Lune

ICCV2019Top-tier venue

Objects365: A Large-Scale, High-Quality Dataset for Object Detection

Shuai Shao, Zeming Li, Tianyuan Zhang, Chao Peng, Gang Yu, Xiangyu Zhang, Jing Li, Jian Sun

Abstract

In this paper, we introduce a new large-scale object detection dataset, Objects365, which has 365 object categories over 600K training images. More than 10 million, high-quality bounding boxes are manually labeled through a three-step, carefully designed annotation pipeline. It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community. Objects365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation. The Objects365 pre-trained models significantly outperform ImageNet pre-trained models with 5.6 points gain (42 vs 36.4) based on the standard setting of 90K iterations on COCO benchmark. Even compared with much long training time like 540K iterations, our Objects365 pretrained model with 90K iterations still have 2.7 points gain (42 vs 39.3). Meanwhile, the finetuning time can be greatly reduced (up to 10 times) when reaching the same accuracy. Better generalization ability of Object365 has also been verified on CityPersons, VOC segmentation, and ADE tasks. The dataset as well as the pretrainedmodels have been released at www.objects365.org.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

353 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Depth Anything V2 cites Swin Transformer V2: Scaling Up Capacity and Resolution
  • YOLOv10: Real-Time End-to-End Object Detection cites DETRs Beat YOLOs on Real-time Object Detection
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers353

  1. YOLOv10: Real-Time End-to-End Object DetectionAo Wang, Hui Chen, Lihao Liu, Kai Chen et al.NeurIPS 2024 · 6,113 citations
  2. DETRs Beat YOLOs on Real-time Object DetectionYian Zhao, Wenyu Lv, Shangliang Xu, Jinman Wei et al.CVPR 2024 · 3,046 citations
  3. Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
  4. Swin Transformer V2: Scaling Up Capacity and ResolutionZe Liu, Han Hu, Yutong Lin, Zhuliang Yao et al.CVPR 2022 · 2,138 citations
  5. Open-vocabulary Object Detection via Vision and Language Knowledge DistillationXiuye Gu, Tsung-Yi Lin, Weicheng Kuo, Yin CuiICLR 2022 · 1,274 citations

Builds on1

  1. Rethinking ImageNet Pre-TrainingKaiming He, Ross B. Girshick, Piotr DollárICCV 2019 · 1,188 citations

Related papers

  1. V3Det: Vast Vocabulary Visual Detection DatasetJiaqi Wang, Pan Zhang, Tao Chu, Yuhang Cao et al.ICCV 2023 · 86 citations
  2. GAIA: A Transfer Learning System of Object Detection That Fits Your NeedsXingyuan Bu, Junran Peng, Junjie Yan, Tieniu Tan et al.CVPR 2021
  3. UnCommon Objects in 3DXingchen Liu, Piyush Tayal, Jianyuan Wang, Jesus Zarzar et al.CVPR 2025
  4. Instance Localization for Self-Supervised Detection PretrainingCeyuan Yang, Zhirong Wu, Bolei Zhou, Stephen LinCVPR 2021
  5. Unsupervised Object Detection Pretraining with Joint Object Priors Generation and Detector LearningYizhou Wang, Meilin Chen, Shixiang Tang, Feng Zhu et al.NeurIPS 2022 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines