# Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detection

arXiv: https://arxiv.org/abs/2606.15253 · HTML: https://mlsanity.com/paper/2606.15253/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 13 Jun 2026.

## Builds on (most cited first, 28 of 28)

- [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)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [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)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation](https://mlsanity.com/paper/2204.02136/) (2022)
- [Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN](https://mlsanity.com/paper/2003.03901/) (2020)
- [Continual Detection Transformer for Incremental Object Detection](https://mlsanity.com/paper/2304.03110/) (2023)
- [Incremental Object Detection via Meta-Learning](https://mlsanity.com/paper/2003.08798/) (2020)
- [PROB: Probabilistic Objectness for Open World Object Detection](https://mlsanity.com/paper/2212.01424/) (2022)
- [Memory Efficient Class-Incremental Learning for Image Classification](https://mlsanity.com/paper/2008.01411/) (2020)
- [SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection](https://mlsanity.com/paper/2402.17323/) (2024)
- [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)
- [Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection](https://mlsanity.com/paper/2307.12427/) (2023)
- [Modeling Missing Annotations for Incremental Learning in Object Detection](https://mlsanity.com/paper/2204.08766/) (2022)
- [DCA: Dividing and Conquering Amnesia in Incremental Object Detection](https://mlsanity.com/paper/2503.15295/) (2025)
- [Dynamic Object Queries for Transformer-based Incremental Object Detection](https://mlsanity.com/paper/2407.21687/) (2024)
- [Specifying What You Know or Not for Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2503.17017/) (2025)

## Built on by (most cited first, 1 of 1)

- [Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection](https://mlsanity.com/paper/2607.17340/) (2026)

## Abstract (arXiv)

Adapting Detection Transformers to Incremental Object Detection (IOD) poses a systemic challenge, as set-based optimization is inherently destabilized by sequential learning. In this work, we identify Gradient Dilution as the root cause of performance degradation, wherein optimization signals required to preserve old knowledge are progressively weakened. This phenomenon manifests as a cascading erosion of preservation gradients in magnitude, direction, and support coverage, driven by three tightly coupled factors: Signal Dispersion, where foreground gradients are overwhelmed by background noise; Assignment Drift, where stochastic query-target matching induces inconsistent gradient trajectories; and Support Attrition, where gradients from retained samples insufficiently cover the old-class feature space, weakening decision boundaries under interference from new classes. To counteract this, we propose FAS, a unified framework that Focuses, Aligns, and Sustains gradient flow throughout incremental learning. Specifically, we introduce prior-injected queries to focus discriminative signals by filtering background interference at the source. We further propose deterministic anchor distillation to align query-target assignments and enforce semantic consistency across stages under unstable matching. Finally, we devise manifold-support replay to sustain distributional support of old classes, counteracting representational erosion induced by continual updates. Extensive experiments show that FAS restores robust optimization dynamics and outperforms state-of-the-art methods, achieving over 5.0 AP improvement in the challenging 40+10x4 incremental setting.