Kaiming He — all works
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine IntelligenceShaoqing Ren, Kaiming He, Ross Girshick, et al.2015 · 65,090 citations
- Mask R-CNN ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetKaiming He et al.2017 · 29,617 citations
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification ↗arXiv:1502.01852 · no summary yetKaiming He et al.2015 · 19,426 citations
- Momentum Contrast for Unsupervised Visual Representation LearningIEEE Computer Society Conference on Computer Vision and Pattern RecognitionKaiming He, Haoqi Fan, Yuxin Wu, et al.2019 · 13,302 citations
- Aggregated Residual Transformations for Deep Neural Networks ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSaining Xie et al.2017 · 12,133 citations
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetKaiming He et al.2015 · 11,470 citations
- Non-local Neural Networks ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXiaolong Wang et al.2018 · 11,175 citations
- Identity Mappings in Deep Residual Networks ↗arXiv:1603.05027 · no summary yetKaiming He et al.2016 · 10,240 citations
- Image Super-Resolution Using Deep Convolutional Networks ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetChao Dong et al.2015 · 10,114 citations
- Deep Residual Learning for Image RecognitionarXiv:1512.03385Kaiming He, Xiangyu Zhang, Shaoqing Ren, et al.2015 · 9,425 citations
- Single Image Haze Removal Using Dark Channel Prior ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetKaiming He, Jian Sun, Xiaoou Tang2010 · 6,262 citations
- Learning a Deep Convolutional Network for Image Super-Resolution ↗Lecture notes in computer science · no summary yetChao Dong et al.2014 · 5,551 citations
- Guided Image Filtering ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetKaiming He, Jian Zhong Sun, Xiaoou Tang2012 · 5,470 citations
- SlowFast Networks for Video Recognition ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetChristoph Feichtenhofer et al.2019 · 3,884 citations
- Exploring Simple Siamese Representation Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXinlei Chen, Kaiming He2021 · 3,665 citations
- R-FCN: Object Detection via Region-based Fully Convolutional Networks ↗arXiv (Cornell University) · no summary yetJifeng Dai et al.2016 · 3,248 citations
- Group Normalization ↗Lecture notes in computer science · no summary yetYuxin Wu, Kaiming He2018 · 3,072 citations
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour ↗arXiv:1706.02677 · no summary yetPriya Goyal et al.2017 · 2,756 citations
- Improved Baselines with Momentum Contrastive Learning ↗arXiv (Cornell University) · no summary yetXinlei Chen et al.2020 · 2,098 citations
- Designing Network Design Spaces ↗arXiv:2003.13678 · no summary yetIlija Radosavovic et al.2020 · 2,040 citations
- Focal Loss for Dense Object DetectionarXiv:1708.02002Tsung-Yi Lin, Priya Goyal, Ross Girshick, et al.2017 · 1,995 citations
- An Empirical Study of Training Self-Supervised Vision Transformers ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXinlei Chen, Saining Xie, Kaiming He2021 · 1,658 citations
- Panoptic Segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAlexander Kirillov et al.2019 · 1,584 citations
- Guided Image Filtering ↗Lecture notes in computer science · no summary yetKaiming He, Jian Sun, Xiaoou Tang2010 · 1,576 citations
- Convolutional neural networks at constrained time cost ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKaiming He, Jian Sun2015 · 1,522 citations
- Panoptic Feature Pyramid Networks ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAlexander Kirillov et al.2019 · 1,406 citations
- Exploring the Limits of Weakly Supervised Pretraining ↗Lecture notes in computer science · no summary yetDhruv Kumar Mahajan et al.2018 · 1,295 citations
- Instance-Aware Semantic Segmentation via Multi-task Network Cascades ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJifeng Dai, Kaiming He, Jian Sun2016 · 1,287 citations
- Deep Hough Voting for 3D Object Detection in Point Clouds ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetCharles R. Qi et al.2019 · 1,270 citations
- PointRend: Image Segmentation As Rendering ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAlexander Kirillov et al.2020 · 1,157 citations
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetJifeng Dai, Kaiming He, Jian Sun2015 · 1,130 citations
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetDi Lin et al.2016 · 1,096 citations
- Rethinking ImageNet Pre-Training ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetKaiming He, Ross Girshick, Piotr Dollár2019 · 1,089 citations
- Feature Denoising for Improving Adversarial Robustness ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetCihang Xie et al.2019 · 915 citations
