By Jianwei Yang and Jiasen Lu The following post breaks down Graph R-CNN for Scene Graph Generation, which will be presented at the European Conference on Computer Vision 2018 (ECCV). The conference takes place September 8th through 14th in Munich, Germany. Visual scene understanding has traditionally focused on identifying objects in images -- learning to predict their … Continue reading What is Graph R-CNN?
by Nilaksh Das, PhD student at Georgia Institute of Technology in the School of Computational Science and Engineering. Das is advised by Polo Chau. “SHIELD is a fast and practical approach to defend deep neural networks from adversarial attacks. This work proposes a multifaceted framework which incorporates compression, randomization, model-retraining, and ensembling to make computer vision models robust to adversarial … Continue reading SHIELD: Defending Deep Neural Networks from Adversarial Attacks
“Can machines categorize new things by learning how to group similar things together?” The following describes work by Yen-Chang Hsu, Zhaoyang Lv, and Zsolt Kira, which will be presented at the 2018 International Conference on Learning Representations (ICLR) in Vancouver. Read the paper here. Clustering is the task of partitioning data into groups, so that … Continue reading Learning to Cluster
The following describes work by Ching-An Cheng and Byron Boots, which was awarded Best Paper at the Further details and proofs are available at The 21st International Conference on Artificial Intelligence and Statistics (AISTATS). The paper can be found here: https://arxiv.org/abs/1801.07292. Learning to make sequential decisions is a fundamental topic in designing automatic agents with artificial intelligence. … Continue reading Convergence of Value Aggregation for Imitation Learning
Video understanding tasks such as action recognition and caption generation are crucial for various real-world applications in surveillance, video retrieval, human behavior understanding, etc. In this work, we present a generic recurrent module to detect relationships and interactions between arbitrary object groups for fine-grained video understanding. Our work is applicable to various open domain video … Continue reading From Object Interactions to Fine-grained Video Understanding
A fundamental question in Natural Language Processing (NLP) is how to represent words. If we have a paragraph we want to translate, or a product review we want to determine whether is positive or negative, or a question we want to answer, ultimately the easiest building block to start from is the individual word. The … Continue reading Learning to Represent Words by how They’re Spelled
Georgia Tech's Research Horizons Magazine has done a very nice write-up of the ML@GT center, featuring many of our research projects. Machine learning has been around for decades, but the advent of big data and more powerful computers has increased its impact significantly — moving machine learning beyond pattern recognition and natural language processing into a … Continue reading The Minds of the New Machines | Research Horizons | Georgia Tech’s Research News