Class-Incremental Few-Shot Object Detection

By Pengyang Li, Yanan Li, Donghui Wang. 2021

14 citations recorded by the source corpus.

Conventional detection networks usually need abundant labeled training samples, while humans can learn new concepts incrementally with just a few examples. This paper focuses on a more challenging but realistic class-incremental few-shot object detection problem (iFSD). It aims to incrementally transfer the model for novel objects from only a few annotated samples without catastrophically forgetting the previously learned ones. To tackle this problem, we propose a novel method LEAST, which can transfer with Less forgetting, fEwer training resources, And Stronger Transfer capability. Specifically, we first present the transfer strategy to reduce unnecessary weight adaptation and improve the transfer capability for iFSD. On this basis, we then integrate the knowledge distillation technique using a less resource-consuming approach to alleviate forgetting and propose a novel clustering-based exemplar selection process to preserve more discriminative features previously learned. Being a generic and effective method, LEAST can largely improve the iFSD performance on various benchmarks.

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. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Qiwen Wang
5. Ziwei Liu
6. Zhiyuan Qi
7. Mang Wang
8. Hangjie Yuan

In Computer Vision and Pattern Recognition

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Qiwen Wang
5. Ziwei Liu
6. Zhiyuan Qi
7. Hangjie Yuan
8. Mang Wang

Citations in the corpus

• Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation (2022, background): “[18] studied object detection based on class-incremental learning on Faster RCNN detector with emphasis on few-shot scenarios, which is also the focus of ONCE algorithm [29].”
• Class-Incremental Learning: A Survey (2023, background): “Other recent works also address the specific settings like few-shot IOD [242], [270], [271], [272], open-world IOD [244] and 3D IOD [273].”