# DCA: Dividing and Conquering Amnesia in Incremental Object Detection

arXiv: https://arxiv.org/abs/2503.15295 · HTML: https://mlsanity.com/paper/2503.15295/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion](https://mlsanity.com/paper/2111.11326/) (2021)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [CLIP-KD: An Empirical Study of CLIP Model Distillation](https://mlsanity.com/paper/2307.12732/) (2023)
- [AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning](https://mlsanity.com/paper/2305.11488/) (2023)
- [Multi-View Correlation Distillation for Incremental Object Detection](https://mlsanity.com/paper/2107.01787/) (2021)
- [SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation](https://mlsanity.com/paper/2012.15439/) (2020)
- [Lifelong Object Detection](https://mlsanity.com/paper/2009.01129/) (2020)

## Built on by (most cited first, 7 of 7)

- [Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging](https://mlsanity.com/paper/2605.18608/) (2026)
- [Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review](https://mlsanity.com/paper/2508.03317/) (2025)
- [Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detection](https://mlsanity.com/paper/2606.15253/) (2026)
- [Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection](https://mlsanity.com/paper/2607.13452/) (2026)
- [Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection](https://mlsanity.com/paper/2607.17340/) (2026)
- [Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detection](https://mlsanity.com/paper/2603.01524/) (2026)
- [Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2608.30316/) (2026)

## Abstract (arXiv)

Incremental object detection (IOD) aims to cultivate an object detector that can continuously localize and recognize novel classes while preserving its performance on previous classes. Existing methods achieve certain success by improving knowledge distillation and exemplar replay for transformer-based detection frameworks, but the intrinsic forgetting mechanisms remain underexplored. In this paper, we dive into the cause of forgetting and discover forgetting imbalance between localization and recognition in transformer-based IOD, which means that localization is less-forgetting and can generalize to future classes, whereas catastrophic forgetting occurs primarily on recognition. Based on these insights, we propose a Divide-and-Conquer Amnesia (DCA) strategy, which redesigns the transformer-based IOD into a localization-then-recognition process. DCA can well maintain and transfer the localization ability, leaving decoupled fragile recognition to be specially conquered. To reduce feature drift in recognition, we leverage semantic knowledge encoded in pre-trained language models to anchor class representations within a unified feature space across incremental tasks. This involves designing a duplex classifier fusion and embedding class semantic features into the recognition decoding process in the form of queries. Extensive experiments validate that our approach achieves state-of-the-art performance, especially for long-term incremental scenarios. For example, under the four-step setting on MS-COCO, our DCA strategy significantly improves the final AP by 6.9%.