Research Area
Year Published

653 Results

June 19, 2018

A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts

Computer Vision and Pattern Recognition (CVPR)

Most existing zero-shot learning methods consider the problem as a visual semantic embedding one. Given the demonstrated capability of Generative Adversarial Networks (GANs) to generate images, we instead leverage GANs to imagine unseen categories from text descriptions and hence recognize novel classes with no examples being seen.

By: Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng, Ahmed Elgammal

June 18, 2018

Don’t Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

Computer Vision and Pattern Recognition (CVPR)

A number of studies have found that today’s Visual Question Answering (VQA) models are heavily driven by superficial correlations in the training data and lack sufficient image grounding. To encourage development of models geared towards the latter, we propose a new setting for VQA where for every question type, train and test sets have different prior distributions of answers.

By: Aishwarya Agrawal, Dhruv Batra, Devi Parikh, Aniruddha Kembhavi

June 18, 2018

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

CVPR Workshop - DeepGlobe 2018

Similar to other challenges in computer vision domain such as DAVIS[21] and COCO[33], DeepGlobe proposes three datasets and corresponding evaluation methodologies, coherently bundled in three competitions with a dedicated workshop co-located with CVPR 2018.

By: Ilke Demir, Krzysztof Koperski, David Lindenbaum, Guan Pang, Jing Huang, Saikat Basu, Forest Hughes, Devis Tuia, Ramesh Raskar

June 18, 2018

Separating Self-Expression and Visual Content in Hashtag Supervision

Computer Vision and Pattern Recognition (CVPR)

This paper presents an approach that extends upon modeling simple image-label pairs with a joint model of images, hashtags, and users. We demonstrate the efficacy of such approaches in image tagging and retrieval experiments, and show how the joint model can be used to perform user-conditional retrieval and tagging.

By: Andreas Veit, Maximilian Nickel, Serge Belongie, Laurens van der Maaten

June 18, 2018

Canonical Tensor Decomposition for Knowledge Base Completion

International Conference on Machine Learning (ICML)

The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem. In this light, the Canonical Tensor Decomposition (CP) (Hitchcock, 1927) seems like a natural solution. However, current implementations of CP on standard Knowledge Base Completion benchmarks are lagging behind their competitors. In this work, we attempt to understand the limits of CP for knowledge base completion.

By: Timothée Lacroix, Nicolas Usunier, Guillaume Obozinski

June 18, 2018

Low-Shot Learning from Imaginary Data

Computer Vision and Pattern Recognition (CVPR)

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea.

By: Yu-Xiong Wang, Ross Girshick, Martial Hebert, Bharath Hariharan

June 18, 2018

Low-shot learning with large-scale diffusion

Computer Vision and Pattern Recognition (CVPR)

This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time.

By: Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou

June 18, 2018

Learning by Asking Questions

Computer Vision and Pattern Recognition (CVPR)

We introduce an interactive learning framework for the development and testing of intelligent visual systems, called learning-by-asking (LBA). We explore LBA in context of the Visual Question Answering (VQA) task.

By: Ishan Misra, Ross Girshick, Rob Fergus, Martial Hebert, Abhinav Gupta, Laurens van der Maaten

June 18, 2018

Learning to Segment Every Thing

Computer Vision and Pattern Recognition (CVPR)

The goal of this paper is to propose a new partially supervised training paradigm, together with a novel weight transfer function, that enables training instance segmentation models on a large set of categories all of which have box annotations, but only a small fraction of which have mask annotations.

By: Ronghang Hu, Piotr Dollar, Kaiming He, Trevor Darrell, Ross Girshick

June 18, 2018

Stacked Latent Attention for Multimodal Reasoning

Computer Vision and Pattern Recognition (CVPR)

Attention has shown to be a pivotal development in deep learning and has been used for a multitude of multimodal learning tasks such as visual question answering and image captioning. In this work, we pinpoint the potential limitations to the design of a traditional attention model.

By: Haoqi Fan, Jiatong Zhou