# Knowledge distillation with a class-aware loss for endoscopic disease detection

arXiv: https://arxiv.org/abs/2207.09530 · HTML: https://mlsanity.com/paper/2207.09530/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 19 Jul 2022.

## Builds on (most cited first, 8 of 8)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Automatic Colon Polyp Detection using Region based Deep CNN and Post Learning Approaches](https://mlsanity.com/paper/1906.11463/) (2019)
- [Endoscopy disease detection challenge 2020](https://mlsanity.com/paper/2003.03376/) (2020)
- [AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy](https://mlsanity.com/paper/1909.02477/) (2019)
- [Augmenting Knowledge Distillation With Peer-To-Peer Mutual Learning For Model Compression](https://mlsanity.com/paper/2110.11023/) (2021)

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

- [Learning Through Guidance: Knowledge Distillation for Endoscopic Image Classification](https://mlsanity.com/paper/2308.08731/) (2023)

## Abstract (arXiv)

Prevalence of gastrointestinal (GI) cancer is growing alarmingly every year leading to a substantial increase in the mortality rate. Endoscopic detection is providing crucial diagnostic support, however, subtle lesions in upper and lower GI are quite hard to detect and cause considerable missed detection. In this work, we leverage deep learning to develop a framework to improve the localization of difficult to detect lesions and minimize the missed detection rate. We propose an end to end student-teacher learning setup where class probabilities of a trained teacher model on one class with larger dataset are used to penalize multi-class student network. Our model achieves higher performance in terms of mean average precision (mAP) on both endoscopic disease detection (EDD2020) challenge and Kvasir-SEG datasets. Additionally, we show that using such learning paradigm, our model is generalizable to unseen test set giving higher APs for clinically crucial neoplastic and polyp categories