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

arXiv: https://arxiv.org/abs/2302.09779 · HTML: https://mlsanity.com/paper/2302.09779/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild](https://mlsanity.com/paper/2007.12107/) (2020)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2003.04668/) (2020)
- [Adaptive Cross-Modal Few-Shot Learning](https://mlsanity.com/paper/1902.07104/) (2019)
- [RepMet: Representative-based metric learning for classification and one-shot object detection](https://mlsanity.com/paper/1806.04728/) (2018)
- [Incremental Few-Shot Instance Segmentation](https://mlsanity.com/paper/2105.05312/) (2021)
- [Few-Shot Object Detection via Association and DIscrimination](https://mlsanity.com/paper/2111.11656/) (2021)
- [Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection](https://mlsanity.com/paper/2203.13903/) (2022)
- [Class-Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2105.07637/) (2021)
- [Towards Generalized and Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2109.11336/) (2021)

## Built on by (most cited first, 2 of 2)

- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)

## Abstract (arXiv)

In this paper, we explore incremental few-shot object detection (iFSD), which incrementally learns novel classes using only a few examples without revisiting base classes. Previous iFSD works achieved the desired results by applying meta-learning. However, meta-learning approaches show insufficient performance that is difficult to apply to practical problems. In this light, we propose a simple fine-tuning-based approach, the Incremental Two-stage Fine-tuning Approach (iTFA) for iFSD, which contains three steps: 1) base training using abundant base classes with the class-agnostic box regressor, 2) separation of the RoI feature extractor and classifier into the base and novel class branches for preserving base knowledge, and 3) fine-tuning the novel branch using only a few novel class examples. We evaluate our iTFA on the real-world datasets PASCAL VOC, COCO, and LVIS. iTFA achieves competitive performance in COCO and shows a 30% higher AP accuracy than meta-learning methods in the LVIS dataset. Experimental results show the effectiveness and applicability of our proposed method.