DeepAI AI Chat
Log In Sign Up

Frustratingly Simple Few-Shot Object Detection

by   Xin Wang, et al.

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


page 2

page 4

page 7

page 8


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

In this paper, we explore incremental few-shot object detection (iFSD), ...

Exploring Effective Knowledge Transfer for Few-shot Object Detection

Recently, few-shot object detection (FSOD) has received much attention f...

FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training

This paper is on Few-Shot Object Detection (FSOD), where given a few tem...

Plug-and-Play Few-shot Object Detection with Meta Strategy and Explicit Localization Inference

Aiming at recognizing and localizing the object of novel categories by a...

An Empirical Study and Comparison of Recent Few-Shot Object Detection Algorithms

The generic object detection (GOD) task has been successfully tackled by...

Classical Sequence Match is a Competitive Few-Shot One-Class Learner

Nowadays, transformer-based models gradually become the default choice f...

Efficient Few-Shot Object Detection via Knowledge Inheritance

Few-shot object detection (FSOD), which aims at learning a generic detec...

Code Repositories


Implementations of few-shot object detection benchmarks

view repo



view repo