Estimating the Semantics via Sector Embedding for Image-Text Retrieval
Zheng Wang, Zhenwei Gao, Mengqun Han, Yang Yang, Heng Tao Shen
Abstract
Based on deterministic single-point embedding, most extant image-text retrieval methods only focus on the match of ground truth while suffering from one-to-many correspondence, where besides annotated positives, many similar instances of another modality should be retrieved by a given query. Recent solutions of probabilistic embedding and rectangle mapping still encounter some drawbacks, albeit their promising effectiveness at multiple matches. Meanwhile, the exploration of one-to-many correspondence is still insufficient. Therefore, this paper proposes a novel geometric representation to <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u> stimate the <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</u> emantics of heterogeneous data via <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</u> ector <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u> mbedding (dubbed ESSE). Specifically, a given image/text can be projected as a sector, where its symmetric axis represents mean semantics and the aperture estimates uncertainty. Further, a sector matching loss is introduced to better handle the multiplicity by considering the sine of included angles as distance calculation, which encourages candidates to be contained by the apertures of a query sector. The experimental results on three widely used benchmarks CUB, Flickr30K and MS-COCO reveal that sector embedding can achieve competitive performance on multiple matches and also improve the traditional ground-truth matching of the baselines. Additionally, we also verify the generalization to video-text retrieval on two extensively used datasets of MSRVTT and MSVD, and to text-based person retrieval on CUHK-PEDES. This superiority and effectiveness can also demonstrate that the bounded property of the aperture can better estimate semantic uncertainty when compared to prior remedies.