Abstract

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 layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the evaluation protocols by sampling multiple groups of training examples to obtain stable comparisons and build new benchmarks based on three datasets: PASCAL VOC, COCO and LVIS. Again, our fine-tuning approach establishes a new state of the art on the revised benchmarks.

Paper

Xin Wang, Thomas E. Huang, Trevor Darrell, Joseph E. Gonzalez, Fisher Yu Frustratingly Simple Few-Shot Object Detection ICML 2020

Code

github.com/ucbdrive/few-shot-object-detection

Citation

@article{wang2020frustratingly,
  title={Frustratingly simple few-shot object detection},
  author={Wang, Xin and Huang, Thomas E and Darrell, Trevor and Gonzalez, Joseph E and Yu, Fisher},
  journal={ICML},
  year={2020}
}