paper-with-me

Papers

Self-supervised Representation Learning From Random Data Projectors

2023-10-11 · Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs

Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. While augmentation-based SSRL algorithms push the boundaries of performance in computer vision and natural language processing, they are often not directly applicable to other data modalities, and can conflict with application-specific data augmentation constraints. This paper presents an SSRL approach that can be applied to any data modality and network architecture because it does not rely on augmentations or masking. Specifically, we show that high-quality data representations can be learned by reconstructing random data projections. We evaluate the proposed approach on a wide range of representation learning tasks that span diverse modalities and real-world applications. We show that it outperforms multiple state-of-the-art SSRL baselines. Due to its wide applicability and strong empirical results, we argue that learning from randomness is a fruitful research direction worthy of attention and further study.

📄 PDF Abstract BibTeX arXiv:2310.07756

Code (1)

layer6ai-labs/lfr 공식 구현 pytorch

Tasks

Data AugmentationRepresentation Learning

Similar Papers 제목 키워드 기반

Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus

2026-04-20 · Esteban Rodríguez-Betancourt, Edgar Casasola-Murillo arxiv

In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even displaying emergent properties. However, state-of-the-art methods usual…

Self-Supervised Learning

Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning

2021-10-11 · Chongjian Ge, Youwei Liang, Yibing Song, Jianbo Jiao 외

Studies on self-supervised visual representation learning (SSL) improve encoder backbones to discriminate training samples without labels. While CNN encoders via SSL achieve comparable recognition performance to those vi…

image-classificationImage Classificationobject-detectionObject Detection+2

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

2021-12-01 · NeurIPS 2021 12 · Chongjian Ge, Youwei Liang, Yibing Song, Jianbo Jiao 외

Studies on self-supervised visual representation learning (SSL) improve encoder backbones to discriminate training samples without labels. While CNN encoders via SSL achieve comparable recognition performance to those vi…

image-classificationImage Classificationobject-detectionObject Detection+2

Capsule Network Projectors are Equivariant and Invariant Learners

2024-05-23 · Miles Everett, Aiden Durrant, Mingjun Zhong, Georgios Leontidis

Learning invariant representations has been the longstanding approach to self-supervised learning. However, recently progress has been made in preserving equivariant properties in representations, yet do so with highly p…

Self-Supervised Learning

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations

2022-09-29 · Grégoire Mialon, Randall Balestriero, Yann Lecun

Self-Supervised Learning (SSL) methods such as VICReg, Barlow Twins or W-MSE avoid collapse of their joint embedding architectures by constraining or regularizing the covariance matrix of their projector's output. This s…

Domain GeneralizationSelf-Supervised Learning