Papers › HUSE: Hierarchical Universal Semantic Embeddings

HUSE: Hierarchical Universal Semantic Embeddings

14 Nov 2019arXiv:1911.05978archive 2025-07-28

Pradyumna Narayana, Aniket Pednekar, Abishek Krishnamoorthy, Kazoo Sone, Sugato Basu

There is a recent surge of interest in cross-modal representation learning corresponding to images and text. The main challenge lies in mapping images and text to a shared latent space where the embeddings corresponding to a similar semantic concept lie closer to each other than the embeddings corresponding to different semantic concepts, irrespective of the modality. Ranking losses are commonly used to create such shared latent space -- however, they do not impose any constraints on inter-class relationships resulting in neighboring clusters to be completely unrelated. The works in the domain of visual semantic embeddings address this problem by first constructing a semantic embedding space based on some external knowledge and projecting image embeddings onto this fixed semantic embedding space. These works are confined only to image domain and constraining the embeddings to a fixed space adds additional burden on learning. This paper proposes a novel method, HUSE, to learn cross-modal representation with semantic information. HUSE learns a shared latent space where the distance between any two universal embeddings is similar to the distance between their corresponding class embeddings in the semantic embedding space. HUSE also uses a classification objective with a shared classification layer to make sure that the image and text embeddings are in the same shared latent space. Experiments on UPMC Food-101 show our method outperforms previous state-of-the-art on retrieval, hierarchical precision and classification results.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

1sh1vam/E-commerce-products-classification-using-images-and-text mentioned on GitHubSyntology: not harvested report
AnkushMalaker/HUSE mentioned on GitHubtfSyntology: not harvested report
amanjain1397/HUSE mentioned on GitHubpytorchSyntology: not harvested report
arpytanshu/HUSE-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
gupta-keshav/HUSE-TF mentioned on GitHubtfSyntology: not harvested report
guramritpalsaggu/HUSE-Tensorflow mentioned on GitHubtfSyntology: not harvested report
harshitsinghai77/hierarchical-universal-semantic-embeddings mentioned on GitHubSyntology: not harvested report
vijaynchakole/HUSE-Hierarchical-Universal-Semantic-Embeddings mentioned on GitHubtfSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationRepresentation LearningRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections