Papers › MOD-CL: Multi-label Object Detection with Constrained Loss

MOD-CL: Multi-label Object Detection with Constrained Loss

31 Jan 2024arXiv:2403.07885archive 2025-07-28

Sota Moriyama, Koji Watanabe, Katsumi Inoue, Akihiro Takemura

We introduce MOD-CL, a multi-label object detection framework that utilizes constrained loss in the training process to produce outputs that better satisfy the given requirements. In this paper, we use MOD_(YOLO), a multi-label object detection model built upon the state-of-the-art object detection model YOLOv8, which has been published in recent years. In Task 1, we introduce the Corrector Model and Blender Model, two new models that follow after the object detection process, aiming to generate a more constrained output. For Task 2, constrained losses have been incorporated into the MOD_(YOLO) architecture using Product T-Norm. The results show that these implementations are instrumental to improving the scores for both Task 1 and Task 2.

PaperPDFCode

Code

sotam2369/MOD-CL officialpytorch 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

ObjectObject DetectionTask 2object-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

RoIAlignRoIPoolSoftmaxYOLOv8

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