# Balancing Specialization, Generalization, and Compression for Detection and Tracking

arXiv: https://arxiv.org/abs/1909.11348 · HTML: https://mlsanity.com/paper/1909.11348/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection](https://mlsanity.com/paper/2110.09246/) (2021)
- [Few-shot Learning with Noisy Labels](https://mlsanity.com/paper/2204.05494/) (2022)
- [Learning Rotation Invariant Features for Cryogenic Electron Microscopy Image Reconstruction](https://mlsanity.com/paper/2101.03549/) (2021)
- [Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression](https://mlsanity.com/paper/2102.07181/) (2021)
- [Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustness](https://mlsanity.com/paper/2109.01945/) (2021)
- [Collaborative Image Understanding](https://mlsanity.com/paper/2210.11907/) (2022)

## Abstract (arXiv)

We propose a method for specializing deep detectors and trackers to restricted settings. Our approach is designed with the following goals in mind: (a) Improving accuracy in restricted domains; (b) preventing overfitting to new domains and forgetting of generalized capabilities; (c) aggressive model compression and acceleration. To this end, we propose a novel loss that balances compression and acceleration of a deep learning model vs. loss of generalization capabilities. We apply our method to the existing tracker and detector models. We report detection results on the VIRAT and CAVIAR data sets. These results show our method to offer unprecedented compression rates along with improved detection. We apply our loss for tracker compression at test time, as it processes each video. Our tests on the OTB2015 benchmark show that applying compression during test time actually improves tracking performance.