Depth Image Classification on NYU-D
79.4Top-1 AccAbsolute SOTA
Evaluation results
| Method | Links | |
|---|---|---|
| Absolute SOTAAnchor Modality=–2026.04 | 79.4 | |
| Supervised SOTA2023.11 | 76.7 | |
| DepthSwinAnchor Modality=–2026.04 | 72.5 | |
| UNIALIGN2026.05 | 71.4 | |
| CodeBind-VL2026.05 | 71.1 | |
| EmergentBridgeAnchor Modality=Image2026.04 | 70.1 | |
| ViT-LENSLanchor=I+T2023.11 | 68.5 | |
| JointCRFAnchor Modality=–2026.04 | 65.8 | |
| EmergentBridgeAnchor Modality=Text2026.04 | 65.8 | |
| DFCRAnchor Modality=–2026.04 | 65.3 | |
| LanguageBindSize=Large, Evaluation Protocol=Zero-shot2023.10 | 65.1 | |
| LanguageBindAnchor Modality=Text2026.04 | 65.1 | |
| ViT-LENSLanchor=I2023.11 | 64.2 | |
| CodeBind-IB2026.05 | 59.3 | |
| ImageBindSize=Huge, Evaluation Protocol=Zero-shot2023.10 | 54 | |
| ImageBind-Hanchor=I2023.11 | 54 | |
| ImageBindAnchor Modality=Image2026.04 | 54 | |
| OneLLM-D2026.05 | 50.9 | |
| OpenCLIPSize=Large, Evaluation Protocol=Zero-shot2023.10 | 45.4 | |
| OpenCLIPAnchor Modality=–2026.04 | 45.4 | |
| Text Pairedanchor=T*2023.11 | 41.9 |