List your company

Acoustic Scene Classification on TUT 2017

83.14AccuracyPALM + ASPL*
2.810423.665244.5265.3748Apr 14, 2025Jun 24, 2025Sep 3, 2025Nov 13, 2025Jan 23, 2026Apr 4, 2026Jun 14, 2026

Evaluation results

MethodLinks
PALM + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0683.14
PALM + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0682.51
PALMShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0679.8
CoCoOp + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0678.76
CoCoOp + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0678.68
CoCoOpShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0675.84
CoOp + ASPLShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0674.9
CoOp + ASPL*Shots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0674.38
Full ModelBackbone=VideoLLaMA2, Sparsity=0%2025.0471.2
CoOpShots=16, Audio Encoder=CLAP-HTSAT, Text Encoder=CLIP (PENGI)2026.0668.2
ShortGPTBackbone=VideoLLaMA2, Sparsity=25%2025.0442.3
DASBackbone=VideoLLaMA2, Sparsity=25%2025.0433.5
OWLBackbone=VideoLLaMA2, Sparsity=25%2025.0422.5
Shortened LLaMABackbone=VideoLLaMA2, Sparsity=25%2025.0412.4
ECOFLaPBackbone=VideoLLaMA2, Sparsity=25%2025.045.9