List your company
ResearchFormerly WizWand

Image Classification on ImageNet-1K (val) (Top-1 Accuracy and Delta)

71.71Delta Top-1 AccuracyWF
-2.629216.670435.9755.2696Nov 11, 2024Feb 13, 2025May 18, 2025Aug 21, 2025Nov 23, 2025Feb 25, 2026May 31, 2026
Updated 4mo ago

Evaluation results

MethodLinks
WFArchitecture=MobileNetV1, Sparsity Level=0.8, Dense Accuracy=71.952026.0571.710.24
MPArchitecture=MobileNetV1, Sparsity Level=0.8, Dense Accuracy=71.952026.0571.520.43
MPArchitecture=MobileNetV1, Sparsity Level=0.7, Dense Accuracy=71.952026.0560.2711.68
CBSArchitecture=MobileNetV1, Sparsity Level=0.8, Dense Accuracy=71.952026.0555.5716.38
FALCONArchitecture=MobileNetV1, Sparsity Level=0.8, Dense Accuracy=71.952026.0546.1325.82
WFArchitecture=MobileNetV1, Sparsity Level=0.7, Dense Accuracy=71.952026.0542.5929.36
CHITAArchitecture=MobileNetV1, Sparsity Level=0.8, Dense Accuracy=71.952026.0542.1729.78
BALF-P-0.7Backbone=MobileNetV2, ∆FLOPs%=−2.07±0.01, ∆Params%=−29.72±0.02, Evaluation Protocol=fine-tuning-free2025.0928.08—
MPArchitecture=MobileNetV1, Sparsity Level=0.6, Dense Accuracy=71.952026.0524.847.15
L2+RESTBackbone=MobileNetV2, ∆Params%=−10.00, Evaluation Protocol=fine-tuning-free2025.0918.47—
LR-S2Backbone=MobileNetV2, ∆FLOPs%=−3.81, ∆Params%=−6.24, Evaluation Protocol=fine-tuning-free2025.0917.46—
ALDSBackbone=MobileNetV2, ∆FLOPs%=−2.62, ∆Params%=−37.61, Evaluation Protocol=fine-tuning-free2025.0916.95—
CBSArchitecture=MobileNetV1, Sparsity Level=0.7, Dense Accuracy=71.952026.0516.8455.11
SNOWSArchitecture=MobileNetV1, Sparsity Level=0.8, Dense Accuracy=70.892026.0516.0654.83
FALCONArchitecture=MobileNetV1, Sparsity Level=0.7, Dense Accuracy=71.952026.0513.5558.4
CHITAArchitecture=MobileNetV1, Sparsity Level=0.7, Dense Accuracy=71.952026.0512.5559.4
SVD-NASBackbone=MobileNetV2, ∆FLOPs%=−15.09, ∆Params%=−9.00, Evaluation Protocol=fine-tuning-free2025.0912.54—
STARFISHArchitecture=MobileNetV1, Sparsity Level=0.8, Dense Accuracy=71.952026.0511.2960.66
WFArchitecture=MobileNetV1, Sparsity Level=0.6, Dense Accuracy=71.952026.0511.0560.9
MPArchitecture=MobileNetV1, Sparsity Level=0.5, Dense Accuracy=71.952026.058.1263.83
ScaleKDTeacher=BEIT-L/14‡, Student=Mixer-B/14, Teacher Params (M)=304.14, Student Params (M)=59.88, Teacher FLOPS (G)=81.06, Student FLOPS (G)=16.45, Pre-training=EVA [41]2024.116.2782.89
BALF-P-0.75Backbone=MobileNetV2, ∆FLOPs%=−1.13±0.01, ∆Params%=−24.78±0.02, Evaluation Protocol=fine-tuning-free2025.096.17—
SNOWSArchitecture=MobileNetV1, Sparsity Level=0.7, Dense Accuracy=70.892026.055.6165.28
CBSArchitecture=MobileNetV1, Sparsity Level=0.6, Dense Accuracy=71.952026.055.5866.37
ScaleKDTeacher=Swin-L†, Student=Mixer-B/16, Teacher Params (M)=196.53, Student Params (M)=59.88, Teacher FLOPS (G)=34.04, Student FLOPS (G)=12.61, Pre-training=IN-22K [45]2024.115.5281.96
BALF-F-0.97Backbone=MobileNetV2, ∆FLOPs%=−2.51±0.00, ∆Params%=−1.55±0.00, Evaluation Protocol=fine-tuning-free2025.094.89—
