Context-Transformer: Tackling Object Confusion for Few-Shot Detection

By Ze Yang, Yali Wang, Xianyu Chen, Jianzhuang Liu, Yu Qiao. 2020

93 citations recorded by the source corpus.

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector pretrained on a source-domain benchmark. However, such transferred detector often fails to recognize new objects in the target domain, due to low data diversity of training samples. To tackle this problem, we propose a novel Context-Transformer within a concise deep transfer framework. Specifically, Context-Transformer can effectively leverage source-domain object knowledge as guidance, and automatically exploit contexts from only a few training images in the target domain. Subsequently, it can adaptively integrate these relational clues to enhance the discriminative power of detector, in order to reduce object confusion in few-shot scenarios. Moreover, Context-Transformer is flexibly embedded in the popular SSD-style detectors, which makes it a plug-and-play module for end-to-end few-shot learning. Finally, we evaluate Context-Transformer on the challenging settings of few-shot detection and incremental few-shot detection. The experimental results show that, our framework outperforms the recent state-of-the-art approaches.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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. Guosheng Lin
2. Chi Zhang
3. Chunhua Shen
4. Yujun Cai
5. Pan Pan
6. Yun Zheng
7. Yinghui Xu
8. Nan Song

In Computer Vision and Pattern Recognition

1. Guosheng Lin
2. Chi Zhang
3. Chunhua Shen
4. Yujun Cai
5. Pan Pan
6. Han-Jia Ye
7. Yun Zheng
8. Yinghui Xu

Citations in the corpus

• Few-Shot Incremental Learning with Continually Evolved Classifiers (2021, methodology): “Apart from image classification, few-shot learning has also been applied to dense prediction tasks [6, 21, 23, 53, 54] and object detection [45].”
• DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection (2021, background): “Since previous detectors usually require a large amount of annotated data, few-shot detection has attracted more and more interest recently [2, 10, 12, 28, 31, 45, 47, 52, 54].”
• DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers (2020, unknown): “Besides image classification, few-shot learning is also investigated in image segmentation [34, 74, 75] and object detection tasks [72].”
• DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning (2020, background): “Few-shot learning has also been investigated for other computer vision tasks, such as image segmentation [92], [93], [94] and object detection [95].”