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

TL;DR

This paper introduces a novel curriculum learning approach using label smoothing with a confidence-aware pacing function, improving accuracy and robustness in robotic surgery scene understanding tasks.

Contribution

It proposes a new paced curriculum learning method with label smoothing for classification and segmentation, incorporating confidence-aware pacing to enhance training effectiveness.

Findings

Improves prediction accuracy across multiple surgical datasets.

Enhances robustness against data corruption and varying severity levels.

Demonstrates effectiveness in classification and segmentation tasks.

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.