Vision Transformers are Good Mask Auto-Labelers
Shiyi Lan, Xitong Yang, Zhiding Yu, Zuxuan Wu, José M. Álvarez, Anima Anandkumar
2023年份
9顶会引用
摘要
https://github.com/NVlabs/mask-auto-labeler Figure 1. Examples of mask pseudo-labels generated by Mask Auto-Labeler on COCO. Only human-annotated bounding boxes are used as supervision during training to obtain these results.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。
引用它的顶会 Paper9
- A Simple Framework for Open-Vocabulary Segmentation and DetectionHao Zhang, Feng Li, Xueyan Zou, Shilong Liu 等ICCV 2023 · 被引用 241 次
- Label-efficient Segmentation via Affinity PropagationWentong Li, Yuqian Yuan, Song Wang, Wenyu Liu 等NeurIPS 2023 · 被引用 11 次
- GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo LabelersTuan Duc Ngo, Binh-Son Hua, Khoi NguyenICCV 2023 · 被引用 9 次
- MonoBox: Tightness-Free Box-Supervised Polyp Segmentation Using Monotonicity ConstraintQiang Hu, Zhenyu Yi, Ying Zhou, Fan Huang 等AAAI 2025 · 被引用 8 次
- Advancing Visual Large Language Model for Multi-Granular Versatile PerceptionWentao Xiang, Haoxian Tan, Yujie Zhong, Cong Wei 等ICCV 2025 · 被引用 1 次
它引用的顶会 Paper23
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu 等ICCV 2021 · 被引用 31,683 次
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn 等ICLR 2021 · 被引用 21,477 次
- Training data-efficient image transformers & distillation through attentionHugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa 等ICML 2021 · 被引用 8,974 次
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou 等ICCV 2021 · 被引用 8,921 次
- Deformable DETR: Deformable Transformers for End-to-End Object DetectionXizhou Zhu, Weijie Su, Lewei Lu, Bin Li 等ICLR 2021 · 被引用 7,353 次
相关 Paper
- Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-LabelingDat Huynh, Jason Kuen, Zhe Lin, Jiuxiang Gu 等CVPR 2022 · 被引用 78 次
- Pseudo-label Alignment for Semi-supervised Instance SegmentationJie Hu, Chen Chen, Liujuan Cao, Shengchuan Zhang 等ICCV 2023 · 被引用 31 次
- BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance SegmentationJungbeom Lee, Jihun Yi, Chaehun Shin, Sungroh YoonCVPR 2021
- SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive MiningSaksham Suri, Sai Saketh Rambhatla, Rama Chellappa, Abhinav ShrivastavaICCV 2023 · 被引用 19 次
- Unsupervised Universal Image SegmentationDantong Niu, Xudong Wang, Xinyang Han, Long Lian 等CVPR 2024 · 被引用 29 次