- Exploring Plain Vision Transformer Backbones for Object Detection ↗Lecture notes in computer science · no summary yetYanghao Li et al.2022 · 872 citations
- Accelerating Very Deep Convolutional Networks for Classification and Detection ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetXiangyu Zhang et al.2015 · 860 citations
- Is Faster R-CNN Doing Well for Pedestrian Detection? ↗Lecture notes in computer science · no summary yetLiliang Zhang et al.2016 · 838 citations
- Feature Pyramid Networks for Object Detection ↗arXiv:1612.03144 · no summary yetTsung-Yi Lin et al.2016 · 767 citations
- Detecting and Recognizing Human-Object Interactions ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetGeorgia Gkioxari et al.2018 · 612 citations
- Masked Autoencoders Are Scalable Vision LearnersarXiv:2111.06377Kaiming He, Xinlei Chen, Saining Xie, et al.2021 · 596 citations
- Long-Term Feature Banks for Detailed Video Understanding ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetChao-Yuan Wu et al.2019 · 476 citations
- Object Detection Networks on Convolutional Feature Maps ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetShaoqing Ren et al.2016 · 462 citations
- Data Distillation: Towards Omni-Supervised Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetIlija Radosavovic et al.2018 · 441 citations
- Convolutional feature masking for joint object and stuff segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJifeng Dai, Kaiming He, Jian Sun2015 · 441 citations
- Instance-Sensitive Fully Convolutional Networks ↗Lecture notes in computer science · no summary yetJifeng Dai et al.2016 · 434 citations
- Optimized Product Quantization ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetTiezheng Ge et al.2013 · 425 citations
- Optimized Product Quantization for Approximate Nearest Neighbor Search ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetTiezheng Ge et al.2013 · 402 citations
- K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKaiming He, Fang Wen, Jian Zhong Sun2013 · 398 citations
- TensorMask: A Foundation for Dense Object Segmentation ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXinlei Chen et al.2019 · 389 citations
- Exploring Randomly Wired Neural Networks for Image Recognition ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetSaining Xie et al.2019 · 365 citations
- A global sampling method for alpha matting ↗no summary yetKaiming He et al.2011 · 315 citations
- Masked Autoencoders as Spatiotemporal Learners ↗neural information processing systems · no summary yetChristoph Feichtenhofer et al.2022 · 302 citations
- Learning to Segment Every Thing ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetRonghang Hu et al.2018 · 293 citations
- Constant Time Weighted Median Filtering for Stereo Matching and Beyond ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetZiyang Ma et al.2013 · 293 citations
- Scaling Language-Image Pre-Training via Masking ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYanghao Li et al.2023 · 283 citations
- Efficient and accurate approximations of nonlinear convolutional networks ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXiangyu Zhang et al.2015 · 273 citations
- A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetChristoph Feichtenhofer et al.2021 · 226 citations
- Statistics of Patch Offsets for Image Completion ↗Lecture notes in computer science · no summary yetKaiming He, Jian Zhong Sun2012 · 191 citations
- Transformers without Normalization ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJiachen Zhu et al.2025 · 179 citations
- Transitive Invariance for Self-Supervised Visual Representation Learning ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetXiaolong Wang, Kaiming He, Abhinav Gupta2017 · 178 citations
- Image Completion Approaches Using the Statistics of Similar Patches ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetKaiming He, Jian Zhong Sun2014 · 173 citations
- Fast matting using large kernel matting Laplacian matrices ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKaiming He, Jian Sun, Xiaoou Tang2010 · 165 citations
- Computing nearest-neighbor fields via Propagation-Assisted KD-Trees ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKaiming He, Jian Sun2012 · 115 citations
- Autoregressive Image Generation without Vector Quantization ↗neural information processing systems · no summary yetTianhong Li et al.2024 · 110 citations
- Fast Guided Filter ↗arXiv (Cornell University) · no summary yetKaiming He, Jian Dong Sun2015 · 101 citations
- A Multigrid Method for Efficiently Training Video Models ↗arXiv:1912.00998 · no summary yetChao-Yuan Wu et al.2019 · 95 citations
- Rectangling panoramic images via warping ↗ACM Transactions on Graphics · no summary yetKaiming He, Huiwen Chang, Jian Zhong Sun2013 · 94 citations
