FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

By Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan. Computer Vision and Pattern Recognition, 2021

543 citations recorded by the source corpus.

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 key to reach favorable few-shot learning performance. We observe object proposals with different Intersection-of-Union (IoU) scores are analogous to the intra-image augmentation used in contrastive visual representation learning. And we exploit this analogy and incorporate supervised contrastive learning to achieve more robust objects representations in FSOD. We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects. We notice the degradation of average precision (AP) for rare objects mainly comes from misclassifying novel instances as confusable classes. And we ease the misclassification issues by promoting instance level intraclass compactness and inter-class variance via our contrastive proposal encoding loss (CPE loss). Our design outperforms current state-of-the-art works in any shot and all data splits, with up to +8.8% on standard benchmark PASCAL VOC and +2.7% on challenging COCO benchmark. Code is available at: https://github.com/MegviiDetection/FSCE.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9833833941dd64af2314ab81f49ccc725f7d2a0b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lifu Huang
2. Ming Ding
3. Yongqiang Zhang
4. Na Dong
5. Gim Hee Lee
6. Sijia Wang
7. Mo Yu
8. Zhiyuan Liu

In Computer Vision and Pattern Recognition

1. Yongqiang Zhang
2. Ming Ding
3. Na Dong
4. Gim Hee Lee
5. Sijia Wang
6. Lifu Huang
7. Mo Yu
8. Bernard Ghanem

Citations in the corpus

• Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data (2023, background): “Approaches of few-shot object detection can be categorized into meta-learning based [34, 11, 36, 38] and fine-tuning based methods [33, 35, 27].”
• The Art of Prompting: Event Detection based on Type Specific Prompts (2022, background): “Few-shot Event Detection: Two primary learning strategies in few-shot classification tasks are Meta-Learning (Kang et al., 2019; Li et al., 2021; Xiao and Marlet, 2020; Yan et al., 2019; Chowd-hury et al., 2021), and Metric Learning (Sun et al., 2021; Wang et al., 2020b; Zhang et al., 2021a; Agarwal ”
• A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, unknown): “FSCE [248] CVPR’21 ResNet-101 Transfer learning 11.”