# HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs

Source: [HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs](<https://www.sota2.com/research/paper/68fa66b31e209131cea11f6c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:57:21.263Z

Authors: Fangyu Liu, Rongtian Ye, Xun Wang, Shuaipeng Li

Published: 2019-11-22T15:51:08.000Z

## Abstract

The hubness problem widely exists in high-dimensional embedding space and is a fundamental source of error for cross-modal matching tasks. In this work, we study the emergence of hubs in Visual Semantic Embeddings (VSE) with application to text-image matching. We analyze the pros and cons of two widely adopted optimization objectives for training VSE and propose a novel hubness-aware loss function (HAL) that addresses previous methods' defects. Unlike (Faghri et al.2018) which simply takes the hardest sample within a mini-batch, HAL takes all samples into account, using both local and global statistics to scale up the weights of "hubs". We experiment our method with various configurations of model architectures and datasets. The method exhibits exceptionally good robustness and brings consistent improvement on the task of text-image matching across all settings. Specifically, under the same model architectures as (Faghri et al. 2018) and (Lee at al. 2018), by switching only the learning objective, we report a maximum R@1improvement of 7.4% on MS-COCO and 8.3% on Flickr30k.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1911.10097>)

[PDF](<https://arxiv.org/pdf/1911.10097.pdf>)