Imperial College London
Portrait Picture

Dr Ben Glocker

Faculty of Engineering, Department of Computing

Professor in Machine Learning for Imaging
 
 
 
//

Contact

 

+44 (0)20 7594 8334b.glocker Website CV

 
 
//

Location

 

377Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Xu:2022,
author = {Xu, M and Islam, M and Glocker, B and Ren, H},
title = {Confidence-Aware Paced-Curriculum Learning by Label Smoothing for  Surgical Scene Understanding},
url = {http://arxiv.org/abs/2212.11511v1},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - Curriculum learning and self-paced learning are the training strategies thatgradually feed the samples from easy to more complex. They have captivatedincreasing attention due to their excellent performance in robotic vision. Mostrecent works focus on designing curricula based on difficulty levels in inputsamples or smoothing the feature maps. However, smoothing labels to control thelearning utility in a curriculum manner is still unexplored. In this work, wedesign a paced curriculum by label smoothing (P-CBLS) using paced learning withuniform label smoothing (ULS) for classification tasks and fuse uniform andspatially varying label smoothing (SVLS) for semantic segmentation tasks in acurriculum manner. In ULS and SVLS, a bigger smoothing factor value enforces aheavy smoothing penalty in the true label and limits learning less information.Therefore, we design the curriculum by label smoothing (CBLS). We set a biggersmoothing value at the beginning of training and gradually decreased it to zeroto control the model learning utility from lower to higher. We also designed aconfidence-aware pacing function and combined it with our CBLS to investigatethe benefits of various curricula. The proposed techniques are validated onfour robotic surgery datasets of multi-class, multi-label classification,captioning, and segmentation tasks. We also investigate the robustness of ourmethod by corrupting validation data into different severity levels. Ourextensive analysis shows that the proposed method improves prediction accuracyand robustness.
AU  - Xu,M
AU  - Islam,M
AU  - Glocker,B
AU  - Ren,H
PY  - 2022///
TI  - Confidence-Aware Paced-Curriculum Learning by Label Smoothing for  Surgical Scene Understanding
UR  - http://arxiv.org/abs/2212.11511v1
ER  -
Download