CORTEXA
← Browse
arxivcs.CVcs.LG2026-07-01

Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning

Ruixin Li, Jin Liu, Yuling Shi, Stefano Lodi

Most self-supervised learning (SSL) methods encourage invariance across augmentations, but strict flip invariance can suppress informative left--right correspondences in approximately bilateral data such as medical images and human faces. We propose Mirror-Fusion-Augmented Self-Supervised Learning (MFASSL), a Vision Transformer framework that injects a soft reflection prior into standard SSL without redesigning the backbone. MFASSL constructs mirror-paired views aligned to an estimated symmetry axis and introduces a lightweight Mirror-Fusion Attention (MFA) module for adaptive token-level interaction between mirrored regions while preserving asymmetric cues. The base SSL objective is further coupled with reflection-consistency and mid-layer token-alignment losses. Across CheXpert, BraTS, CelebA-HQ, and WFLW, MFASSL improves downstream performance, calibration, and reflection robustness over MoCo-v3, DINO, and MAE baselines under matched ViT-B/16 settings. It also achieves stronger and more consistent gains than recent equivariant SSL approaches with only approximately 2.7\% additional parameters. These results show that lightweight geometry-aware priors can effectively complement invariance-based SSL.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CVeess.SP2026-07-13

DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations

Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri, Belkacem Chikhaoui, Khadidja Henni

Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less than 10\% of clinical recordings. We present DiffEEG, a 9.6M-parameter self-supervised foundation model that addresses…

View free PDFSource page
arxivcs.CVcs.LG2026-07-16

Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality

Kunal Pratap Singh, Ali Garjani, Rishubh Singh, Muhammad Uzair Khattak, Efe Tarhan, Jason Toskov, et al.

Cross-modal learning, i.e., learning to predict one modality from another, is a fundamental mechanism for self-supervision via leveraging multimodality. Many practical applications, e.g., deploying a household robot, involve devices that are equipped with a rich set of sensors th…

View free PDFSource page
arxivcs.CVcs.AIcs.CLcs.LG2026-07-22

Self-supervision drives representational convergence in medical foundation models more than clinical supervision

Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia, Lisa Adams, Sven Nebelung, Jakob Nikolas Kather, et al.

Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations onto a shared structure. Whether this convergence is real, what produces it, and whether it is clinica…

View free PDFSource page
arxivcs.CVcs.LG2026-07-11

TVT-PAPD: Pathology-Aware Prototype Distillation for Self-Supervised Whole Slide Image Classification

Ramesh Naidu Laveti, Jaya Sreevalsan-Nair, T K Srikanth

Self-supervised learning (SSL) has emerged as an effective paradigm for learning transferable representations from large-scale unlabeled whole slide images (WSIs). However, existing SSL methods primarily learn generic visual features and often fail to explicitly capture pathology…

View free PDFSource page