paper-with-me

홈 › Papers

Learning Visually-Grounded Semantics from Contrastive Adversarial Samples

2018-06-27 · COLING 2018 8 · Haoyue Shi, Jiayuan Mao, Tete Xiao, Yuning Jiang, Jian Sun

We study the problem of grounding distributional representations of texts on the visual domain, namely visual-semantic embeddings (VSE for short). Begin with an insightful adversarial attack on VSE embeddings, we show the limitation of current frameworks and image-text datasets (e.g., MS-COCO) both quantitatively and qualitatively. The large gap between the number of possible constitutions of real-world semantics and the size of parallel data, to a large extent, restricts the model to establish the link between textual semantics and visual concepts. We alleviate this problem by augmenting the MS-COCO image captioning datasets with textual contrastive adversarial samples. These samples are synthesized using linguistic rules and the WordNet knowledge base. The construction procedure is both syntax- and semantics-aware. The samples enforce the model to ground learned embeddings to concrete concepts within the image. This simple but powerful technique brings a noticeable improvement over the baselines on a diverse set of downstream tasks, in addition to defending known-type adversarial attacks. We release the codes at https://github.com/ExplorerFreda/VSE-C.

📄 PDF Abstract BibTeX arXiv:1806.10348

Code (1)

ExplorerFreda/VSE-C 공식 구현 pytorch

Tasks

Adversarial AttackImage Captioning

Similar Papers 제목 키워드 기반

Explainable Semantic Space by Grounding Language to Vision with Cross-Modal Contrastive Learning

2021-11-13 · NeurIPS 2021 12 · Yizhen Zhang, Minkyu Choi, Kuan Han, Zhongming Liu

In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical…

Contrastive LearningImage RetrievalLanguage ModelingLanguage Modelling+1

FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering

2023-03-19 · Weizhe Lin, Zhilin Wang, Bill Byrne

The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the ori…

Common Sense ReasoningInformation RetrievalKnowledge GraphsQuestion Answering+3

Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes

2015-11-22 · CVPR 2016 6 · Satwik Kottur, Ramakrishna Vedantam, José M. F. Moura, Devi Parikh

We propose a model to learn visually grounded word embeddings (vis-w2v) to capture visual notions of semantic relatedness. While word embeddings trained using text have been extremely successful, they cannot uncover noti…

Common Sense ReasoningImage RetrievalRetrievalVisual Grounding+1

Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs

2026-01-20 · Yujin Jo, Sangyoon Bae, Taesup Kim arxiv

Hallucinations in large vision--language models (LVLMs) often arise when language priors dominate over visual evidence, leading to object misidentification and visually inconsistent descriptions. We address this problem …

Support-set bottlenecks for video-text representation learning

2020-10-06 · ICLR 2021 1 · Mandela Patrick, Po-Yao Huang, Yuki Asano, Florian Metze 외

The dominant paradigm for learning video-text representations -- noise contrastive learning -- increases the similarity of the representations of pairs of samples that are known to be related, such as text and video from…

Contrastive LearningRepresentation LearningRetrievalText to Video Retrieval+1