paper-with-me

홈 › Papers

Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks

2017-04-02 · ICCV 2017 10 · Tanmay Gupta, Kevin Shih, Saurabh Singh, Derek Hoiem

An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular, the task of visual recognition is aligned to the task of visual question answering by forcing each to use the same word-region embeddings. We show this leads to greater inductive transfer from recognition to VQA than standard multitask learning. Visual recognition also improves, especially for categories that have relatively few recognition training labels but appear often in the VQA setting. Thus, our paper takes a small step towards creating more general vision systems by showing the benefit of interpretable, flexible, and trainable core representations.

📄 PDF Abstract BibTeX arXiv:1704.00260

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task LearningQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Inductive Document Network Embedding with Topic-Word Attention

2020-01-10 · Robin Brochier, Adrien Guille, Julien Velcin

Document network embedding aims at learning representations for a structured text corpus i.e. when documents are linked to each other. Recent algorithms extend network embedding approaches by incorporating the text conte…

Network Embedding

When Does Perceptual Alignment Benefit Vision Representations?

2024-10-14 · Shobhita Sundaram, Stephanie Fu, Lukas Muttenthaler, Netanel Y. Tamir 외

Humans judge perceptual similarity according to diverse visual attributes, including scene layout, subject location, and camera pose. Existing vision models understand a wide range of semantic abstractions but improperly…

Depth EstimationImage GenerationInductive BiasRetrieval+1

Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks

2020-04-22 · ACL 2020 6 · Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu 외

Text classification is fundamental in natural language processing (NLP), and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word …

ClassificationDocument EmbeddingGeneral ClassificationInductive Learning+2

An Autoencoder Approach to Learning Bilingual Word Representations

2014-02-06 · NeurIPS 2014 12 · Sarath Chandar A P, Stanislas Lauly, Hugo Larochelle, Mitesh M. Khapra 외

Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from paralle…

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

2015-09-24 · Ivan Vulić, Marie-Francine Moens

We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, …

Representation LearningSentenceTranslationWord Embeddings