Papers › Semantic Diversity Learning for Zero-Shot Multi-label Classification

Semantic Diversity Learning for Zero-Shot Multi-label Classification

12 May 2021ICCV 2021 10arXiv:2105.05926archive 2025-07-28

Avi Ben-Cohen, Nadav Zamir, Emanuel Ben Baruch, Itamar Friedman, Lihi Zelnik-Manor

Training a neural network model for recognizing multiple labels associated with an image, including identifying unseen labels, is challenging, especially for images that portray numerous semantically diverse labels. As challenging as this task is, it is an essential task to tackle since it represents many real-world cases, such as image retrieval of natural images. We argue that using a single embedding vector to represent an image, as commonly practiced, is not sufficient to rank both relevant seen and unseen labels accurately. This study introduces an end-to-end model training for multi-label zero-shot learning that supports semantic diversity of the images and labels. We propose to use an embedding matrix having principal embedding vectors trained using a tailored loss function. In addition, during training, we suggest up-weighting in the loss function image samples presenting higher semantic diversity to encourage the diversity of the embedding matrix. Extensive experiments show that our proposed method improves the zero-shot model's quality in tag-based image retrieval achieving SoTA results on several common datasets (NUS-Wide, COCO, Open Images).

PaperPDFConference PDFCode

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

Code

Alibaba-MIIL/ZS_SDL officialmentioned on GitHubpytorch 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

ClassificationDiversityImage RetrievalMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationMulti-label zero-shot learningRetrievalTAGZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-label zero-shot learning NUS-WIDE SDL mAP 25.9 #7 of 10 Archive leaderboard report
Multi-label zero-shot learning Open Images V4 ZS-SDL MAP 62.9 #3 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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