# Fast Hierarchical Learning for Few-Shot Object Detection

arXiv: https://arxiv.org/abs/2210.05008 · HTML: https://mlsanity.com/paper/2210.05008/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 10 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Learning Discriminative Model Prediction for Tracking](https://mlsanity.com/paper/1904.07220/) (2019)
- [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)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2003.04668/) (2020)
- [Learning What to Learn for Video Object Segmentation](https://mlsanity.com/paper/2003.11540/) (2020)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [LSTD: A Low-Shot Transfer Detector for Object Detection](https://mlsanity.com/paper/1803.01529/) (2018)
- [Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking](https://mlsanity.com/paper/1608.03773/) (2016)
- [Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation](https://mlsanity.com/paper/2103.11731/) (2021)
- [IIRC: Incremental Implicitly-Refined Classification](https://mlsanity.com/paper/2012.12477/) (2020)
- [Class-Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2105.07637/) (2021)
- [Correlation Tracking via Joint Discrimination and Reliability Learning](https://mlsanity.com/paper/1804.08965/) (2018)
- [Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy](https://mlsanity.com/paper/2006.15479/) (2020)
- [Contextual Relabelling of Detected Objects](https://mlsanity.com/paper/1906.02534/) (2019)
- [Fast Few-Shot Classification by Few-Iteration Meta-Learning](https://mlsanity.com/paper/2010.00511/) (2020)
- [HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification](https://mlsanity.com/paper/2110.11148/) (2021)

## Abstract (arXiv)

Transfer learning based approaches have recently achieved promising results on the few-shot detection task. These approaches however suffer from ``catastrophic forgetting'' issue due to finetuning of base detector, leading to sub-optimal performance on the base classes. Furthermore, the slow convergence rate of stochastic gradient descent (SGD) results in high latency and consequently restricts real-time applications. We tackle the aforementioned issues in this work. We pose few-shot detection as a hierarchical learning problem, where the novel classes are treated as the child classes of existing base classes and the background class. The detection heads for the novel classes are then trained using a specialized optimization strategy, leading to significantly lower training times compared to SGD. Our approach obtains competitive novel class performance on few-shot MS-COCO benchmark, while completely retaining the performance of the initial model on the base classes. We further demonstrate the application of our approach to a new class-refined few-shot detection task.