activity
20162026
most citedTowards Transmission-Friendly and Robust CNN Models over Cloud and Device

28 citations · 162 across the 42 of their papers we have counts for

collaborators
Showing 2017Show all

6 papers · 1 filter

cs.CV2017★ 11 cited

Efficient K-Shot Learning with Regularized Deep Networks

Donghyun Yoo, Haoqi Fan, Vishnu Naresh Boddeti +1

Feature representations from pre-trained deep neural networks have been known to exhibit excellent generalization and utility across a variety of related tasks. Fine-tuning is by f…

cs.CV2017

On the Capacity of Face Representation

Sixue Gong, Vishnu Naresh Boddeti, Anil K. Jain

In this paper we address the following question, given a face representation, how many identities can it resolve? In other words, what is the capacity of the face representation? A…

cs.CV2017★ 4 cited

Face Alignment Robust to Pose, Expressions and Occlusions

Vishnu Naresh Boddeti, Myung-Cheol Roh, Jongju Shin +2

We propose an Ensemble of Robust Constrained Local Models for alignment of faces in the presence of significant occlusions and of any unknown pose and expression. To account for pa…

cs.CV2017

Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking

Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distrib…

cs.CV2017

Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

Ryo Yonetani, Vishnu Naresh Boddeti, Kris M. Kitani +1

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers…

cs.LG2017

Emergence of Selective Invariance in Hierarchical Feed Forward Networks

Dipan K. Pal, Vishnu Boddeti, Marios Savvides

Many theories have emerged which investigate how in- variance is generated in hierarchical networks through sim- ple schemes such as max and mean pooling. The restriction to max/me…