SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.05926 · ICCV · 2021

Semantic Diversity Learning for Zero-Shot Multi-label Classification

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 the 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).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2105.05926")
get_code_for_paper("2105.05926")
have("2105.05926")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2105.05926.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2105.05926.svg)](https://syntology.ai/paper/2105.05926)

Connect an agent — have() is free.