Frustratingly Simple Few-Shot Object Detection

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.

arXiv comment12 pages, 8 figures

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Prototypical Networks for Few-shot Learning
• On First-Order Meta-Learning Algorithms
• A Closer Look at Few-shot Classification

Cited by in corpus (21)

• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• Dynamic Relevance Learning for Few-Shot Object Detection
• Class-Incremental Few-Shot Object Detection
• Hallucination Improves Few-Shot Object Detection
• Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
• Dual-Awareness Attention for Few-Shot Object Detection
• Modeling and Optimization Trade-off in Meta-learning
• Online Structured Meta-learning
• Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
• Towards Generalized and Incremental Few-Shot Object Detection
• Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
• Towards Open World Object Detection
• MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
• Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection
• Dataset Bias in Few-shot Image Recognition
• Procrustean Training for Imbalanced Deep Learning
• Top-Related Meta-Learning Method for Few-Shot Object Detection
• Few-Shot Video Object Detection
• A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters