ImageNet Classification Leaderboard
The goal of this page is:
- To keep on track of state-of-the-art (SOTA) on ImageNet Classification and new CNN architectures
- To see the comparison of famous CNN models at a glance (performance, speed, size, etc.)
- To access their research papers and implementations on different frameworks
If you want to keep following this page, please star and watch this repository.
Leaderboard
- Mult-Adds: The number of multiply-add operations
- FLOPS: The floating point operations
Value References
Numbers in the ‘Reference’ column indicate the reference webpages and papers for each model’s values.
- TF-Slim
- Keras: Applications
- CBAM: Convolutional Block Attention Module
- Squeeze-and-Excitation Networks
- Progressive Neural Architecture Search
- Residual Attention Network for Image Classification
- Deep Pyramidal Residual Networks
- Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
- MnasNet: Platform-Aware Neural Architecture Search for Mobile
Contribution
If you want
- To add any value from your own model and paper on the leaderboard
- To revise any mistake in the leaderboard
- To update any value on the existing model
please leave your suggestion in the issue page of this repository.
Author
Byung Soo Ko / kobiso62@gmail.com