A self-distillation training scheme for audio-visual embeddings progressively replaces labeled triplets with model-generated soft alignments, improving cross-modal retrieval MAP by roughly 2 percent on AVE and VEGAS.
Canonical correlation analysis: An overview with application to learning methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning
A self-distillation training scheme for audio-visual embeddings progressively replaces labeled triplets with model-generated soft alignments, improving cross-modal retrieval MAP by roughly 2 percent on AVE and VEGAS.