issues
search
wusize
/
CLIPSelf
[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
https://arxiv.org/abs/2310.01403
Other
149
stars
7
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
The model and loaded state dict do not match exactly
#24
WangZz777
closed
2 weeks ago
0
why class_weight is uneven between categories in F-ViT?
#23
Bilibilee
closed
1 month ago
1
How to train on custom dataset with ground truth masks?
#22
Irennnne
opened
1 month ago
0
inference time
#21
eternaldolphin
opened
1 month ago
1
Problem happend when perform "test_eva_vitb16_macc_boxes_masks.sh "
#20
JuanJia
closed
2 months ago
1
How to get CLIPSelf Checkpoints?
#19
meilijunxi
closed
3 months ago
0
Could you provide the K-Means Visualization code?
#18
SuleBai
closed
3 months ago
2
ValueError: assignment destination is read-only
#17
SuleBai
opened
3 months ago
3
RuntimeError: Pretrained weights (checkpoints) not found for model EVA02-CLIP-B-16.Available pretrained tags (['eva', 'eva02', 'eva_clip', 'eva02_clip'].
#16
cpy0029
opened
3 months ago
1
Is it intentional or a mistake that coco_proposals.json and coco_pseudo_4764.json are completely identical.
#15
Bilibilee
opened
3 months ago
6
question about the results in the paper
#14
jayaylee2
closed
3 months ago
2
Config files for F-ViT from OpenAI-CLIP
#13
yhosoya66
opened
4 months ago
2
Visualization of image segmentation
#12
cjm178
closed
4 months ago
0
performance of Zero-shot Classification and Zero-shot Cross-Modal Retrieval
#11
hamigualisingl
opened
4 months ago
9
Environmental problem
#10
zhangyupeng123
opened
4 months ago
12
Providing Scripts and Checkpoints for training on CC3M
#9
ORippler
opened
4 months ago
1
Generating text embedding files
#8
yhosoya66
closed
4 months ago
2
Request for Window Attention Weights and Code as Referenced in Table 7
#7
cilinyan
closed
5 months ago
3
Error about the dataset-type: invalid choice: 'grid_distill'
#6
wxqlab
opened
5 months ago
1
Can the Lvis_v1 dataset be evaluated?
#5
Xianqiao-Cai
closed
4 months ago
0
CAT-Seg's training setting
#4
BuRr-Lee
opened
7 months ago
3
What are the compute resources required for this?
#3
yxchng
opened
7 months ago
4
Can you provide the VIT/B 16 weights trained by CLIPself on the COCO dataset using Open AI clip?
#2
winnerwu6
closed
8 months ago
2
the Mean Accuracy in table1 means evaluation of ovcoco(65) or coco(80)?
#1
eternaldolphin
opened
9 months ago
2