Human not in the loop: objective sample difficulty measures for
Curriculum Learning
- URL: http://arxiv.org/abs/2302.01243v1
- Date: Thu, 2 Feb 2023 17:25:29 GMT
- Title: Human not in the loop: objective sample difficulty measures for
Curriculum Learning
- Authors: Zhengbo Zhou, Jun Luo, Gene Kitamura, Shandong Wu
- Abstract summary: We propose a new automated curriculum learning technique using the variance of gradients (VoG) to compute an objective difficulty measure of samples.
Specifically, we used VoG as a metric to rank each sample in terms of the classification difficulty, where high VoG scores indicate more difficult cases for classification.
Our experiment results showed comparable and higher performance for the binary and multi-class bone fracture classification tasks.
- Score: 5.203119819023793
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Curriculum learning is a learning method that trains models in a meaningful
order from easier to harder samples. A key here is to devise automatic and
objective difficulty measures of samples. In the medical domain, previous work
applied domain knowledge from human experts to qualitatively assess
classification difficulty of medical images to guide curriculum learning, which
requires extra annotation efforts, relies on subjective human experience, and
may introduce bias. In this work, we propose a new automated curriculum
learning technique using the variance of gradients (VoG) to compute an
objective difficulty measure of samples and evaluated its effects on elbow
fracture classification from X-ray images. Specifically, we used VoG as a
metric to rank each sample in terms of the classification difficulty, where
high VoG scores indicate more difficult cases for classification, to guide the
curriculum training process We compared the proposed technique to a baseline
(without curriculum learning), a previous method that used human annotations on
classification difficulty, and anti-curriculum learning. Our experiment results
showed comparable and higher performance for the binary and multi-class bone
fracture classification tasks.
Related papers
- Preview-based Category Contrastive Learning for Knowledge Distillation [53.551002781828146]
We propose a novel preview-based category contrastive learning method for knowledge distillation (PCKD)
It first distills the structural knowledge of both instance-level feature correspondence and the relation between instance features and category centers.
It can explicitly optimize the category representation and explore the distinct correlation between representations of instances and categories.
arXiv Detail & Related papers (2024-10-18T03:31:00Z) - DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated
MR Images [2.352695945685781]
We propose a new method that employs transfer learning techniques to correct sampling selection errors introduced by sparse annotations during supervised learning for automated tumor segmentation.
The proposed method derives high-quality classifiers for the different tissue classes from sparse and unambiguous annotations.
Compared to training on fully labeled data, we reduced the time for labeling and training by a factor greater than 70 and 180 respectively without sacrificing accuracy.
arXiv Detail & Related papers (2024-03-12T09:17:21Z) - Multi-task Explainable Skin Lesion Classification [54.76511683427566]
We propose a few-shot-based approach for skin lesions that generalizes well with few labelled data.
The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network.
arXiv Detail & Related papers (2023-10-11T05:49:47Z) - Learning Discriminative Representation via Metric Learning for
Imbalanced Medical Image Classification [52.94051907952536]
We propose embedding metric learning into the first stage of the two-stage framework specially to help the feature extractor learn to extract more discriminative feature representations.
Experiments mainly on three medical image datasets show that the proposed approach consistently outperforms existing onestage and two-stage approaches.
arXiv Detail & Related papers (2022-07-14T14:57:01Z) - Medical Knowledge-Guided Deep Learning for Imbalanced Medical Image
Classification [3.9745217005532183]
We propose a medical-knowledge-guided one-class classification approach to boost the model's performance.
We design a deep learning-based one-class classification pipeline for imbalanced image classification.
We show superior model performance when compared to six state-of-the-art methods.
arXiv Detail & Related papers (2021-11-20T16:14:19Z) - Curriculum Learning: A Survey [65.31516318260759]
Curriculum learning strategies have been successfully employed in all areas of machine learning.
We construct a taxonomy of curriculum learning approaches by hand, considering various classification criteria.
We build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm.
arXiv Detail & Related papers (2021-01-25T20:08:32Z) - Learn like a Pathologist: Curriculum Learning by Annotator Agreement for
Histopathology Image Classification [29.49041112835749]
We propose a curriculum learning method that trains on progressively-harder images as determined by annotator agreement.
We evaluate our hypothesis on the challenging and clinically-important task of colorectal polyp classification.
arXiv Detail & Related papers (2020-09-29T00:25:21Z) - Semi-supervised Medical Image Classification with Relation-driven
Self-ensembling Model [71.80319052891817]
We present a relation-driven semi-supervised framework for medical image classification.
It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations.
Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
arXiv Detail & Related papers (2020-05-15T06:57:54Z) - Melanoma Detection using Adversarial Training and Deep Transfer Learning [6.22964000148682]
We propose a two-stage framework for automatic classification of skin lesion images.
In the first stage, we leverage the inter-class variation of the data distribution for the task of conditional image synthesis.
In the second stage, we train a deep convolutional neural network for skin lesion classification.
arXiv Detail & Related papers (2020-04-14T22:46:20Z) - Medical-based Deep Curriculum Learning for Improved Fracture
Classification [36.54112505898611]
We propose and compare several strategies relying on curriculum learning, to support the classification of proximal femur fracture from X-ray images.
Our strategies are derived from knowledge such as medical decision trees and inconsistencies in the annotations of multiple experts.
Our results show that, compared to class-uniform and random strategies, the proposed medical knowledge-based curriculum, performs up to 15% better in terms of accuracy.
arXiv Detail & Related papers (2020-04-01T14:56:43Z) - CurricularFace: Adaptive Curriculum Learning Loss for Deep Face
Recognition [79.92240030758575]
We propose a novel Adaptive Curriculum Learning loss (CurricularFace) that embeds the idea of curriculum learning into the loss function.
Our CurricularFace adaptively adjusts the relative importance of easy and hard samples during different training stages.
arXiv Detail & Related papers (2020-04-01T08:43:10Z)
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.