Text-to-Image Retrieval on MS-COCO 1K
65.1R@1CRCL
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CRCLGlobal-level method=false2023.10 | 65.1 | 91.2 | 96.1 | 528.2 | |
| CCR&CCSGlobal-level method=false2023.10 | 64.3 | 90.6 | 95.8 | 526.4 | |
| RCLGlobal-level method=false2023.10 | 64.3 | 90.8 | 96 | 526.6 | |
| MSCNNoise=20%2024.03 | 64.3 | 90.4 | 95.8 | 524.6 | |
| CMCANGlobal-level method=false2023.10 | 63.9 | 90.7 | 96.2 | 524.8 | |
| CGMNGlobal-level method=false2023.10 | 63.8 | 90.7 | 95.7 | 520.7 | |
| GSMNGlobal-level method=false2023.10 | 63.3 | 90.1 | 95.7 | 522.5 | |
| NCRGlobal-level method=false2023.10 | 63.3 | 90.4 | 95.8 | 522.5 | |
| DECLGlobal-level method=false2023.10 | 63.3 | 90.1 | 95.6 | 523.1 | |
| SGRAFGlobal-level method=false2023.10 | 63.2 | 90.7 | 96.1 | 524.3 | |
| NAAFGlobal-level method=false2023.10 | 63.1 | 91.4 | 96.5 | 524.6 | |
| VSRNGlobal-level method=true2023.10 | 62.8 | 89.7 | 95.1 | 516.8 | |
| SEPSFine-grained alignment=true, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.11 | 62.8 | 87.5 | — | — | |
| MV-VSEGlobal-level method=true2023.10 | 62.7 | 90.4 | 95.7 | 521.9 | |
| BiCroGlobal-level method=false2023.10 | 62.7 | 90 | 95.7 | 521 | |
| NCRNoise=20%, re-implemented=true2024.03 | 62.5 | 89.6 | 95.3 | 519.2 | |
| REPAIRNoise=20%2024.03 | 62.5 | 89.8 | 95.5 | 521.2 | |
| VSE∞Global-level method=true2023.10 | 61.7 | 90.3 | 95.6 | 520.8 | |
| IMRAMGlobal-level method=false2023.10 | 61.7 | 89.1 | 95 | 516.6 | |
| REPAIRNoise=40%2024.03 | 61 | 88.8 | 95 | 515 | |
| NCRNoise=40%, re-implemented=true2024.03 | 60.6 | 88.6 | 94.9 | 513.6 | |
| BiCroNoise=20%, re-implemented=true2024.03 | 60.5 | 88.8 | 95.1 | 513.2 | |
| BiCroNoise=40%, re-implemented=true2024.03 | 60.4 | 87.9 | 94.2 | 511.2 | |
| MSCNNoise=40%2024.03 | 60.3 | 88.5 | 94.4 | 510.9 | |
| DECLNoise=20%2024.03 | 59.9 | 88.3 | 94.7 | 511.9 | |
| MSCNNoise=60%2024.03 | 59.2 | 87.1 | 92.8 | 506.5 | |
| SCANGlobal-level method=false2023.10 | 58.8 | 88.4 | 94.8 | 507.9 | |
| BiCroNoise=60%, re-implemented=true2024.03 | 58.8 | 86.9 | 93.7 | 506.2 | |
| REPAIRNoise=60%2024.03 | 58.6 | 87.3 | 94.1 | 506 | |
| CAMPGlobal-level method=false2023.10 | 58.5 | 87.9 | 95 | 506.8 | |
| UARDAGlobal-level method=false2023.10 | 57.8 | 82.9 | 89.2 | 500.3 | |
| DECLNoise=40%2024.03 | 57.8 | 86.9 | 93.9 | 504.7 | |
| NCRNoise=60%, re-implemented=true2024.03 | 57.8 | 87.1 | 94 | 503.1 | |
| VSE∞Noise=20%2024.03 | 57.4 | 86.5 | 92.8 | 500.5 | |
| CVSEGlobal-level method=true2023.10 | 55.7 | 86.9 | 93.8 | 496.4 | |
| DECLNoise=60%2024.03 | 54.5 | 85.2 | 92.6 | 492.9 | |
| SGRNoise=20%2024.03 | 42.5 | 77.7 | 88.2 | 434 | |
| SGRNoise=40%2024.03 | 37 | 72.8 | 85.1 | 406.4 | |
| LAPSFine-grained alignment=true, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.11 | 35.8 | 66.1 | — | — | |
| SGRNoise=60%2024.03 | 33.8 | 68.6 | 81.7 | 381.3 | |
| VSE∞Noise=40%2024.03 | 31.4 | 63.8 | 75 | 399.9 | |
| FedAFDData Setting=IID, Evaluation Location=Server, #rounds=212026.03 | 26.02 | — | — | — | |
| VSE∞Noise=60%2024.03 | 26 | 60.1 | 76.3 | 339.7 | |
| CreamFLData Setting=IID, Evaluation Location=Server, #rounds=222026.03 | 25.98 | — | — | — | |
| FedETData Setting=IID, Evaluation Location=Server, #rounds=232026.03 | 25.88 | — | — | — | |
| FedMKDData Setting=IID, Evaluation Location=Server, #rounds=222026.03 | 25.71 | — | — | — | |
| FedGEMSData Setting=IID, Evaluation Location=Server, #rounds=262026.03 | 25.64 | — | — | — | |
| FedMDData Setting=IID, Evaluation Location=Server, #rounds=252026.03 | 25.52 | — | — | — | |
| FedDFAData Setting=IID, Evaluation Location=Server, #rounds=252026.03 | 25.48 | — | — | — | |
| LOCALData Setting=IID, Evaluation Location=Server, #rounds=292026.03 | 25.01 | — | — | — | |
| D2S-VSEFine-grained alignment=false, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.11 | 24.8 | 53.9 | — | — | |
| SCANFine-grained alignment=true, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.11 | 23.2 | 51.5 | — | — | |
| SCANNoise=20%2024.03 | 20.6 | 55.6 | 73.5 | 322.6 | |
| VSE++Fine-grained alignment=false, Zero-shot=true, Backbone=CLIP ViT-B/16, Training Dataset=Flickr2025.11 | 20.5 | 46.8 | — | — | |
| SCANNoise=40%2024.03 | 18.9 | 51.1 | 69.9 | 314.4 | |
| SCANNoise=60%2024.03 | 16.8 | 47.8 | 66.4 | 293.4 |