# Multi-View Correlation Distillation for Incremental Object Detection

arXiv: https://arxiv.org/abs/2107.01787 · HTML: https://mlsanity.com/paper/2107.01787/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 5 Jul 2021.

## Builds on (most cited first, 27 of 27)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [Class-incremental Learning via Deep Model Consolidation](https://mlsanity.com/paper/1903.07864/) (2019)
- [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2005.10977/) (2020)
- [Encoder Based Lifelong Learning](https://mlsanity.com/paper/1704.01920/) (2017)
- [Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2003.04668/) (2020)
- [Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning](https://mlsanity.com/paper/2001.00294/) (2020)
- [Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN](https://mlsanity.com/paper/2003.03901/) (2020)
- [Towards Robust Pattern Recognition: A Review](https://mlsanity.com/paper/2006.06976/) (2020)
- [Less-forgetful Learning for Domain Expansion in Deep Neural Networks](https://mlsanity.com/paper/1711.05959/) (2017)
- [Context-Transformer: Tackling Object Confusion for Few-Shot Detection](https://mlsanity.com/paper/2003.07304/) (2020)
- [FoCL: Feature-Oriented Continual Learning for Generative Models](https://mlsanity.com/paper/2003.03877/) (2020)
- [A Neurobiological Evaluation Metric for Neural Network Model Search](https://mlsanity.com/paper/1805.10726/) (2018)
- [Lifelong Metric Learning](https://mlsanity.com/paper/1705.01209/) (2017)

## Built on by (most cited first, 30 of 36)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Continual Detection Transformer for Incremental Object Detection](https://mlsanity.com/paper/2304.03110/) (2023)
- [Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference](https://mlsanity.com/paper/2211.15969/) (2022)
- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection](https://mlsanity.com/paper/2307.12427/) (2023)
- [MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition](https://mlsanity.com/paper/2208.05768/) (2022)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)
- [Dense Semantic Contrast for Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2109.07756/) (2021)
- [Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection](https://mlsanity.com/paper/2109.03426/) (2021)
- [Modeling Missing Annotations for Incremental Learning in Object Detection](https://mlsanity.com/paper/2204.08766/) (2022)
- [VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model](https://mlsanity.com/paper/2403.05346/) (2024)
- [Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection](https://mlsanity.com/paper/2407.11499/) (2024)
- [Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning](https://mlsanity.com/paper/2212.14284/) (2022)
- [Knowledge Distillation Using Hierarchical Self-Supervision Augmented Distribution](https://mlsanity.com/paper/2109.03075/) (2021)
- [Refining CLIP's Spatial Awareness: A Visual-Centric Perspective](https://mlsanity.com/paper/2504.02328/) (2025)
- [Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts](https://mlsanity.com/paper/2507.07100/) (2025)
- [MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition](https://mlsanity.com/paper/2305.14758/) (2023)
- [DCA: Dividing and Conquering Amnesia in Incremental Object Detection](https://mlsanity.com/paper/2503.15295/) (2025)
- [Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector](https://mlsanity.com/paper/2502.05540/) (2025)
- [Multi-View Class Incremental Learning](https://mlsanity.com/paper/2306.09675/) (2023)
- [USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model](https://mlsanity.com/paper/2306.02275/) (2023)
- [Specifying What You Know or Not for Multi-Label Class-Incremental Learning](https://mlsanity.com/paper/2503.17017/) (2025)
- [I3DOD: Towards Incremental 3D Object Detection via Prompting](https://mlsanity.com/paper/2308.12512/) (2023)
- [BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection](https://mlsanity.com/paper/2403.02637/) (2024)
- [MultIOD: Rehearsal-free Multihead Incremental Object Detector](https://mlsanity.com/paper/2309.05334/) (2023)
- [Incremental Object Detection with CLIP](https://mlsanity.com/paper/2310.08815/) (2023)
- [DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic](https://mlsanity.com/paper/2506.21260/) (2025)
- [Class-Incremental Motion Forecasting](https://mlsanity.com/paper/2603.09420/) (2026)
- [Focus, Align, and Sustain: Counteracting Gradient Dilution in Incremental Object Detection](https://mlsanity.com/paper/2606.15253/) (2026)
- [Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection](https://mlsanity.com/paper/2607.17340/) (2026)

## Abstract (arXiv)

In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data. Fine-tuning the old model with only new data will lead to a well-known phenomenon of catastrophic forgetting, which severely degrades the performance of modern object detectors. In this paper, we propose a novel Multi-View Correlation Distillation (MVCD) based incremental object detection method, which explores the correlations in the feature space of the two-stage object detector (Faster R-CNN). To better transfer the knowledge learned from the old classes and maintain the ability to learn new classes, we design correlation distillation losses from channel-wise, point-wise and instance-wise views to regularize the learning of the incremental model. A new metric named Stability-Plasticity-mAP is proposed to better evaluate both the stability for old classes and the plasticity for new classes in incremental object detection. The extensive experiments conducted on VOC2007 and COCO demonstrate that MVCD can effectively learn to detect objects of new classes and mitigate the problem of catastrophic forgetting.