pith. machine review for the scientific record. sign in

arxiv: 1806.10348 · v1 · submitted 2018-06-27 · 💻 cs.CL · cs.CV

Recognition: unknown

Learning Visually-Grounded Semantics from Contrastive Adversarial Samples

Authors on Pith no claims yet
classification 💻 cs.CL cs.CV
keywords adversarialsamplesembeddingssemanticsconceptscontrastivedatasetsimage
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.