open-mmlab/mmdetection

SwinT Weight Fine-tuning Leads to Drastic Decline in 'Pole' Object Detection in GroundingDINO

Open

#11,005 opened on Oct 7, 2023

View on GitHubContributor guide
 (13 comments) (0 reactions) (1 assignee)Python (9,821 forks)batch import
good first issue

Repository metrics

Stars
 (32,878 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Dear Author,

Firstly, I would like to express my gratitude for providing the fine-tuning methods for GroundingDINO. Your work is deeply appreciated. However, I've noticed a significant discrepancy in the detection results for the 'pole' object, before and after fine-tuning the SwinT weights. As illustrated in the attached image, after fine-tuning, the model seems unable to detect the 'pole' category in the image. I'm genuinely puzzled by this outcome. Could you perhaps shed some light on why this might be happening?

Furthermore, if I want to specifically fine-tune the model for the 'pole' category, could you suggest a specific method or strategy?

Thank you so much for your time and assistance. Your insights will be invaluable to my work.

Warm regards.

Contributor guide

Research direction
Examine the fine tuning configuration and training data for the 'pole' category; verify that the SwinT backbone weights are not overfitting or losing generalization for unseen categories.
Tech stack
pythonpytorch
Domain
machine learningbackend
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchmmdetection
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65