Object Recognition
Object recognition is a computer vision technique for detecting + classifying objects in images or videos. Since this is a combined task of object detection plus image classification, the state-of-the-art tables are recorded for each component task here and here.
( Image credit: Tensorflow Object Detection API )
Papers
Showing 1–10 of 2042 papers
All datasetsshape biasCIFAR10-DVSN-Caltech 101ObjectNet (All classes)ObjectNet (ImageNet classes)ObjectNet (ImageNet classes, trained on ImageNet)DVS128 GestureMECCANON-CARS
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Imagen | shape bias | 98.7 | — | Unverified |
| 2 | Stable Diffusion | shape bias | 92.7 | — | Unverified |
| 3 | Parti | shape bias | 91.7 | — | Unverified |
| 4 | ViT-22B-384 | shape bias | 86.4 | — | Unverified |
| 5 | ViT-22B-560 | shape bias | 83.8 | — | Unverified |
| 6 | CLIP (ViT-B) | shape bias | 79.9 | — | Unverified |
| 7 | ViT-22B-224 | shape bias | 78 | — | Unverified |
| 8 | ResNet-50 (L2 eps 5.0 adv trained) | shape bias | 69.5 | — | Unverified |
| 9 | ResNet-50 (with strong augmentations) | shape bias | 62.2 | — | Unverified |
| 10 | SWSL (ResNeXt-101) | shape bias | 49.8 | — | Unverified |