ConvMixer

Reported on 4 benchmarks across 3 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech2 results

Keyword SpottingonGoogle Speech Commands
Google Speech Commands V1 12
97.3
best: 98.56 (TripletLoss-res15)
Keyword SpottingonGoogle Speech Commands
Google Speech Commands V2 12
98.2
best: 98.8 (WaveFormer)

Medical2 results

Medical Image SegmentationonDRIVE
F1 score
0.8245
best: 0.8322 (FSG-Net)
Retinal Vessel SegmentationonDRIVE
F1 score
0.8245
best: 0.8322 (FSG-Net)