# SALAD: Self-Assessment Learning for Action Detection

arXiv: https://arxiv.org/abs/2011.06958 · HTML: https://mlsanity.com/paper/2011.06958/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2020.

## Built on by (most cited first, 2 of 2)

- [Temporal Action Localization Using Gated Recurrent Units](https://mlsanity.com/paper/2108.03375/) (2021)
- [Dilation-Erosion for Single-Frame Supervised Temporal Action Localization](https://mlsanity.com/paper/2212.06348/) (2022)

## Abstract (arXiv)

Literature on self-assessment in machine learning mainly focuses on the production of well-calibrated algorithms through consensus frameworks i.e. calibration is seen as a problem. Yet, we observe that learning to be properly confident could behave like a powerful regularization and thus, could be an opportunity to improve performance.Precisely, we show that used within a framework of action detection, the learning of a self-assessment score is able to improve the whole action localization process.Experimental results show that our approach outperforms the state-of-the-art on two action detection benchmarks. On THUMOS14 dataset, the mAP at tIoU@0.5 is improved from 42.8% to 44.6%, and from 50.4% to 51.7% on ActivityNet1.3 dataset. For lower tIoU values, we achieve even more significant improvements on both datasets.