Frustratingly Simple Few-Shot Object Detection

By Thomas E. Huang, Trevor Darrell, Joseph E. Gonzalez, Fisher Yu. 2020

747 citations recorded by the source corpus.

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. The code as well as the pretrained models are available at this https URL.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

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. Jianfeng Gao
  2. Mohit Bansal
  3. Zhe Gan
  4. Trevor Darrell
  5. Bernt Schiele
  6. Caiming Xiong
  7. Percy Liang
  8. Yoshua Bengio

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Ming-Hsuan Yang
  5. Bernt Schiele
  6. Xiaogang Wang
  7. Jitendra Malik
  8. Andrew Zisserman

In Meta & Continual Learning

  1. Bernt Schiele
  2. Yaoyao Liu
  3. K. J. Joseph
  4. Vineeth Nallure Balasubramanian
  5. Qianru Sun
  6. Salman Hameed Khan
  7. Han-Jia Ye
  8. De-chuan Zhan

Citations in the corpus