|国家预印本平台
首页|SCoRe: Submodular Combinatorial Representation Learning

SCoRe: Submodular Combinatorial Representation Learning

SCoRe: Submodular Combinatorial Representation Learning

来源:Arxiv_logoArxiv
英文摘要

In this paper we introduce the SCoRe (Submodular Combinatorial Representation Learning) framework, a novel approach in representation learning that addresses inter-class bias and intra-class variance. SCoRe provides a new combinatorial viewpoint to representation learning, by introducing a family of loss functions based on set-based submodular information measures. We develop two novel combinatorial formulations for loss functions, using the Total Information and Total Correlation, that naturally minimize intra-class variance and inter-class bias. Several commonly used metric/contrastive learning loss functions like supervised contrastive loss, orthogonal projection loss, and N-pairs loss, are all instances of SCoRe, thereby underlining the versatility and applicability of SCoRe in a broad spectrum of learning scenarios. Novel objectives in SCoRe naturally model class-imbalance with up to 7.6\% improvement in classification on CIFAR-10-LT, CIFAR-100-LT, MedMNIST, 2.1% on ImageNet-LT, and 19.4% in object detection on IDD and LVIS (v1.0), demonstrating its effectiveness over existing approaches.

Anay Majee、Rishabh Iyer、Krishnateja Killamsetty、Suraj Kothawade

计算技术、计算机技术

Anay Majee,Rishabh Iyer,Krishnateja Killamsetty,Suraj Kothawade.SCoRe: Submodular Combinatorial Representation Learning[EB/OL].(2023-09-29)[2025-08-02].https://arxiv.org/abs/2310.00165.点此复制

评论