Papers › A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection Training

A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection Training

20 Aug 2024arXiv:2408.10787archive 2025-07-28

Bilal Faye, Binta Sow, Hanane Azzag, Mustapha Lebbah

Object detection is a fundamental challenge in computer vision, centered on recognizing objects within images, with diverse applications in areas like image analysis, robotics, and autonomous vehicles. Although existing methods have achieved great success, they are often constrained by a fixed vocabulary of objects. To overcome this limitation, approaches like MDETR have redefined object detection by incorporating region-level vision-language pre-training, enabling open-vocabulary object detectors. However, these methods are computationally heavy due to the simultaneous training of large models for both vision and language representations. To address this, we introduce a lightweight framework that significantly reduces the number of parameters while preserving, or even improving, performance. Our solution is applied to MDETR, resulting in the development of Lightweight MDETR (LightMDETR), an optimized version of MDETR designed to enhance computational efficiency without sacrificing accuracy. The core of our approach involves freezing the MDETR backbone and training only the Universal Projection module (UP), which bridges vision and language representations. A learnable modality token parameter allows the UP to seamlessly switch between modalities. Evaluations on tasks like phrase grounding, referring expression comprehension, and segmentation show that LightMDETR not only reduces computational costs but also outperforms several state-of-the-art methods in terms of accuracy.

PaperPDFCode

Code

b-faye/lightmdetr officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous VehiclesComputational EfficiencyObject DetectionOpen Vocabulary Object DetectionOpen-vocabulary object detectionPhrase GroundingReferring ExpressionReferring Expression Comprehensionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MDETR

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections