CLIP-EBC (ViT-L/14)

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

CrowdsonShanghaiTech B
MAE· uses extra data· 2024-03-14
5.9
best: 5.51 (EBC-ZIP-B)
SOTA
CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification arXiv:2403.09281
CrowdsonShanghaiTech B
RMSE· uses extra data· 2024-03-14
9.2
best: 8.63 (EBC-ZIP-B)
SOTA
CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification arXiv:2403.09281
CrowdsonNWPU-Crowd (Val)
MAE· 2024-03-14
32.3
best: 28.26 (EBC-ZIP-B)
SOTA
CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification arXiv:2403.09281
CrowdsonNWPU-Crowd (Val)
RMSE· 2024-03-14
79.7
best: 64.84 (EBC-ZIP-B)
SOTA
CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification arXiv:2403.09281