- Benchmarking Detection Transfer Learning with Vision Transformers ↗arXiv (Cornell University) · no summary yetYanghao Li et al.2021 · 86 citations
- Sparse projections for high-dimensional binary codes ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYan Xia et al.2015 · 84 citations
- Mean Flows for One-step Generative Modeling ↗neural information processing systems · no summary yetZhengyang Geng et al.2025 · 83 citations
- Are Labels Necessary for Neural Architecture Search? ↗Lecture notes in computer science · no summary yetChenxi Liu et al.2020 · 71 citations
- Graph Cuts for Supervised Binary Coding ↗Lecture notes in computer science · no summary yetTiezheng Ge, Kaiming He, Jian Zhong Sun2014 · 62 citations
- Joint Inverted Indexing ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetYan Xia et al.2013 · 62 citations
- GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations ↗arXiv (Cornell University) · no summary yetZhilin Yang et al.2018 · 34 citations
- A geodesic-preserving method for image warping ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetDongping Li et al.2015 · 31 citations
- Back to Basics: Let Denoising Generative Models Denoise ↗arXiv (Cornell University) · no summary yetLi, Tianhong, Kaiming He2025 · 30 citations
- Content-Aware Rotation ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetKaiming He, Huiwen Chang, Jian Zhong Sun2013 · 30 citations
- Deconstructing Denoising Diffusion Models for Self-Supervised Learning ↗arXiv (Cornell University) · no summary yetXinlei Chen et al.2024 · 25 citations
- Product Sparse Coding ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetTiezheng Ge, Kaiming He, Jian Zhong Sun2014 · 24 citations
- Graph Structure of Neural Networks ↗arXiv (Cornell University) · no summary yetJiaxuan You et al.2020 · 21 citations
- GLoMo: Unsupervised Learning of Transferable Relational Graphs ↗neural information processing systems · no summary yetZhilin Yang et al.2018 · 21 citations
- Return of Unconditional Generation: A Self-supervised Representation Generation Method ↗neural information processing systems · no summary yetTianhong Li, Dina Katabi, Kaiming He2024 · 17 citations
- Improved Mean Flows: On the Challenges of Fastforward Generative Models ↗arXiv (Cornell University) · no summary yetZhengyang Geng et al.2025 · 12 citations
- A Decade's Battle on Dataset Bias: Are We There Yet? ↗arXiv (Cornell University) · no summary yetZhuang Liu, Kaiming He2024 · 11 citations
- Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens ↗arXiv (Cornell University) · no summary yetLijie Fan et al.2024 · 10 citations
- Generative Modeling via Drifting ↗arXiv (Cornell University) · no summary yetDeng, Mingyang et al.2026 · 9 citations
- Physically Compatible 3D Object Modeling from a Single Image ↗neural information processing systems · no summary yetMinghao Guo et al.2024 · 6 citations
- Image Generators are Generalist Vision Learners ↗arXiv (Cornell University) · no summary yetValentin Gabeur et al.2026 · 5 citations
- One-step Latent-free Image Generation with Pixel Mean Flows ↗arXiv (Cornell University) · no summary yetYiyang Lu et al.2026 · 5 citations
- Is Noise Conditioning Necessary for Denoising Generative Models? ↗arXiv (Cornell University) · no summary yetQiao Sun et al.2025 · 5 citations
- ELF: Embedded Language Flows ↗arXiv (Cornell University) · no summary yetKeya Hu et al.2026 · 3 citations
- ARC Is a Vision Problem! ↗arXiv (Cornell University) · no summary yetHu, Keya et al.2025 · 3 citations
- Fractal Generative Models ↗arXiv (Cornell University) · no summary yetTianhong Li et al.2025 · 3 citations
- TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes ↗arXiv (Cornell University) · no summary yetMinghao Guo et al.2024 · 3 citations
- GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training ↗arXiv (Cornell University) · no summary yetHaixu Wu et al.2026 · 2 citations
- Diffuse and Disperse: Image Generation with Representation Regularization ↗arXiv (Cornell University) · no summary yetRunqian Wang, Kaiming He2025 · 2 citations
- Bidirectional Normalizing Flow: From Data to Noise and Back ↗arXiv (Cornell University) · no summary yetLu, Yiyang et al.2025 · 2 citations
- Dynamic Inhomogeneous Quantum Resource Scheduling with Reinforcement Learning ↗arXiv (Cornell University) · no summary yetLinsen Li et al.2024 · 1 citation
- Natural Image Pretraining Improves Abstract Reasoning ↗Lecture notes in computer science · no summary yetXiaoman Delores Ding et al.2026
- VISTA: A Visual Harness for Reasoning in an Interactive World ↗arXiv (Cornell University) · no summary yetQiushi Han et al.2026
This page in Markdown → https://md.research.elamur.ai/free/en/authors/kaiming-he/works/