TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Xinyu, Dai, Huangyu, Mao, Lingtao, Zheng, Zexin, Liang, Zihan, Chen, Ben, Lei, Chenyi, Ou, Wenwu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911694313226240
author Sun, Xinyu
Dai, Huangyu
Mao, Lingtao
Zheng, Zexin
Liang, Zihan
Chen, Ben
Lei, Chenyi
Ou, Wenwu
author_facet Sun, Xinyu
Dai, Huangyu
Mao, Lingtao
Zheng, Zexin
Liang, Zihan
Chen, Ben
Lei, Chenyi
Ou, Wenwu
contents E-commerce image search often takes a cropped image as the query, while each candidate is represented by full item images and structured text. This image-to-multimodal retrieval setting presents two asymmetries: a modality disparity -- a visual query must match image--text items, and a granularity disparity -- a cropped query must be compared with full images containing background context and possible distractors. Detection-based pipelines handle the granularity disparity through explicit localization but incur extra cost and error propagation, whereas CLIP-style encoders avoid detection, but are vulnerable to backgrounds or irrelevant items. To address these limitations, we propose TIGER-FG, a text-guided implicit fine-grained grounding framework for image-to-multimodal e-commerce retrieval. TIGER-FG uses item text as semantic guidance to produce target-focused item representations without object detection for retrieval. We further introduce dual distillation objectives that preserve target-region spatial consistency and query--item similarity structure, yielding more stable and discriminative multimodal representations. In addition, we construct ECom-RF-IMMR, a realistic benchmark suite with a 10M-pair training set and two evaluation benchmarks covering standard and cluttered item layouts. TIGER-FG improves Recall@1 over the strongest baseline by 6.1 and 34.4 percentage points on the two evaluation benchmarks, respectively, with only 85.7M query-side parameters and 256-dim embeddings. Results on public e-commerce benchmarks further demonstrate its generalization to noisy and one-to-many retrieval scenarios. Code and data will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18434
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
Sun, Xinyu
Dai, Huangyu
Mao, Lingtao
Zheng, Zexin
Liang, Zihan
Chen, Ben
Lei, Chenyi
Ou, Wenwu
Information Retrieval
Computer Vision and Pattern Recognition
E-commerce image search often takes a cropped image as the query, while each candidate is represented by full item images and structured text. This image-to-multimodal retrieval setting presents two asymmetries: a modality disparity -- a visual query must match image--text items, and a granularity disparity -- a cropped query must be compared with full images containing background context and possible distractors. Detection-based pipelines handle the granularity disparity through explicit localization but incur extra cost and error propagation, whereas CLIP-style encoders avoid detection, but are vulnerable to backgrounds or irrelevant items. To address these limitations, we propose TIGER-FG, a text-guided implicit fine-grained grounding framework for image-to-multimodal e-commerce retrieval. TIGER-FG uses item text as semantic guidance to produce target-focused item representations without object detection for retrieval. We further introduce dual distillation objectives that preserve target-region spatial consistency and query--item similarity structure, yielding more stable and discriminative multimodal representations. In addition, we construct ECom-RF-IMMR, a realistic benchmark suite with a 10M-pair training set and two evaluation benchmarks covering standard and cluttered item layouts. TIGER-FG improves Recall@1 over the strongest baseline by 6.1 and 34.4 percentage points on the two evaluation benchmarks, respectively, with only 85.7M query-side parameters and 256-dim embeddings. Results on public e-commerce benchmarks further demonstrate its generalization to noisy and one-to-many retrieval scenarios. Code and data will be released.
title TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval
topic Information Retrieval
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.18434