Filter by Research Area
Filter by Research Area
Year Published

110 Results

April 30, 2018

The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings

International Conference on Learning Representations (ICLR)

We discuss the feasibility of the following learning problem: given unmatched samples from two domains and nothing else, learn a mapping between the two, which preserves semantics. Due to the lack of paired samples and without any definition of the semantic information, the problem might seem ill-posed.

By: Tomer Galanti, Lior Wolf, Sagie Benaim
April 30, 2018

Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks

International Conference on Learning Representations (ICLR)

We consider the problem of detecting out-of-distribution images in neural networks. We propose ODIN, a simple and effective method that does…

By: Shiyu Liang, Yixuan Li, R. Srikant
April 30, 2018

Emergent Translation in Multi-Agent Communication

International Conference on Learning Representations (ICLR)

In this work, we propose a communication game where two agents, native speakers of their own respective languages, jointly learn to solve a visual referential task. We find that the ability to understand and translate a foreign language emerges as a means to achieve shared goals.

By: Jason Lee, Kyunghyun Cho, Jason Weston, Douwe Kiela
April 15, 2018

Towards End-to-End Spoken Language Understanding

International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018)

Spoken language understanding system is traditionally designed as a pipeline of a number of components.

By: Dmitriy Serdyuk, Yongqiang Wang, Christian Fuegen, Anuj Kumar, Baiyang Liu, Yoshua Bengio
March 8, 2018

Generative Street Addresses from Satellite Imagery

ISPRS International Journal of Geo-Information

We describe our automatic generative algorithm to create street addresses from satellite images by learning and labeling roads, regions, and address cells. Currently, 75% of the world’s roads lack adequate street addressing systems. Recent geocoding initiatives tend to convert pure latitude and longitude information into a memorable form for unknown areas. However, settlements are identified by streets, and such addressing schemes are not coherent with the road topology.

By: Ilke Demir, Forest Hughes, Aman Raj, Kaunil Dhruv, Suryanarayana Murthy Muddala, Sanyam Garg, Barrett Doo, Ramesh Raskar
December 15, 2017

Mapping the world population one building at a time

ArXive

Here, we present a computer vision method based on machine learning to create population maps from satellite imagery at a global scale, with a spatial sensitivity corresponding to individual buildings and suitable for global deployment.

By: Tobias Tiecke, Xianming Liu, Amy Zhang, Andreas Gros, Nan Li, Gregory Yetman, Talip Kilic, Siobhan Murray
July 21, 2017

Link the head to the “beak”: Zero Shot Learning from Noisy Text Description at Part Precision

CVPR 2017

In this paper, we study learning visual classifiers from unstructured text descriptions at part precision with no training images. We propose a learning framework that is able to connect text terms to its relevant parts and suppress connections to non-visual text terms without any part-text annotations. F

By: Mohamed Elhoseiny, Yizhe Zhu, Han Zhang, Ahmed Elgammal
July 21, 2017

Relationship Proposal Networks

Conference on Computer Vision and Pattern Recognition 2017

In this paper we address the challenges of image scene object recognition by using pairs of related regions in images to train a relationship proposer that at test time produces a manageable number of related regions.

By: Ji Zhang, Mohamed Elhoseiny, Scott Cohen, Walter Chang, Ahmed Elgammal
May 21, 2017

CAN: Creative Adversarial Networks

IEEE International Conference on Communications (ICCC)

We propose a new system for generating art. The system generates art by looking at art and learning about style; and becomes creative by increasing the arousal potential of the generated art by deviating from the learned styles. We build over Generative Adversarial Networks (GAN), which have shown the ability to learn to generate novel images simulating a given distribution.

By: Ahmed Elgammal, Bingchen Liu, Mohamed Elhoseiny, Marian Mazzone
May 16, 2017

Cultural Diffusion and Trends in Facebook Photographs

The International AAAI Conference on Web and Social Media (ICWSM)

Online social media is a social vehicle in which people share various moments of their lives with their friends, such as playing sports, cooking dinner or just taking a selfie for fun, via visual means, i.e., photographs. Our study takes a closer look at the popular visual concepts illustrating various cultural lifestyles from aggregated, de-identified photographs.

By: Quenzeng You, Dario Garcia, Manohar Paluri, Jiebo Luo, Jungseock Joo