Mixed-order self-paced curriculum learning for universal lesion detection

• URL: http://arxiv.org/abs/2302.04677v1
• Date: Thu, 9 Feb 2023 14:52:44 GMT
• Title: Mixed-order self-paced curriculum learning for universal lesion detection
• Authors: Han Li, Hu Han, and S. Kevin Zhou
• Abstract summary: Self-paced curriculum learning (SCL) has demonstrated its great potential in computer vision, natural language processing, etc. It implements easy-to-hard sampling based on online estimation of data difficulty. Most SCL methods adopt a loss-based strategy of estimating data difficulty and deweighting the hard' samples in the early training stage.
• Score: 36.198165949330566
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-paced curriculum learning (SCL) has demonstrated its great potential in computer vision, natural language processing, etc. During training, it implements easy-to-hard sampling based on online estimation of data difficulty. Most SCL methods commonly adopt a loss-based strategy of estimating data difficulty and deweighting the `hard' samples in the early training stage. While achieving success in a variety of applications, SCL stills confront two challenges in a medical image analysis task, such as universal lesion detection, featuring insufficient and highly class-imbalanced data: (i) the loss-based difficulty measurer is inaccurate; ii) the hard samples are under-utilized from a deweighting mechanism. To overcome these challenges, in this paper we propose a novel mixed-order self-paced curriculum learning (Mo-SCL) method. We integrate both uncertainty and loss to better estimate difficulty online and mix both hard and easy samples in the same mini-batch to appropriately alleviate the problem of under-utilization of hard samples. We provide a theoretical investigation of our method in the context of stochastic gradient descent optimization and extensive experiments based on the DeepLesion benchmark dataset for universal lesion detection (ULD). When applied to two state-of-the-art ULD methods, the proposed mixed-order SCL method can provide a free boost to lesion detection accuracy without extra special network designs.

Related papers

• A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty [12.382999548648726]
  Existing studies assume a uniform unlearning difficulty across samples. We propose a Memory Removal Difficulty ($mathrmMRD$) metric to quantify sample-level unlearning difficulty. We also propose an $mathrmMRD$-based weighted sampling method to optimize existing unlearning algorithms.
  arXiv  Detail & Related papers  (2025-04-09T07:48:10Z)
• SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples [54.760757107700755]
  Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. The class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation. We propose a method that enhances the performance of Imbalanced Semi-Supervised Learning by Mining Hard Examples (SeMi)
  arXiv  Detail & Related papers  (2025-01-10T14:35:16Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• SPLAL: Similarity-based pseudo-labeling with alignment loss for semi-supervised medical image classification [11.435826510575879]
  Semi-supervised learning (SSL) methods can mitigate challenges by leveraging both labeled and unlabeled data. SSL methods for medical image classification need to address two key challenges: (1) estimating reliable pseudo-labels for the images in the unlabeled dataset and (2) reducing biases caused by class imbalance. In this paper, we propose a novel SSL approach, SPLAL, that effectively addresses these challenges.
  arXiv  Detail & Related papers  (2023-07-10T14:53:24Z)
• Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time [66.08455276899578]
  We show that informative sampling can prohibit accurate estimation of treatment outcomes if not properly accounted for. We present a general framework for learning treatment outcomes in the presence of informative sampling using inverse intensity-weighting. We propose a novel method, TESAR-CDE, that instantiates this framework using Neural CDEs.
  arXiv  Detail & Related papers  (2023-06-07T08:51:06Z)
• Robust Semi-Supervised Learning for Histopathology Images through Self-Supervision Guided Out-of-Distribution Scoring [1.8558180119033003]
  We propose a novel pipeline for addressing open-set supervised learning challenges in digital histology images. Our pipeline efficiently estimates an OOD score for each unlabelled data point based on self-supervised learning. Our framework is compatible with any semi-SL framework, and we base our experiments on the popular Mixmatch semi-SL framework.
  arXiv  Detail & Related papers  (2023-03-17T12:38:28Z)
• An interpretable machine learning system for colorectal cancer diagnosis from pathology slides [2.7968867060319735]
  This study is conducted with one of the largest WSI colorectal samples dataset with approximately 10,500 WSIs. Our proposed method predicts, for the patch-based tiles, a class based on the severity of the dysplasia. It is trained with an interpretable mixed-supervision scheme to leverage the domain knowledge introduced by pathologists.
  arXiv  Detail & Related papers  (2023-01-06T17:10:32Z)
• Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection [81.07346419422605]
  Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. We propose a novel hierarchical semi-supervised contrastive learning framework, for contamination-resistant anomaly detection.
  arXiv  Detail & Related papers  (2022-07-24T18:49:26Z)
• Competence-based Multimodal Curriculum Learning for Medical Report Generation [98.10763792453925]
  We propose a Competence-based Multimodal Curriculum Learning framework ( CMCL) to alleviate the data bias and make best use of available data. Specifically, CMCL simulates the learning process of radiologists and optimize the model in a step by step manner. Experiments on the public IU-Xray and MIMIC-CXR datasets show that CMCL can be incorporated into existing models to improve their performance.
  arXiv  Detail & Related papers  (2022-06-24T08:16:01Z)
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning [55.733193075728096]
  Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
  arXiv  Detail & Related papers  (2022-02-11T13:49:51Z)
• A multi-stage semi-supervised improved deep embedded clustering (MS-SSIDEC) method for bearing fault diagnosis under the situation of insufficient labeled samples [20.952315351460527]
  It costs a lot of labor and time to label data in actual industrial processes, which challenges the application of intelligent fault diagnosis methods. To solve this problem, a multi-stage semi-supervised improved deep embedded clustering (MS-SSIDEC) method is proposed. This method includes three stages: pre-training, deep clustering and enhanced supervised learning.
  arXiv  Detail & Related papers  (2021-09-28T06:49:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.