# Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting

arXiv: https://arxiv.org/abs/2205.03307 · HTML: https://mlsanity.com/paper/2205.03307/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for continual learning, one of 12 directions in Knowledge distillation.
- Builds on 42 of its 73 references that are in the map.
- First posted on arXiv 6 May 2022.

## Placed in

- Knowledge distillation / [Distillation for continual learning](https://mlsanity.com/distill/distillation-for-continual-learning/)

## Builds on (most cited first, 30 of 42)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds](https://mlsanity.com/paper/1808.01050/) (2018)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [Distribution Matching for Crowd Counting](https://mlsanity.com/paper/2009.13077/) (2020)
- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [Switching Convolutional Neural Network for Crowd Counting](https://mlsanity.com/paper/1708.00199/) (2017)
- [Learning Representation for Clustering via Prototype Scattering and Positive Sampling](https://mlsanity.com/paper/2111.11821/) (2021)
- [Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs](https://mlsanity.com/paper/1708.00953/) (2017)
- [CrowdNet: A Deep Convolutional Network for Dense Crowd Counting](https://mlsanity.com/paper/1608.06197/) (2016)
- [Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting](https://mlsanity.com/paper/2012.04529/) (2020)
- [From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer](https://mlsanity.com/paper/1908.06473/) (2019)
- [Crowd Counting with Deep Structured Scale Integration Network](https://mlsanity.com/paper/1908.08692/) (2019)
- [ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding](https://mlsanity.com/paper/1811.11968/) (2018)
- [Counting with Focus for Free](https://mlsanity.com/paper/1903.12206/) (2019)
- [HA-CCN: Hierarchical Attention-based Crowd Counting Network](https://mlsanity.com/paper/1907.10255/) (2019)
- [Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method](https://mlsanity.com/paper/1910.12384/) (2019)
- [Cross-View Cross-Scene Multi-View Crowd Counting](https://mlsanity.com/paper/2205.01551/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)

## Built on by (most cited first, 9 of 9)

- [CountFormer: Multi-View Crowd Counting Transformer](https://mlsanity.com/paper/2407.02047/) (2024)
- [Continual Learning for Smart City: A Survey](https://mlsanity.com/paper/2404.00983/) (2024)
- [Cross-head Supervision for Crowd Counting with Noisy Annotations](https://mlsanity.com/paper/2303.09245/) (2023)
- [Domain Incremental Lifelong Learning in an Open World](https://mlsanity.com/paper/2305.06555/) (2023)
- [Towards Model-Based Data Acquisition for Subjective Multi-Task NLP Problems](https://mlsanity.com/paper/2312.08198/) (2023)
- [Continuous Risk Prediction](https://mlsanity.com/paper/2410.09449/) (2024)
- [Density Map Distillation for Incremental Object Counting](https://mlsanity.com/paper/2304.05255/) (2023)
- [Continuous QA Learning with Structured Prompts](https://mlsanity.com/paper/2208.14602/) (2022)
- [A Unified Object Counting Network with Object Occupation Prior](https://mlsanity.com/paper/2212.14193/) (2022)

## Abstract (arXiv)

Crowd counting has important applications in public safety and pandemic control. A robust and practical crowd counting system has to be capable of continuously learning with the new incoming domain data in real-world scenarios instead of fitting one domain only. Off-the-shelf methods have some drawbacks when handling multiple domains: (1) the models will achieve limited performance (even drop dramatically) among old domains after training images from new domains due to the discrepancies of intrinsic data distributions from various domains, which is called catastrophic forgetting; (2) the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of the domain shift; and (3) it leads to linearly increasing storage overhead, either mixing all the data for training or simply training dozens of separate models for different domains when new ones are available. To overcome these issues, we investigated a new crowd counting task in the incremental domains training setting called Lifelong Crowd Counting. Its goal is to alleviate the catastrophic forgetting and improve the generalization ability using a single model updated by the incremental domains. Specifically, we propose a self-distillation learning framework as a benchmark (Forget Less, Count Better, or FLCB) for lifelong crowd counting, which helps the model sustainably leverage previous meaningful knowledge for better crowd counting to mitigate the forgetting when the new data arrive. In addition, a new quantitative metric, normalized backward transfer (nBwT), is developed to evaluate the forgetting degree of the model in the lifelong learning process. Extensive experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.