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

arXiv: https://arxiv.org/abs/2403.07885 · HTML: https://mlsanity.com/paper/2403.07885/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Builds on (most cited first, 3 of 3)

- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [ROAD-R: The Autonomous Driving Dataset with Logical Requirements](https://mlsanity.com/paper/2210.01597/) (2022)

## Built on by (most cited first, 1 of 1)

- [Integrating Legal and Logical Specifications in Perception, Prediction, and Planning for Automated Driving: A Survey of Methods](https://mlsanity.com/paper/2510.25386/) (2025)

## Abstract (arXiv)

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 mathrmMODYOLO, 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 mathrmMODYOLO architecture using Product T-Norm. The results show that these implementations are instrumental to improving the scores for both Task 1 and Task 2.