List your company

Sound Event Classification on ESC50 Actions

98.25Top-1 AccuracyPALM
94.786895.685996.58597.4841Jun 14, 2026

Evaluation results

MethodLinks
PALMShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0698.25
PALM + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0698
CoCoOp + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0697.83
CoCoOpShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0697.75
PALM + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0697.75
CoCoOp + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0697.42
CoOp + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0696.25
CoOp + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0695.5
CoOpShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0694.92