Inverting face embeddings with convolutional neural networks.
Andrey Zhmoginov, Mark Sandler: Inverting face embeddings with convolutional neural networks. CoRR abs/1606.04189 (2016)
View ArticleCycleGAN, a Master of Steganography.
Casey Chu, Andrey Zhmoginov, Mark Sandler: CycleGAN, a Master of Steganography. CoRR abs/1712.02950 (2017)
View ArticleThe Power of Sparsity in Convolutional Neural Networks.
Soravit Changpinyo, Mark Sandler, Andrey Zhmoginov: The Power of Sparsity in Convolutional Neural Networks. CoRR abs/1702.06257 (2017)
View ArticleK For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning.
Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew G. Howard: K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning. CoRR abs/1810.10703 (2018)
View ArticleInverted Residuals and Linear Bottlenecks: Mobile Networks for...
Mark Sandler, Andrew G. Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen: Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. CoRR...
View ArticleMobileNetV2: Inverted Residuals and Linear Bottlenecks.
Mark Sandler, Andrew G. Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen: MobileNetV2: Inverted Residuals and Linear Bottlenecks. CVPR 2018: 4510-4520
View ArticleNon-discriminative data or weak model? On the relative importance of data and...
Mark Sandler, Jonathan Baccash, Andrey Zhmoginov, Andrew Howard: Non-discriminative data or weak model? On the relative importance of data and model resolution. CoRR abs/1909.03205 (2019)
View ArticleInformation-Bottleneck Approach to Salient Region Discovery.
Andrey Zhmoginov, Ian Fischer, Mark Sandler: Information-Bottleneck Approach to Salient Region Discovery. CoRR abs/1907.09578 (2019)
View ArticleK for the Price of 1: Parameter-efficient Multi-task and Transfer Learning.
Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew G. Howard: K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning. ICLR (Poster) 2019
View ArticleNon-Discriminative Data or Weak Model? On the Relative Importance of Data and...
Mark Sandler, Jonathan Baccash, Andrey Zhmoginov, Andrew Howard: Non-Discriminative Data or Weak Model? On the Relative Importance of Data and Model Resolution. ICCV Workshops 2019: 1036-1044
View ArticleLarge-Scale Generative Data-Free Distillation.
Liangchen Luo, Mark Sandler, Zi Lin, Andrey Zhmoginov, Andrew Howard: Large-Scale Generative Data-Free Distillation. CoRR abs/2012.05578 (2020)
View ArticleImage segmentation via Cellular Automata.
Mark Sandler, Andrey Zhmoginov, Liangcheng Luo, Alexander Mordvintsev, Ettore Randazzo, Blaise Agüera y Arcas: Image segmentation via Cellular Automata. CoRR abs/2008.04965 (2020)
View ArticleInformation-Bottleneck Approach to Salient Region Discovery.
Andrey Zhmoginov, Ian Fischer, Mark Sandler: Information-Bottleneck Approach to Salient Region Discovery. ECML/PKDD (3) 2020: 531-546
View ArticleCompositional Models: Multi-Task Learning and Knowledge Transfer with Modular...
Andrey Zhmoginov, Dina Bashkirova, Mark Sandler: Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks. CoRR abs/2107.10963 (2021)
View ArticleBasisNet: Two-stage Model Synthesis for Efficient Inference.
Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew G. Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, Adriana Kovashka: BasisNet: Two-stage Model Synthesis for Efficient Inference. CoRR...
View ArticleMeta-Learning Bidirectional Update Rules.
Mark Sandler, Max Vladymyrov, Andrey Zhmoginov, Nolan Miller, Andrew Jackson, Tom Madams, Blaise Agüera y Arcas: Meta-Learning Bidirectional Update Rules. CoRR abs/2104.04657 (2021)
View ArticleMeta-Learning Bidirectional Update Rules.
Mark Sandler, Max Vladymyrov, Andrey Zhmoginov, Nolan Miller, Tom Madams, Andrew Jackson, Blaise Agüera y Arcas: Meta-Learning Bidirectional Update Rules. ICML 2021: 9288-9300
View ArticleBasisNet: Two-Stage Model Synthesis for Efficient Inference.
Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, Adriana Kovashka: BasisNet: Two-Stage Model Synthesis for Efficient Inference. CVPR Workshops...
View ArticleTransformers learn in-context by gradient descent.
Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo, João Sacramento, Alexander Mordvintsev, Andrey Zhmoginov, Max Vladymyrov: Transformers learn in-context by gradient descent. CoRR abs/2212.07677...
View ArticleDecentralized Learning with Multi-Headed Distillation.
Andrey Zhmoginov, Mark Sandler, Nolan Miller, Gus Kristiansen, Max Vladymyrov: Decentralized Learning with Multi-Headed Distillation. CoRR abs/2211.15774 (2022)
View Article