01 · NeurIPS 2018 12 · Ruixiang Zhang, Tong Che, Zoubin Ghahramani, Yoshua Bengio 외

In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems. Most state-of-the-art few-shot classification models can be integrated with MetaGAN in a principled and…

Classification Few-Shot Image Classification Few-Shot Learning General Classification+2

Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning

2022-07-14 · Xingping Dong, Tianran Ouyang, Shengcai Liao, Bo Du 외

Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervised meta-training (SSMT) setting has been …

Few-Shot Learning Meta-Learning