wangf3014 SCLIP issues - Githubissues

wangf3014 / SCLIP

Official implementation of SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

110 stars 9 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

训练代码有开源计划吗

#16 APeiZou closed 1 week ago
0
performance degrade when applying a consistent evaluating code with other methods (TCL, GroupVit..)

#15 wuwuwuxxx opened 5 months ago
2
Questions about PAMR

#13 KarlLi5 opened 6 months ago
0
About the demo

#12 Kaisor-Yuan opened 6 months ago
6
Reason on a single image and output any category

#11 WuHenry-0609 opened 7 months ago
0
How to visualize the attention map

#10 jiinhui opened 7 months ago
0
Using other ViT models yeilds lower miou score

#9 yiheng003 opened 7 months ago
0
Code of Learned projection

#8 yuan-zm opened 7 months ago
0
Question about the visualization

#7 KarlLi5 opened 8 months ago
3
Why directly add the results of q_attn and k_attn instead of normalizing them?

#6 kinredon closed 8 months ago
2
Question about performance and hyparameter

#5 changhaonan opened 8 months ago
6
About post processing.

#4 Colezwhy closed 8 months ago
1
算法细节问题

#3 WeiCL7777 opened 8 months ago
1
Some questions about reproducing COCO-stuff164k results using SCLIP

#2 taiwuyouxu opened 9 months ago
1
Inquiry Regarding GPU Configuration for Running

#1 XiudingCai closed 9 months ago
2