# Robust Unsupervised Multi-Object Tracking in Noisy Environments

arXiv: https://arxiv.org/abs/2105.10005 · HTML: https://mlsanity.com/paper/2105.10005/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 20 May 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1703.06748/) (2017)
- [Stochastic Latent Residual Video Prediction](https://mlsanity.com/paper/2002.09219/) (2020)
- [Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking](https://mlsanity.com/paper/1911.09033/) (2019)
- [GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization](https://mlsanity.com/paper/2104.12465/) (2021)
- [Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers](https://mlsanity.com/paper/1809.03137/) (2018)
- [Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement](https://mlsanity.com/paper/2003.13917/) (2020)
- [Robustness Analysis of Visual QA Models by Basic Questions](https://mlsanity.com/paper/1709.04625/) (2017)
- [A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases](https://mlsanity.com/paper/1806.06423/) (2018)
- [Contextualized Keyword Representations for Multi-modal Retinal Image Captioning](https://mlsanity.com/paper/2104.12471/) (2021)
- [Y-net: Multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazing](https://mlsanity.com/paper/2003.13912/) (2020)
- [Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning](https://mlsanity.com/paper/2002.09027/) (2020)
- [PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification](https://mlsanity.com/paper/2104.01271/) (2021)
- [S3Net: A Single Stream Structure for Depth Guided Image Relighting](https://mlsanity.com/paper/2105.00681/) (2021)
- [LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement](https://mlsanity.com/paper/2105.01299/) (2021)
- [Wavelet Channel Attention Module with a Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2007.09163/) (2020)
- [Multi-modal Bifurcated Network for Depth Guided Image Relighting](https://mlsanity.com/paper/2105.00690/) (2021)

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

- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)

## Abstract (arXiv)

Physical processes, camera movement, and unpredictable environmental conditions like the presence of dust can induce noise and artifacts in video feeds. We observe that popular unsupervised MOT methods are dependent on noise-free inputs. We show that the addition of a small amount of artificial random noise causes a sharp degradation in model performance on benchmark metrics. We resolve this problem by introducing a robust unsupervised multi-object tracking (MOT) model: AttU-Net. The proposed single-head attention model helps limit the negative impact of noise by learning visual representations at different segment scales. AttU-Net shows better unsupervised MOT tracking performance over variational inference-based state-of-the-art baselines. We evaluate our method in the MNIST-MOT and the Atari game video benchmark. We also provide two extended video datasets: ``Kuzushiji-MNIST MOT'' which consists of moving Japanese characters and ``Fashion-MNIST MOT'' to validate the effectiveness of the MOT models.