paper-with-me

홈 › Papers

SMI: Efficient Self-Supervised Learning via Mutual-Information-Inspired Dependency Optimization

2026-06-06 · Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas arxiv

Self-supervised learning (SSL) has achieved remarkable representation learning performance, but many existing methods rely on large batch sizes, memory banks, momentum encoders, or global synchronization mechanisms that substantially increase computational cost and training complexity. In this work, we propose Semantic Mutual Information (SMI), a lightweight self-supervised objective derived from a mutual-information-inspired dependency formulation under Gaussian assumptions. Unlike conventional correlation matching objectives that operate on high-dimensional feature correlation matrices, SMI performs optimization on a sample-level dependency matrix through a nonlinear transformation of pairwise correlations. This formulation induces distinct optimization dynamics that emphasize strongly dependent semantic pairs while maintaining representation diversity. Experimental results on ImageNet using a ResNet-50 backbone demonstrate that SMI achieves competitive linear evaluation performance relative to state-of-the-art SSL approaches while substantially reducing computational complexity. Across multiple low-resource benchmarks, SMI consistently improves transfer performance over Barlow Twins, particularly on fine-grained datasets. Furthermore, analyses of optimization dynamics and representation geometry suggest improved alignment--redundancy balance, greater feature diversity, and more spatially localized semantic representations. These results indicate that nonlinear dependency optimization provides an effective and computationally efficient alternative to conventional correlation-based self-supervised learning objectives.

📄 PDF Abstract BibTeX arXiv:2606.08332

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised LearningRepresentation Learning

Similar Papers 제목 키워드 기반

Unsupervised Dependency Graph Network

2022-05-01 · ACL 2022 5 · Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li 외

Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspire…

Dependency ParsingLanguage ModelingLanguage ModellingMasked Language Modeling+3

Unsupervised Dependency Graph Network

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recent work has identified properties of pretrained self-attention models that mirror those of dependency parse structures. In particular, some self-attention heads correspond well to individual dependency types. Inspire…

Dependency ParsingLanguage ModelingLanguage ModellingMasked Language Modeling+3

TVDIM: Enhancing Image Self-Supervised Pretraining via Noisy Text Data

2021-06-03 · Pengda Qin, Yuhong Li, Kefeng Deng, Qiang Wu

Among ubiquitous multimodal data in the real world, text is the modality generated by human, while image reflects the physical world honestly. In a visual understanding application, machines are expected to understand im…

Contrastive Learningimage-classificationImage ClassificationSelf-Supervised Learning

Feature-Suppressed Contrast for Self-Supervised Food Pre-training

2023-08-07 · Xinda Liu, Yaohui Zhu, Linhu Liu, Jiang Tian 외

Most previous approaches for analyzing food images have relied on extensively annotated datasets, resulting in significant human labeling expenses due to the varied and intricate nature of such images. Inspired by the ef…

Food RecognitionSelf-Supervised Learning

Neural Methods for Point-wise Dependency Estimation

2020-06-09 · NeurIPS 2020 12 · Yao-Hung Hubert Tsai, Han Zhao, Makoto Yamada, Louis-Philippe Morency 외

Since its inception, the neural estimation of mutual information (MI) has demonstrated the empirical success of modeling expected dependency between high-dimensional random variables. However, MI is an aggregate statisti…

Cross-Modal RetrievalRepresentation LearningRetrieval