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.
Anchor-aware deep metric learning for audio-visual retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 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.