MFASSL adds mirror-paired views, a lightweight Mirror-Fusion Attention module, and reflection-consistency losses to improve SSL on bilateral data with ~2.7% extra parameters.
Advances in neural information processing systems34, 15682–15694 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
MFASSL adds mirror-paired views, a lightweight Mirror-Fusion Attention module, and reflection-consistency losses to improve SSL on bilateral data with ~2.7% extra parameters.