Research Area
Year Published

631 Results

September 4, 2018

Mass Displacement Networks

British Machine Vision Convention (BMVC)

Despite the large improvements in performance attained by deep learning in computer vision, one can often further improve results with some additional post-processing that exploits the geometric nature of the underlying task. This commonly involves displacing the posterior distribution of a CNN in a way that makes it more appropriate for the task at hand, e.g. better aligned with local image features, or more compact. In this work we integrate this geometric post-processing within a deep architecture, introducing a differentiable and probabilistically sound counterpart to the common geometric voting technique used for evidence accumulation in vision.

By: Natalia Neverova, Iasonas Kokkinos
September 4, 2018

Self-Supervised Feature Learning for Semantic Segmentation of Overhead Imagery

British Machine Vision Convention (BMVC)

In this work, we study various self-supervised feature learning techniques for semantic segmentation of overhead imageries.

By: Suriya Singh, Anil Batra, Guan Pang, Lorenzo Torresani, Saikat Basu, Manohar Paluri, C.V. Jawahar
September 3, 2018

ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases

European Conference on Computer Vision (ECCV)

ConvNets and ImageNet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversarial examples and their tendency to exhibit undesirable biases question the reliability of these methods. This work investigates these questions from the perspective of the end-user by using human subject studies and explanations.

By: Pierre Stock, Moustapha Cisse
September 3, 2018

QuaterNet: A Quaternion-based Recurrent Model for Human Motion

British Machine Vision Convention (BMVC)

Deep learning for predicting or generating 3D human pose sequences is an active research area. Previous work regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angle or exponential map parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations.

By: Dario Pavllo, David Grangier, Michael Auli
August 27, 2018

Providing Streaming Joins as a Service at Facebook

International Conference on Very Large Data Bases (VLDB)

This paper describes an end-to-end streaming join service that addresses the challenges above through a streaming join operator that uses an adaptive stream synchronization algorithm that is able to handle the different distributions we observe in real-world streams regarding their event times.

By: Gabriela Jacques da Silva, Ran Lei, Luwei Cheng, Guoqiang Jerry Chen, Kuen Ching, Tanji Hu, Yuan Mei, Kevin Wilfong, Rithin Shetty, Serhat Yilmaz, Anirban Banerjee, Benjamin Heintz, Shridhar Iyer, Anshul Jaiswal
August 26, 2018

Rosetta: Large Scale System for Text Detection and Recognition in Images

Knowledge Discovery in Databases (KDD)

In this paper we present a deployed, scalable optical character recognition (OCR) system, which we call Rosetta, designed to process images uploaded daily at Facebook scale.

By: Fedor Borisyuk, Albert Gordo, Viswanath Sivakumar
August 26, 2018

Designing Variable Stiffness Profiles To Optimize The Physical Human Robot Interface Of Hand Exoskeletons

The 7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics

The design of comfortable and effective physical human robot interaction (pHRI) interfaces for force transfer is a prominent challenge for coupled human-robot systems. Forces applied by the robot at the fingers create reaction forces on the dorsal surface of the hand, often leading to high pressure concentrations which can cause pain and discomfort. In this paper, the interaction between the pHRI interface and the dorsal surface of the hand is systematically characterized, and a new method for the design of comfortable interfaces is presented.

By: Rohit John Varghese, Gaurav Mukherjee, Raymond King, Sean Keller, Ashish D. Deshpande
August 22, 2018

FBOSS: Building Switch Software at Scale


We present FBOSS, our own data center switch software, that is designed with the basis on our switch-as-a-server and deploy-early-and-iterate principles.

By: Sean Choi, Boris Burkov, Alex Eckert, Tian Fang, Saman Kazemkhani, Rob Sherwood, Ying Zhang, James Hongyi Zeng
August 21, 2018

SE-Sync: A certifiably correct algorithm for synchronization over the special Euclidean group

International Journal of Robotics Research

Many important geometric estimation problems naturally take the form of synchronization over the special Euclidean group: estimate the values of a set of unknown group elements x1, . . . , xn ∈ SE(d) given noisy measurements of a subset of their pairwise relative transforms xi−1xj. Examples of this class include the foundational problems of pose-graph simultaneous localization and mapping (SLAM) (in robotics), camera motion estimation (in computer vision), and sensor network localization (in distributed sensing), among others. This inference problem is typically formulated as a nonconvex maximum-likelihood estimation that is computationally hard to solve in general. Nevertheless, in this paper we present an algorithm that is able to efficiently recover certifiably globally optimal solutions of the special Euclidean synchronization problem in a non-adversarial noise regime.

By: David M. Rosen, Luca Carlone, Afonso S. Bandeira, John J. Leonard
August 20, 2018

TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering

Knowledge Discovery in Databases (KDD)

In this paper, we propose a method for constructing topic taxonomies, wherein every node represents a conceptual topic and is defined as a cluster of semantically coherent concept terms.

By: Chao Zhang, Fangbo Tao, Xiusi Chen, Jiaming Shen, Meng Jiang, Brian Sadler, Michelle Vanni, Jiawei Han