{"ID":5551711,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T12:15:27.216345251Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00850","arxiv_id":"2607.00850","title":"Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning","abstract":"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.","short_abstract":"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 Tr...","url_abs":"https://arxiv.org/abs/2607.00850","url_pdf":"https://arxiv.org/pdf/2607.00850v1","authors":"[\"Ruixin Li\",\"Jin Liu\",\"Yuling Shi\",\"Stefano Lodi\"]","published":"2026-07-01T12:16:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Vision Transformer\",\"Transformer\"]","has_code":false}