DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Liang-Chieh Chen, G. Papandreou, Iasonas Kokkinos, K. Murphy, A. Yuille
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 2 June 2016
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Liang-Chieh Chen, G. Papandreou, Iasonas Kokkinos, K. Murphy, A. Yuille
- Computer ScienceInternational Conference on Learning…
- 22 December 2014
This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF).
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
- Jonathan Huang, V. Rathod, K. Murphy
- Computer ScienceComputer Vision and Pattern Recognition
- 30 November 2016
A unified implementation of the Faster R-CNN, R-FCN and SSD systems is presented and the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures is traced out.
Progressive Neural Architecture Search
- Chenxi Liu, Barret Zoph, K. Murphy
- Computer ScienceEuropean Conference on Computer Vision
- 2 December 2017
We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary…
Deep Variational Information Bottleneck
- Alexander A. Alemi, Ian S. Fischer, Joshua V. Dillon, K. Murphy
- Computer ScienceInternational Conference on Learning…
- 1 December 2016
It is shown that models trained with the VIB objective outperform those that are trained with other forms of regularization, in terms of generalization performance and robustness to adversarial attack.
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
- Saining Xie, Chen Sun, Jonathan Huang, Z. Tu, K. Murphy
- Computer ScienceEuropean Conference on Computer Vision
- 13 December 2017
It is shown that it is possible to replace many of the 3D convolutions by low-cost 2D convolution, suggesting that temporal representation learning on high-level “semantic” features is more useful.
Generation and Comprehension of Unambiguous Object Descriptions
- Junhua Mao, Jonathan Huang, Alexander Toshev, Oana-Maria Camburu, A. Yuille, K. Murphy
- Computer ScienceComputer Vision and Pattern Recognition
- 7 November 2015
This work proposes a method that can generate an unambiguous description of a specific object or region in an image and which can also comprehend or interpret such an expression to infer which object is being described, and shows that this method outperforms previous methods that generate descriptions of objects without taking into account other potentially ambiguous objects in the scene.
Knowledge vault: a web-scale approach to probabilistic knowledge fusion
- Xin Dong, E. Gabrilovich, Wei Zhang
- Computer ScienceKnowledge Discovery and Data Mining
- 24 August 2014
The Knowledge Vault is a Web-scale probabilistic knowledge base that combines extractions from Web content (obtained via analysis of text, tabular data, page structure, and human annotations) with prior knowledge derived from existing knowledge repositories that computes calibrated probabilities of fact correctness.
A Review of Relational Machine Learning for Knowledge Graphs
- Maximilian Nickel, K. Murphy, Volker Tresp, E. Gabrilovich
- Computer ScienceProceedings of the IEEE
- 2 March 2015
This paper provides a review of how statistical models can be “trained” on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph) and how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web.
NAS-Bench-101: Towards Reproducible Neural Architecture Search
- Chris Ying, Aaron Klein, Esteban Real, Eric Christiansen, K. Murphy, F. Hutter
- Computer ScienceInternational Conference on Machine Learning
- 25 February 2019
This work introduces NAS-Bench-101, the first public architecture dataset for NAS research, which allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the pre-computed dataset.
...
...