# Frustratingly Simple Few-Shot Object Detection

arXiv: https://arxiv.org/abs/2003.06957 · HTML: https://mlsanity.com/paper/2003.06957/

## Key facts

- Cited by 282 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 30 of 282)

- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [GLIPv2: Unifying Localization and Vision-Language Understanding](https://mlsanity.com/paper/2206.05836/) (2022)
- [Visual Prompting via Image Inpainting](https://mlsanity.com/paper/2209.00647/) (2022)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models](https://mlsanity.com/paper/2204.08790/) (2022)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving](https://mlsanity.com/paper/2203.07724/) (2022)
- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)
- [Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection](https://mlsanity.com/paper/2103.15158/) (2021)
- [DETReg: Unsupervised Pretraining with Region Priors for Object Detection](https://mlsanity.com/paper/2106.04550/) (2021)
- [Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment](https://mlsanity.com/paper/2305.11733/) (2023)
- [Relational Embedding for Few-Shot Classification](https://mlsanity.com/paper/2108.09666/) (2021)
- [Few-Shot Object Detection with Fully Cross-Transformer](https://mlsanity.com/paper/2203.15021/) (2022)
- [Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment](https://mlsanity.com/paper/2104.07719/) (2021)
- [Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks](https://mlsanity.com/paper/2112.09791/) (2021)
- [Few-shot Object Counting and Detection](https://mlsanity.com/paper/2207.10988/) (2022)
- [Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types](https://mlsanity.com/paper/2103.13318/) (2021)
- [Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection](https://mlsanity.com/paper/2103.17115/) (2021)
- [Spatio-temporal Relation Modeling for Few-shot Action Recognition](https://mlsanity.com/paper/2112.05132/) (2021)
- [Multi-Modal Classifiers for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.05493/) (2023)

## Abstract (arXiv)

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.