Timezone: »
The design of neural network architectures is an important component for achieving state-of-the-art performance with machine learning systems across a broad array of tasks. Much work has endeavored to design and build architectures automatically through clever construction of a search space paired with simple learning algorithms. Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks. An open question is the degree to which such methods may generalize to new domains. In this work we explore the construction of meta-learning techniques for dense image prediction focused on the tasks of scene parsing, person-part segmentation, and semantic image segmentation. Constructing viable search spaces in this domain is challenging because of the multi-scale representation of visual information and the necessity to operate on high resolution imagery. Based on a survey of techniques in dense image prediction, we construct a recursive search space and demonstrate that even with efficient random search, we can identify architectures that outperform human-invented architectures and achieve state-of-the-art performance on three dense prediction tasks including 82.7% on Cityscapes (street scene parsing), 71.3% on PASCAL-Person-Part (person-part segmentation), and 87.9% on PASCAL VOC 2012 (semantic image segmentation). Additionally, the resulting architecture is more computationally efficient, requiring half the parameters and half the computational cost as previous state of the art systems.
Author Information
Liang-Chieh Chen (Google Inc.)
Maxwell Collins (Google Inc.)
Yukun Zhu (Google)
George Papandreou (Google)
Barret Zoph (Google Brain)
Florian Schroff (Google Inc., Venice, CA)
Hartwig Adam (Google)
Jonathon Shlens (Google Research)
More from the Same Authors
-
2021 Spotlight: Revisiting ResNets: Improved Training and Scaling Strategies »
Irwan Bello · William Fedus · Xianzhi Du · Ekin Dogus Cubuk · Aravind Srinivas · Tsung-Yi Lin · Jonathon Shlens · Barret Zoph -
2021 : STEP: Segmenting and Tracking Every Pixel »
Mark Weber · Jun Xie · Maxwell Collins · Yukun Zhu · Paul Voigtlaender · Hartwig Adam · Bradley Green · Andreas Geiger · Bastian Leibe · Daniel Cremers · Aljosa Osep · Laura Leal-TaixĂ© · Liang-Chieh Chen -
2022 : Improving Zero-shot Generalization and Robustness of Multi-modal Models »
Yunhao Ge · Jie Ren · Ming-Hsuan Yang · Yuxiao Wang · Andrew Gallagher · Hartwig Adam · Laurent Itti · Balaji Lakshminarayanan · Jiaping Zhao -
2021 Poster: Revisiting ResNets: Improved Training and Scaling Strategies »
Irwan Bello · William Fedus · Xianzhi Du · Ekin Dogus Cubuk · Aravind Srinivas · Tsung-Yi Lin · Jonathon Shlens · Barret Zoph -
2020 Workshop: Self-Supervised Learning -- Theory and Practice »
Pengtao Xie · Shanghang Zhang · Pulkit Agrawal · Ishan Misra · Cynthia Rudin · Abdelrahman Mohamed · Wenzhen Yuan · Barret Zoph · Laurens van der Maaten · Xingyi Yang · Eric Xing -
2020 Poster: RandAugment: Practical Automated Data Augmentation with a Reduced Search Space »
Ekin Dogus Cubuk · Barret Zoph · Jonathon Shlens · Quoc V Le -
2020 Poster: Rethinking Pre-training and Self-training »
Barret Zoph · Golnaz Ghiasi · Tsung-Yi Lin · Yin Cui · Hanxiao Liu · Ekin Dogus Cubuk · Quoc V Le -
2020 Oral: Rethinking Pre-training and Self-training »
Barret Zoph · Golnaz Ghiasi · Tsung-Yi Lin · Yin Cui · Hanxiao Liu · Ekin Dogus Cubuk · Quoc V Le -
2019 Poster: A Fourier Perspective on Model Robustness in Computer Vision »
Dong Yin · Raphael Gontijo Lopes · Jonathon Shlens · Ekin Dogus Cubuk · Justin Gilmer -
2019 Poster: Stand-Alone Self-Attention in Vision Models »
Niki Parmar · Prajit Ramachandran · Ashish Vaswani · Irwan Bello · Anselm Levskaya · Jonathon Shlens -
2017 : Google Lens »
Hartwig Adam -
2017 Demonstration: Electronic Screen Protector with Efficient and Robust Mobile Vision »
HEE JUNG RYU · Florian Schroff -
2013 Poster: DeViSE: A Deep Visual-Semantic Embedding Model »
Andrea Frome · Greg Corrado · Jonathon Shlens · Samy Bengio · Jeff Dean · Marc'Aurelio Ranzato · Tomas Mikolov -
2013 Demonstration: DeViSE: A Deep Visual-Semantic Embedding Model »
Jonathon Shlens · Andrea Frome