UCL Discovery Stage
UCL home » Library Services » Electronic resources » UCL Discovery Stage

Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding

Xu, Mengya; Islam, Mobarakol; Glocker, Ben; Ren, Hongliang; (2023) Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding. IEEE Transactions on Automation Science and Engineering pp. 1-12. 10.1109/tase.2023.3276361. (In press). Green open access

[thumbnail of Confidence-Aware_Paced-Curriculum_Learning_by_Label_Smoothing_for_Surgical_Scene_Understanding.pdf]
Preview
PDF
Confidence-Aware_Paced-Curriculum_Learning_by_Label_Smoothing_for_Surgical_Scene_Understanding.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic vision. Most recent works focus on designing curricula based on difficulty levels in input samples or smoothing the feature maps. However, smoothing labels to control the learning utility in a curriculum manner is still unexplored. In this work, we design a paced curriculum by label smoothing (P-CBLS) using paced learning with uniform label smoothing (ULS) for classification tasks and fuse uniform and spatially varying label smoothing (SVLS) for semantic segmentation tasks in a curriculum manner. In ULS and SVLS, a bigger smoothing factor value enforces a heavy smoothing penalty in the true label and limits learning less information. Therefore, we design the curriculum by label smoothing (CBLS). We set a bigger smoothing value at the beginning of training and gradually decreased it to zero to control the model learning utility from lower to higher. We also designed a confidence-aware pacing function and combined it with our CBLS to investigate the benefits of various curricula. The proposed techniques are validated on four robotic surgery datasets of multi-class, multi-label classification, captioning, and segmentation tasks. We also investigate the robustness of our method by corrupting validation data into different severity levels. Our extensive analysis shows that the proposed method improves prediction accuracy and robustness. The code is publicly available at https://github.com/XuMengyaAmy/P-CBLS. Note to Practitioners —The motivation of this article is to improve the performance and robustness of deep neural networks in safety-critical applications such as robotic surgery by controlling the learning ability of the model in a curriculum learning manner and allowing the model to imitate the cognitive process of humans and animals. The designed approaches do not add parameters that require additional computational resources.

Type: Article
Title: Confidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tase.2023.3276361
Publisher version: https://doi.org/10.1109/TASE.2023.3276361
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Surgical scene understanding, computer vision for medical robotics, deep learning methods, medical robots
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery-pp.ucl.ac.uk/id/eprint/10171337
Downloads since deposit
1,050Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item