paper-with-me

홈 › Papers

Estimating semantic structure for the VQA answer space

2020-06-10 · Corentin Kervadec, Grigory Antipov, Moez Baccouche, Christian Wolf

Since its appearance, Visual Question Answering (VQA, i.e. answering a question posed over an image), has always been treated as a classification problem over a set of predefined answers. Despite its convenience, this classification approach poorly reflects the semantics of the problem limiting the answering to a choice between independent proposals, without taking into account the similarity between them (e.g. equally penalizing for answering cat or German shepherd instead of dog). We address this issue by proposing (1) two measures of proximity between VQA classes, and (2) a corresponding loss which takes into account the estimated proximity. This significantly improves the generalization of VQA models by reducing their language bias. In particular, we show that our approach is completely model-agnostic since it allows consistent improvements with three different VQA models. Finally, by combining our method with a language bias reduction approach, we report SOTA-level performance on the challenging VQAv2-CP dataset.

📄 PDF Abstract BibTeX arXiv:2006.05726

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Taskonomy: Disentangling Task Transfer Learning

2018-04-23 · CVPR 2018 6 · Amir Zamir, Alexander Sax, William Shen, Leonidas Guibas 외

Do visual tasks have a relationship, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answers these questions positively, implying existence of a stru…

Multi-Task LearningTransfer Learning

Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Knowledge-based visual question answering (KVQA) task aims to answer questions that require additional external knowledge as well as an understanding of images and questions. Recent studies on KVQA inject an external kno…

Question AnsweringSemantic SimilaritySemantic Textual SimilarityVisual Question Answering+1

Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base

2022-07-27 · Jinyeong Chae, Jihie Kim

Knowledge-based visual question answering (KVQA) task aims to answer questions that require additional external knowledge as well as an understanding of images and questions. Recent studies on KVQA inject an external kno…

Question AnsweringSemantic SimilaritySemantic Textual SimilarityVisual Question Answering+1

Knowledge Questions from Knowledge Graphs

2016-10-31 · Dominic Seyler, Mohamed Yahya, Klaus Berberich

We address the novel problem of automatically generating quiz-style knowledge questions from a knowledge graph such as DBpedia. Questions of this kind have ample applications, for instance, to educate users about or to e…

Knowledge GraphsMultiple-choice

Latent Space Embedding for Retrieval in Question-Answer Archives

2017-09-01 · EMNLP 2017 9 · Deepak P, Dinesh Garg, Shirish Shevade

Community-driven Question Answering (CQA) systems such as Yahoo! Answers have become valuable sources of reusable information. CQA retrieval enables usage of historical CQA archives to solve new questions posed by users.…

Question AnsweringRetrievalSemantic SimilaritySemantic Textual Similarity+2