Visible to the public Biblio

Filters: First Letter Of Title is L  [Clear All Filters]
J. Zhao, C. K. Chang, L. Itti.  2017.  Learning to Recognize Objects by Retaining other Factors of Variation. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA. :1-9.

Most ConvNets formulate object recognition from natural images as a single task classification problem, and attempt to learn features useful for object categories, but invariant to other factors of variation such as pose and illumination. They do not explicitly learn these other factors; instead, they usually discard them by pooling and normalization. Here, we take the opposite approach: we train ConvNets for object recognition by retaining other factors (pose in our case) and learning them jointly with object category. We design a new multi-task leaning (MTL) ConvNet, named disentangling CNN (disCNN), which explicitly enforces the disentangled representations of object identity and pose, and is trained to predict object categories and pose transformations. disCNN achieves significantly better object recognition accuracies than the baseline CNN trained solely to predict object categories on the iLab-20M dataset, a large-scale turntable dataset with detailed pose and lighting information. We further show that the pretrained features on iLab-20M generalize to both Washington RGB-D and ImageNet datasets, and the pretrained disCNN features are significantly better than the pretrained baseline CNN features for fine-tuning on ImageNet.

Venkatesh Saligrama, Manqi Zhao.  2012.  Local Anomaly Detection. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2012, La Palma, Canary Islands, April 21-23, 2012. 22:969–983.
Joseph Wang, Venkatesh Saligrama.  2012.  Local Supervised Learning through Space Partitioning. Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States.. :91–99.
Joseph Wang, Venkatesh Saligrama.  2013.  Locally-Linear Learning Machines (L3M). Asian Conference on Machine Learning, {ACML} 2013, Canberra, ACT, Australia, November 13-15, 2013. 29:451–466.
Joseph Wang, Kirill Trapeznikov, Venkatesh Saligrama.  2014.  An LP for Sequential Learning Under Budgets. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2014, Reykjavik, Iceland, April 22-25, 2014. 33:987–995.
Abhinav Ganesan, Sidharth Jaggi, Venkatesh Saligrama.  2015.  Learning immune-defectives graph through group tests. {IEEE} International Symposium on Information Theory, {ISIT} 2015, Hong Kong, China, June 14-19, 2015. :66–70.
Weicong Ding, Prakash Ishwar, Venkatesh Saligrama.  2015.  Learning shared rankings from mixtures of noisy pairwise comparisons. 2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015. :5446–5450.
Jonathan Root, Jing Qian, Venkatesh Saligrama.  2015.  Learning Efficient Anomaly Detectors from K-NN Graphs. Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2015, San Diego, California, USA, May 9-12, 2015. 38
Abhinav Ganesan, Sidharth Jaggi, Venkatesh Saligrama.  2017.  Learning Immune-Defectives Graph Through Group Tests. {IEEE} Trans. Information Theory. 63:3010–3028.
Jacek Cyranka, Md. Ariful Islam, Greg Byrne, Paul Jones, Scott A. Smolka, Radu Grosu.  2017.  Lagrangian Reachability. International Conference on Computer Aided Verification (CAV 2017). :379–400.
Namaki, M, Chowdhury, F, Islam, M, Doppa, J, Wu, Y.  2017.  Learning to Speed Up Query Planning in Graph Databases. International Conference on Automated Planning and Scheduling.
Marcell Vazquez{-}Chanlatte, Jyotirmoy V. Deshmukh, Xiaoqing Jin, Sanjit A. Seshia.  2017.  Logical Clustering and Learning for Time-Series Data. 29th International Conference on Computer Aided Verification (CAV). :305–325.
Wang, Wei, Yu, Nanpeng.  2016.  LMP decomposition with three-phase DCOPF for distribution system. Innovative Smart Grid Technologies-Asia (ISGT-Asia), 2016 IEEE. :1–8.
Dai, Jin, Lin, Hai.  2015.  Learning-based design of fault-tolerant cooperative multi-agent systems. American Control Conference (ACC), 2015. :1929–1934.
Zhang, Xiaobin, Wu, Bo, Lin, Hai.  2015.  Learning based supervisor synthesis of pomdp for pctl specifications. Decision and Control (CDC), 2015 IEEE 54th Annual Conference on. :7470–7475.