Image Classification on ImageNet Mini
82.44Top-1 AccuracyCLUENet (base)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CLUENet (base)#Param=30.20, FLOPs=6.40, FPS=679.05±7.12, Memory=7.7, Type=Clustering-based2025.12 | 82.44 | 92.47 | |
| CLUENet (small)#Param=15.05, FLOPs=3.16, FPS=878.60±21.68, Memory=6.5, Type=Clustering-based2025.12 | 81.49 | 92.06 | |
| CLUENet (tiny)#Param=5.68, FLOPs=1.30, FPS=867.76±17.89, Memory=5.5, Type=Clustering-based2025.12 | 80.51 | 91.29 | |
| EfficientFormer (s2)#Param=12.16, FLOPs=1.27, FPS=695.41±1.71, Memory=1.5, Type=Attention-based2025.12 | 79.75 | 90.42 | |
| ShuffleNetv2 (x2.0)#Param=6.52, FLOPs=0.64, FPS=1205.17±7.59, Memory=1.3, Type=Convolution-based2025.12 | 79.63 | 90.93 | |
| FEC (large)#Param=29.26, FLOPs=6.55, FPS=550.69±2.58, Memory=7.6, Type=Clustering-based2025.12 | 79.33 | 90.55 | |
| EfficientFormer (s1)#Param=5.76, FLOPs=0.66, FPS=1128.59±0.75, Memory=1.5, Type=Attention-based2025.12 | 78.97 | 90.32 | |
| CLUENet (micro)#Param=3.02, FLOPs=0.65, FPS=871.89±13.84, Memory=4.2, Type=Clustering-based2025.12 | 78.75 | 90.83 | |
| ShuffleNetv2 (x1.5)#Param=2.58, FLOPs=0.31, FPS=1194.72±23.26, Memory=1.1, Type=Convolution-based2025.12 | 78.39 | 90.4 | |
| CoC (medium)#Param=28.83, FLOPs=5.96, FPS=605.67±3.18, Memory=4.2, Type=Clustering-based2025.12 | 78.39 | 90.29 | |
| EfficientFormer (s0)#Param=3.26, FLOPs=0.40, FPS=1166.09±21.46, Memory=1.5, Type=Attention-based2025.12 | 77.92 | 89.71 | |
| FEC (base)#Param=14.63, FLOPs=3.37, FPS=859.63±16.23, Memory=5.3, Type=Clustering-based2025.12 | 77.81 | 90.26 | |
| PVTv2 (b1)#Param=13.55, FLOPs=2.06, FPS=1154.58±39.86, Memory=2.9, Type=Attention-based2025.12 | 77.57 | 89.86 | |
| ResNet18#Param=14.17, FLOPs=2.38, FPS=1150.75±27.15, Memory=2.7, Type=Convolution-based2025.12 | 76.95 | 89.88 | |
| FEC (small)#Param=5.44, FLOPs=1.38, FPS=854.25±37.49, Memory=5.2, Type=Clustering-based2025.12 | 76.74 | 89.34 | |
| CoC (small)#Param=14.20, FLOPs=2.80, FPS=883.46±29.31, Memory=3.2, Type=Clustering-based2025.12 | 76.56 | 89.13 | |
| PVTv2 (b0)#Param=3.44, FLOPs=0.54, FPS=1195.32±31.63, Memory=1.7, Type=Attention-based2025.12 | 75.34 | 88.52 | |
| EfficientViT (m5)#Param=12.13, FLOPs=0.52, FPS=1160.99±44.32, Memory=1.0, Type=Attention-based2025.12 | 75.32 | 88.03 | |
| ConvNeXtv2 (N)#Param=15.05, FLOPs=2.46, FPS=1148.19±28.45, Memory=2.8, Type=Convolution-based2025.12 | 75.04 | 87.48 | |
| CoC (tiny)#Param=5.28, FLOPs=1.12, FPS=887.11±18.92, Memory=2.2, Type=Clustering-based2025.12 | 74.9 | 88.29 | |
| ClusterFormer (tiny)#Param=30.27, FLOPs=5.58, FPS=588.56±5.11, Memory=9.6, Type=Clustering-based2025.12 | 73.99 | 88.26 | |
| ClusterFormer#Param=15.01, FLOPs=3.02, FPS=694.91±5.99, Memory=12.0, Adjusted=true, Type=Clustering-based2025.12 | 73.93 | 87.29 | |
| EfficientViT (m3)#Param=6.61, FLOPs=0.26, FPS=1132.69±24.25, Memory=1.0, Type=Attention-based2025.12 | 73.88 | 87.16 | |
| EfficientViT (m2)#Param=3.99, FLOPs=0.20, FPS=1173.13±22.48, Memory=0.9, Type=Attention-based2025.12 | 73.59 | 86.78 | |
| ConvNeXtv2 (F)#Param=4.89, FLOPs=0.79, FPS=1177.66±21.15, Memory=1.8, Type=Convolution-based2025.12 | 73.14 | 86.33 | |
| ConvNeXtv2 (A)#Param=3.42, FLOPs=0.55, FPS=1172.04±34.80, Memory=1.6, Type=Convolution-based2025.12 | 71.15 | 84.97 | |
| ClusterFormer#Param=5.63, FLOPs=1.24, FPS=669.00±4.52, Memory=9.3, Adjusted=true, Type=Clustering-based2025.12 | 70.73 | 85.73 |