Semantic Segmentation on CC3M-TagMask

Metric: mIoU (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	mIoU▼	Extra Data	Paper	Date↕	Code
1	TTD (TCL)	65.5	No	TTD: Text-Tag Self-Distillation Enhancing Image-...	2024-03-30	Code
2	TCL	60.4	No	Learning to Generate Text-grounded Mask for Open...	2022-12-01	Code
3	TTD (MaskCLIP)	50.2	No	TTD: Text-Tag Self-Distillation Enhancing Image-...	2024-03-30	Code
4	MaskCLIP	41	No	Extract Free Dense Labels from CLIP	2021-12-02	Code

#1TTD (TCL)SOTA
65.5
mIoU· 2024-03-30
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias Code
#2TCLSOTA
60.4
mIoU· 2022-12-01
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs Code
#3TTD (MaskCLIP)
50.2
mIoU· 2024-03-30
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias Code
#4MaskCLIPSOTA
41
mIoU· 2021-12-02
Extract Free Dense Labels from CLIP Code