FALCONArchitecture=MobileNetV1, Sparsity Level=0.6, Dense Accuracy=71.952026.054.7767.18
CHITAArchitecture=MobileNetV1, Sparsity Level=0.6, Dense Accuracy=71.952026.054.6567.3
ScaleKDTeacher=Swin-L†, Student=Mixer-S/16, Teacher Params (M)=196.53, Student Params (M)=18.53, Teacher FLOPS (G)=34.04, Student FLOPS (G)=3.78, Pre-training=IN-22K [45]2024.114.6178.63
L2+RESTBackbone=MobileNetV2, ∆Params%=−5.00, Evaluation Protocol=fine-tuning-free2025.094.42—
ScaleKDTeacher=BEIT-L/14‡, Student=ViT-B/14, Teacher Params (M)=304.14, Student Params (M)=86.57, Teacher FLOPS (G)=81.06, Student FLOPS (G)=23.09, Pre-training=EVA [41]2024.114.4186.43
STARFISHArchitecture=MobileNetV1, Sparsity Level=0.7, Dense Accuracy=71.952026.054.2867.67
ScaleKDTeacher=Swin-L†, Student=ViT-S/16, Teacher Params (M)=196.53, Student Params (M)=22.05, Teacher FLOPS (G)=34.04, Student FLOPS (G)=4.61, Pre-training=IN-22K [45]2024.114.0383.93
ScaleKDTeacher=Swin-L†, Student=ViT-B/16, Teacher Params (M)=196.53, Student Params (M)=86.57, Teacher FLOPS (G)=34.04, Student FLOPS (G)=17.58, Pre-training=IN-22K [45]2024.113.7385.53
ScaleKDTeacher=BEIT-L/14‡, Student=ResNet-50, Teacher Params (M)=304.14, Student Params (M)=25.56, Teacher FLOPS (G)=81.06, Student FLOPS (G)=4.12, Pre-training=EVA [41]2024.113.782.34
ScaleKDTeacher=Swin-L†, Student=ResNet-50, Teacher Params (M)=196.53, Student Params (M)=25.56, Teacher FLOPS (G)=34.04, Student FLOPS (G)=4.12, Pre-training=IN-22K [45]2024.113.3982.03
ScaleKDTeacher=Swin-L†, Student=MobileNet-V1, Teacher Params (M)=196.53, Student Params (M)=4.23, Teacher FLOPS (G)=34.04, Student FLOPS (G)=0.58, Pre-training=IN-22K [45]2024.113.0575.15
WFArchitecture=MobileNetV1, Sparsity Level=0.5, Dense Accuracy=71.952026.053.0468.91
ScaleKDTeacher=Swin-L†, Student=Swin-T, Teacher Params (M)=196.53, Student Params (M)=28.29, Teacher FLOPS (G)=34.04, Student FLOPS (G)=4.36, Pre-training=IN-22K [45]2024.112.6283.8
SNOWSArchitecture=MobileNetV1, Sparsity Level=0.6, Dense Accuracy=70.892026.052.1968.7
ScaleKDTeacher=Swin-L†, Student=ConvNeXt-T, Teacher Params (M)=196.53, Student Params (M)=28.59, Teacher FLOPS (G)=34.04, Student FLOPS (G)=4.46, Pre-training=IN-22K [45]2024.112.0284.16
STARFISHArchitecture=MobileNetV1, Sparsity Level=0.6, Dense Accuracy=71.952026.051.8570.1
CBSArchitecture=MobileNetV1, Sparsity Level=0.5, Dense Accuracy=71.952026.051.7470.21
FALCONArchitecture=MobileNetV1, Sparsity Level=0.5, Dense Accuracy=71.952026.051.670.35
CHITAArchitecture=MobileNetV1, Sparsity Level=0.5, Dense Accuracy=71.952026.051.5370.42
STARFISHArchitecture=MobileNetV1, Sparsity Level=0.5, Dense Accuracy=71.952026.050.8371.12
SNOWSArchitecture=MobileNetV1, Sparsity Level=0.5, Dense Accuracy=70.892026.050.7970.1
BALF-P-0.8Backbone=MobileNetV2, ∆FLOPs%=−0.23±0.00, ∆Params%=−19.80±0.00, Evaluation Protocol=fine-tuning-free2025.090.61—
BALF-P-0.9Backbone=MobileNetV2, ∆FLOPs%=−0.12±0.00, ∆Params%=−10.69±0.05, Evaluation Protocol=fine-tuning-free2025.090.23—