UMG-CLIP-E/14
|
UMG-CLIP: A Unified Multi-Granularity Vision Gene…
|
31.60
|
2024-01-12
|
|
PosSAM
|
PosSAM: Panoptic Open-vocabulary Segment Anything
|
29.20
|
2024-03-14
|
|
UMG-CLIP-L/14
|
UMG-CLIP: A Unified Multi-Granularity Vision Gene…
|
29.10
|
2024-01-12
|
|
MAFT+
|
Collaborative Vision-Text Representation Optimizi…
|
27.10
|
2024-08-01
|
|
FC-CLIP
|
Convolutions Die Hard: Open-Vocabulary Segmentati…
|
26.80
|
2023-08-04
|
|
CLIPSelf
|
CLIPSelf: Vision Transformer Distills Itself for …
|
23.70
|
2023-10-02
|
|
ODISE(Caption)
|
Open-Vocabulary Panoptic Segmentation with Text-t…
|
23.40
|
2023-03-08
|
|
ODISE (Label)
|
Open-Vocabulary Panoptic Segmentation with Text-t…
|
22.60
|
2023-03-08
|
|
FreeSeg
|
FreeSeg: Unified, Universal and Open-Vocabulary I…
|
16.30
|
2023-03-30
|
|
MaskCLIP
|
Extract Free Dense Labels from CLIP
|
15.10
|
2021-12-02
|
|