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

by   Mengya Xu, et al.

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.


page 1

page 2

page 6

page 7

page 12


Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation

Purpose: In curriculum learning, the idea is to train on easier samples ...

Confidence-Aware Calibration and Scoring Functions for Curriculum Learning

Despite the great success of state-of-the-art deep neural networks, seve...

Rethinking Curriculum Learning with Incremental Labels and Adaptive Compensation

Like humans, deep networks learn better when samples are organized and i...

HiCu: Leveraging Hierarchy for Curriculum Learning in Automated ICD Coding

There are several opportunities for automation in healthcare that can im...

Calibrating Histopathology Image Classifiers using Label Smoothing

The classification of histopathology images fundamentally differs from t...

Label-similarity Curriculum Learning

Curriculum learning can improve neural network training by guiding the o...

Temporal Label Smoothing for Early Prediction of Adverse Events

Models that can predict adverse events ahead of time with low false-alar...

Please sign up or login with your details

Forgot password? Click here to reset