EndoCIL: A Class-Incremental Learning Framework for Endoscopic Image Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Bingrong, Shi, Jun, Zheng, Yushan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909857466023936
author Liu, Bingrong
Shi, Jun
Zheng, Yushan
author_facet Liu, Bingrong
Shi, Jun
Zheng, Yushan
contents Class-incremental learning (CIL) for endoscopic image analysis is crucial for real-world clinical applications, where diagnostic models should continuously adapt to evolving clinical data while retaining performance on previously learned ones. However, existing replay-based CIL methods fail to effectively mitigate catastrophic forgetting due to severe domain discrepancies and class imbalance inherent in endoscopic imaging. To tackle these challenges, we propose EndoCIL, a novel and unified CIL framework specifically tailored for endoscopic image diagnosis. EndoCIL incorporates three key components: Maximum Mean Discrepancy Based Replay (MDBR), employing a distribution-aligned greedy strategy to select diverse and representative exemplars, Prior Regularized Class Balanced Loss (PRCBL), designed to alleviate both inter-phase and intra-phase class imbalance by integrating prior class distributions and balance weights into the loss function, and Calibration of Fully-Connected Gradients (CFG), which adjusts the classifier gradients to mitigate bias toward new classes. Extensive experiments conducted on four public endoscopic datasets demonstrate that EndoCIL generally outperforms state-of-the-art CIL methods across varying buffer sizes and evaluation metrics. The proposed framework effectively balances stability and plasticity in lifelong endoscopic diagnosis, showing promising potential for clinical scalability and deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EndoCIL: A Class-Incremental Learning Framework for Endoscopic Image Classification
Liu, Bingrong
Shi, Jun
Zheng, Yushan
Computer Vision and Pattern Recognition
Class-incremental learning (CIL) for endoscopic image analysis is crucial for real-world clinical applications, where diagnostic models should continuously adapt to evolving clinical data while retaining performance on previously learned ones. However, existing replay-based CIL methods fail to effectively mitigate catastrophic forgetting due to severe domain discrepancies and class imbalance inherent in endoscopic imaging. To tackle these challenges, we propose EndoCIL, a novel and unified CIL framework specifically tailored for endoscopic image diagnosis. EndoCIL incorporates three key components: Maximum Mean Discrepancy Based Replay (MDBR), employing a distribution-aligned greedy strategy to select diverse and representative exemplars, Prior Regularized Class Balanced Loss (PRCBL), designed to alleviate both inter-phase and intra-phase class imbalance by integrating prior class distributions and balance weights into the loss function, and Calibration of Fully-Connected Gradients (CFG), which adjusts the classifier gradients to mitigate bias toward new classes. Extensive experiments conducted on four public endoscopic datasets demonstrate that EndoCIL generally outperforms state-of-the-art CIL methods across varying buffer sizes and evaluation metrics. The proposed framework effectively balances stability and plasticity in lifelong endoscopic diagnosis, showing promising potential for clinical scalability and deployment.
title EndoCIL: A Class-Incremental Learning Framework for Endoscopic Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.17200