Plain-Det: A Plain Multi-Dataset Object Detector

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shi, Cheng, Zhu, Yuchen, Yang, Sibei
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929420051152896
author Shi, Cheng
Zhu, Yuchen
Yang, Sibei
author_facet Shi, Cheng
Zhu, Yuchen
Yang, Sibei
contents Recent advancements in large-scale foundational models have sparked widespread interest in training highly proficient large vision models. A common consensus revolves around the necessity of aggregating extensive, high-quality annotated data. However, given the inherent challenges in annotating dense tasks in computer vision, such as object detection and segmentation, a practical strategy is to combine and leverage all available data for training purposes. In this work, we propose Plain-Det, which offers flexibility to accommodate new datasets, robustness in performance across diverse datasets, training efficiency, and compatibility with various detection architectures. We utilize Def-DETR, with the assistance of Plain-Det, to achieve a mAP of 51.9 on COCO, matching the current state-of-the-art detectors. We conduct extensive experiments on 13 downstream datasets and Plain-Det demonstrates strong generalization capability. Code is release at https://github.com/ChengShiest/Plain-Det
format Preprint
id arxiv_https___arxiv_org_abs_2407_10083
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Plain-Det: A Plain Multi-Dataset Object Detector
Shi, Cheng
Zhu, Yuchen
Yang, Sibei
Computer Vision and Pattern Recognition
Recent advancements in large-scale foundational models have sparked widespread interest in training highly proficient large vision models. A common consensus revolves around the necessity of aggregating extensive, high-quality annotated data. However, given the inherent challenges in annotating dense tasks in computer vision, such as object detection and segmentation, a practical strategy is to combine and leverage all available data for training purposes. In this work, we propose Plain-Det, which offers flexibility to accommodate new datasets, robustness in performance across diverse datasets, training efficiency, and compatibility with various detection architectures. We utilize Def-DETR, with the assistance of Plain-Det, to achieve a mAP of 51.9 on COCO, matching the current state-of-the-art detectors. We conduct extensive experiments on 13 downstream datasets and Plain-Det demonstrates strong generalization capability. Code is release at https://github.com/ChengShiest/Plain-Det
title Plain-Det: A Plain Multi-Dataset Object Detector
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.10083