Frustratingly Simple Few-Shot Object Detection

Xin Wang, Thomas E. Huang, Trevor Darrell, Joseph E. Gonzalez, Fisher Yu
3/16/2020
cs.CV

Official code: ucbdrive/few-shot-object-detection (1,217 stars, Apache-2.0, last commit 2023-11-21).

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. The code as well as the pretrained models are available at https://github.com/ucbdrive/few-shot-object-detection.

View on arXivView PDF

Code Implementations(1)

ucbdrive/few-shot-object-detectionOfficial100%
Apache-2.0

Implementations of few-shot object detection benchmarks

1,217222PythonMar 16, 20202 years agoApache-2.0
few-shot-learningfew-shot-object-detectionicml-2020

Similar Papers

Meta-Tuning Loss Functions and Data Augmentation for Few-Shot Object Detection

90% match2023

Few-shot Object Detection via Feature Reweighting

89% match1 repo5652018

Efficient Meta-Learning Enabled Lightweight Multiscale Few-Shot Object Detection in Remote Sensing Images

88% match2024

Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark

87% match1 repo132022

Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach

87% match1 repo102023

Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation

87% match1 repo4342022

Cite this paper

@article{wang2020frustratingly,
  title  = {Frustratingly Simple Few-Shot Object Detection},
  author = {Xin Wang and Thomas E. Huang and Trevor Darrell and Joseph E. Gonzalez and Fisher Yu},
  year   = {2020},
  eprint = {2003.06957},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2003.06957}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2003.06957.svg)](https://codeofpaper.com/paper/2003.06957)

Discussion