Papers › VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search...

VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words

1 Jan 2021ACL 2021 5arXiv:2101.00265archive 2025-07-28

Xiaopeng Lu, Tiancheng Zhao, Kyusong Lee

Text-to-image retrieval is an essential task in cross-modal information retrieval, i.e., retrieving relevant images from a large and unlabelled dataset given textual queries. In this paper, we propose VisualSparta, a novel (Visual-text Sparse Transformer Matching) model that shows significant improvement in terms of both accuracy and efficiency. VisualSparta is capable of outperforming previous state-of-the-art scalable methods in MSCOCO and Flickr30K. We also show that it achieves substantial retrieving speed advantages, i.e., for a 1 million image index, VisualSparta using CPU gets ~391X speedup compared to CPU vector search and ~5.4X speedup compared to vector search with GPU acceleration. Experiments show that this speed advantage even gets bigger for larger datasets because VisualSparta can be efficiently implemented as an inverted index. To the best of our knowledge, VisualSparta is the first transformer-based text-to-image retrieval model that can achieve real-time searching for large-scale datasets, with significant accuracy improvement compared to previous state-of-the-art methods.

PaperPDFConference PDFCode

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

Code

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

Cross-Modal Information RetrievalCross-Modal RetrievalImage RetrievalInformation RetrievalRetrieval

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval COCO 2014 VisualSparta Text-to-image R@1 44.4 #24 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 VisualSparta Text-to-image R@10 82.4 #24 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 VisualSparta Text-to-image R@5 72.8 #24 of 36 Archive leaderboard report
Image Retrieval COCO (Common Objects in Context) VisualSparta QPS 451.4 #2 of 6 Archive leaderboard report
Image Retrieval COCO (Common Objects in Context) VisualSparta Recall@10 96.3 #2 of 6 Archive leaderboard report
Image Retrieval COCO (Common Objects in Context) VisualSparta recall@1 68.2 #2 of 6 Archive leaderboard report
Image Retrieval COCO (Common Objects in Context) VisualSparta recall@5 91.8 #2 of 6 Archive leaderboard report
Image Retrieval Flickr30K 1K test VisualSparta R@1 57.4 #5 of 18 Archive leaderboard report
Image Retrieval Flickr30K 1K test VisualSparta R@10 88.1 #5 of 18 Archive leaderboard report
Image Retrieval Flickr30K 1K test VisualSparta R@5 82.0 #5 of 18 Archive leaderboard report
Image Retrieval Flickr30k VisualSparta QPS 451.4 #9 of 9 Archive leaderboard report
Image Retrieval Flickr30k VisualSparta Recall@1 57.4 #9 of 9 Archive leaderboard report
Image Retrieval Flickr30k VisualSparta Recall@10 88.1 #9 of 9 Archive leaderboard report
Image Retrieval Flickr30k VisualSparta Recall@5 82.0 #9 of 9 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.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxSparse TransformerTransformerWeight Decay

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