Skip to content

PraroopChanda/GroundDINO_FineTune

Folders and files

NameName
Last commit message
Last commit date

Latest commit

8609b5e · Apr 1, 2025

History

2 Commits
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025
Apr 1, 2025

Repository files navigation

GroundingDINO Fine-Tune

This repo contains fine-tuned version of GroundingDINO for custom object detection tasks (KITTI).

Some Sample Results Without Fine Tuning

🖼️ Example 1 Without Fine Tuning

Dog and Person Dog Person and Glass Dog Person and Chair Dog and Bag

Figure: From left to right (Input Promt) — Dog and Person, Dog Person and Glass, Dog Person and Chair, Dog and Bag.

🖼️ Example 2 Fine Tuning on Kitti Dataset

Car Person

Figure: From left to right (Input Promt) — Car, Person.

Model Info

  • Base: GroundingDINO
  • Fine Tuned on: KITTI Dataset
  • Detection Loss: Hungarian matcher + classification + L1/IoU
  • GPU: NVIDIA A100

The code is build upon ECCV 2024 Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published