Aggregative Self-Supervised Feature Learning from a Limited Sample
원문 초록
Self-supervised learning (SSL) is an efficient approach that addresses the issue of limited training data and annotation shortage. The key part in SSL is its proxy task that defines the supervisory signals and drives the learning toward effective feature representations. However, most SSL approaches usually focus on a single proxy task, which greatly limits the expressive power of the learned features and therefore deteriorates the network generalization capacity. In this regard, we hereby propose two strategies of aggregation in terms of complementarity of various forms to boost the robustness of self-supervised learned features. We firstly propose a principled framework of multi-task aggregative self-supervised learning from a limited sample to form a unified representation, with an intent of exploiting feature complementarity among different tasks. Then, in self-aggregative SSL, we propose to self-complement an existing proxy task with an auxiliary loss function based on a linear centered kernel alignment metric, which explicitly promotes the exploring of where are uncovered by the features learned from a proxy task at hand to further boost the modeling capability. Our extensive experiments on 2D natural image and 3D medical image classification tasks under limited data and annotation scenarios confirm that the proposed aggregation strategies successfully boost the classification accuracy.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Deep Modeling and Optimization of Medical Image Classification
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
Robust Training with Data Augmentation for Medical Imaging Classification
Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach
Detecção da Psoríase Utilizando Visão Computacional: Uma Abordagem Comparativa Entre CNNs e Vision Transformers
Recent Advances in Medical Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.