Image Classification 벤치마크
Image Classification on Caltech-256
Accuracy
- 2021-07-19 — Inceptionv4: Accuracy 85.94
- 2021-10-23 — AG-Net: Accuracy 96.89
| Rank | Model | Accuracy | Extra Training Data | Paper | Code | Year |
|---|---|---|---|---|---|---|
| 1 | AG-Net | 96.89% | Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition | DanielKovach/AG-Net | 2021 | |
| 2 | Inceptionv4 | 85.94 | ✓ | Non-binary deep transfer learning for image classification | XuyangSHEN/Non-binary-deep-transfer-learning-for-image-classification | 2021 |
| 3 | swin-transformer | 77 | ||||
| 4 | Inceptionv4 (random initialization) | 67.2 | Non-binary deep transfer learning for image classification | XuyangSHEN/Non-binary-deep-transfer-learning-for-image-classification | 2021 | |
| 5 | WaveMixLite-256/7 | 54.62 | WaveMix: A Resource-efficient Neural Network for Image Analysis | pranavphoenix/WaveMix | 2022 |