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

arXiv:2607.00850 · cs.CV, cs.LG · Submitted 2026-07-01 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-07-01

Updated: 2026-07-01

Comments: Accepted at ECML PKDD 2026. The final authenticated version will be available in the Springer LNCS proceedings

Journal ref: Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2026, LNCS 16945, pp. 629-647, Springer, 2027

DOI: 10.1007/978-3-032-37670-1_36

Code: https://github.com/Lirxstar/MFASSL

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 26× in this paper · explained in 3 episodes
• Self-Supervised Learning — 18× in this paper · explained in 7 episodes
• Calibration — 17× in this paper · explained in 7 episodes
• Transformer — 17× in this paper · explained in 2 episodes
• Alignment — 12× in this paper · explained in 1 episode
• Representation Learning — 9× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Mirror-Fusion Attention — 7× in this paper
• Benchmark — 6× in this paper · explained in 2 episodes
• AUC — 5× in this paper · explained in 2 episodes
• Core — 5× in this paper · explained in 2 episodes
• Distillation — 4× in this paper · explained in 2 episodes
• Mirror-Fusion-Augmented Self-Supervised Learning — 4× in this paper
• Robustness — 4× in this paper · explained in 5 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Contrastive Learning — 3× in this paper · explained in 5 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Self-Supervised Learning (SSL) — 3× in this paper · explained in 4 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Foundation Models — 2× in this paper · explained in 7 episodes
• nnU-Net — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes

Sources

• BEiT: BERT Pre-Training of Image Transformers
• Steerable CNNs
• Equivariant Contrastive Learning
• Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
• Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
• FitNets: Hints for Thin Deep Nets
• Group Equivariant Stand-Alone Self-Attention For Vision
• iBOT: Image BERT Pre-Training with Online Tokenizer

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models