Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning

2022-08-15 · Dongwoo Park, Jong-Min Lee

Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a hierarchical attention network with sequentially large receptive fields to fully exploit the query and support images. In addition, meta-learning does not distinguish the categories well because it determines whether the support and query images match. In other words, metric-based learning for classification is ineffective because it does not work directly. Thus, we propose a contrastive learning method called meta-contrastive learning, which directly helps achieve the purpose of the meta-learning strategy. Finally, we establish a new state-of-the-art network, by realizing significant margins. Our method brings 2.3, 1.0, 1.3, 3.4 and 2.4% AP improvements for 1-30 shots object detection on COCO dataset. Our code is available at: https://github.com/infinity7428/hANMCL

📄 PDF Abstract BibTeX arXiv:2208.07039

Code (1)

infinity7428/hANMCL 공식 구현 pytorch

Tasks

Contrastive Learning Few-Shot Learning Few-Shot Object Detection Meta-Learning object-detection Object Detection

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning

2019-10-01 · ICCV 2019 10 · Xiaopeng Yan, Ziliang Chen, Anni Xu, Xiaoxi Wang 외

Resembling the rapid learning capability of human, low-shot learning empowers vision systems to understand new concepts by training with few samples. Leading approaches derived from meta-learning on images with a single …

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

Meta-RCNN: Meta Learning for Few-Shot Object Detection

2019-09-25 · Xiongwei Wu, Doyen Sahoo, Steven C. H. Hoi

Despite significant advances in object detection in recent years, training effective detectors in a small data regime remains an open challenge. Labelling training data for object detection is extremely expensive, and th…

Cross-Domain Few-Shot Object Detection Few-Shot Object Detection Meta-Learning Object+3

Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning

2019-09-28 · Xiaopeng Yan, Ziliang Chen, Anni Xu, Xiaoxi Wang 외

Resembling the rapid learning capability of human, few-shot learning empowers vision systems to understand new concepts by training with few samples. Leading approaches derived from meta-learning on images with a single …

Few-Shot Learning Few-Shot Object Detection Meta-Learning Object+3

Frustratingly Simple Few-Shot Object Detection

2020-03-16 · ICML 2020 1 · Xin Wang, Thomas E. Huang, Trevor Darrell, Joseph E. Gonzalez 외

Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last la…

Cross-Domain Few-Shot Object Detection Few-Shot Object Detection Meta-Learning Object+2

Top-Related Meta-Learning Method for Few-Shot Object Detection

2020-07-14 · Qian Li, Nan Guo, Xiaochun Ye, Duo Wang 외

Many meta-learning methods are proposed for few-shot detection. However, previous most methods have two main problems, poor detection APs, and strong bias because of imbalance and insufficient datasets. Previous works ma…

Few-Shot Object Detection Meta-Learning object-detection Object Detection