openai/CLIP
1
0
Fork 0
mirror of https://github.com/openai/CLIP.git synced 2026-11-05 01:37:26 +00:00
Code Issues 274 Projects Packages Wiki Activity

[GH-ISSUE #300] Mis-orderred prompt for KITTI dataset #258

New issue
Open
opened 2026-10-31 21:13:02 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-31 21:13:02 +00:00
Owner
Copy link

Originally created by @haooooooqi on GitHub (Nov 10, 2022).
Original GitHub issue: https://github.com/openai/CLIP/issues/300

Hi,
Thanks so much for providing such impactful work to the community!
I noticed there might be a potential use of the mis-ordered KITTI prompt from https://github.com/openai/CLIP/blob/main/data/prompts.md#kitti

The prompt shared in this git repo is:

classes = [
    'a photo i took of a car on my left or right side.',
    'a photo i took with a car nearby.',
    'a photo i took with a car in the distance.',
    'a photo i took with no car.',
]

Here is the default order of the KITTI (distance) dataset:

above_20  below_20  below_8  no_vehicle

If we pair them:

above_20:  'a photo i took of a car on my left or right side.'
below_20: 'a photo i took with a car nearby.'
below_8: 'a photo i took with a car in the distance.'
no_vehicle: 'a photo i took with no car.'

Seems the right pair should be:

above_20:  'a photo i took with a car in the distance.'
below_20: 'a photo i took with a car nearby.'
below_8: 'a photo i took of a car on my left or right side.'
no_vehicle: 'a photo i took with no car.'

With the order chance, I can get 26.9 (comparing to 23.1 reported in the paper) with the ViT-L/14 224 model.

Hope that could be helpful :)

Haoqi

Originally created by @haooooooqi on GitHub (Nov 10, 2022). Original GitHub issue: https://github.com/openai/CLIP/issues/300 Hi, Thanks so much for providing such impactful work to the community! I noticed there might be a potential use of the mis-ordered KITTI prompt from https://github.com/openai/CLIP/blob/main/data/prompts.md#kitti The prompt shared in this git repo is: ``` classes = [ 'a photo i took of a car on my left or right side.', 'a photo i took with a car nearby.', 'a photo i took with a car in the distance.', 'a photo i took with no car.', ] ``` Here is the default order of the KITTI (distance) dataset: ``` above_20 below_20 below_8 no_vehicle ``` If we pair them: ``` above_20: 'a photo i took of a car on my left or right side.' below_20: 'a photo i took with a car nearby.' below_8: 'a photo i took with a car in the distance.' no_vehicle: 'a photo i took with no car.' ``` Seems the right pair should be: ``` above_20: 'a photo i took with a car in the distance.' below_20: 'a photo i took with a car nearby.' below_8: 'a photo i took of a car on my left or right side.' no_vehicle: 'a photo i took with no car.' ``` With the order chance, I can get 26.9 (comparing to 23.1 reported in the paper) with the ViT-L/14 224 model. Hope that could be helpful :) Haoqi
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
codex/pin-github-workflow-refs-20260325-132838
jongwook/issue-396
jongwook-patch-1
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
openai/CLIP#258
No description provided.