AI Paper Atlas

Research map / Benchmarks / ImageNet, MobileNetV2

ImageNet, MobileNetV2 leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet, MobileNetV2. Best accuracy: 74.3 (MobileNetV2 + CA, r=32, CVPR 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ImageNet, MobileNetV2 · accuracy

15 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
174.3MobileNetV2 + CA, r=32
MobileNetV2
Coordinate Attention for Efficient Mobile Network Design
CVPR 2021 · Table: Comparisons of models e
CNN features
273DMS-MobileNetV2
MobileNetV2
Differentiable Model Scaling using Differentiable Topk
ICML 2024 · Experiments on ImageNet with V
Neural architecture search
372.94NIPQ-BOPs+KD
MobileNet-v2
NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization
CVPR 2023 · Table: ImageNet classification
Quantization
472.1N2UQ
MobileNet-V2
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
CVPR 2022 · Table 2
Quantization
571.92Ours
MobileNetV2
Distribution Adaptive INT8 Quantization for Training CNNs
AAAI 2021 · ImageNet results table
Quantization
671.9DDQ, 4-bit weights/8-bit activations, 90 epochs
MobileNetV2
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
ICML 2021 · Table 1
Quantization
771.9Forward
MobileNetV2
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
ICML 2020 · Appendix, Forward Selection is
Pruning and efficient tuning
871.68Data-Aware PNMQ
MobileNet-v2
Data-Free Network Compression via Parametric Non-Uniform Mixed Precision Quantization
CVPR 2022 · Table 2
Quantization
971.61DSP (g=4)
MobileNetV2
Dynamic Structure Pruning for Compressing CNNs
AAAI 2023 · Table 2
Pruning and efficient tuning
1071.6DEPrune-BH
MobileNet-V2
DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism
NeurIPS 2024 · Table 4
Pruning and efficient tuning
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.