Papers › Sketch Me That Shoe

Sketch Me That Shoe

1 Jun 2016CVPR 2016 6archive 2025-07-28

Qian Yu, Feng Liu, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Chen-Change Loy

We investigate the problem of fine-grained sketch-based image retrieval (SBIR), where free-hand human sketches are used as queries to perform instance-level retrieval of images. This is an extremely challenging task because (i) visual comparisons not only need to be fine-grained but also executed cross-domain, (ii) free-hand (finger) sketches are highly abstract, making fine-grained matching harder, and most importantly (iii) annotated cross-domain sketch-photo datasets required for training are scarce, challenging many state-of-the-art machine learning techniques. In this paper, for the first time, we address all these challenges, providing a step towards the capabilities that would underpin a commercial sketch-based image retrieval application. We introduce a new database of 1,432 sketch-photo pairs from two categories with 32,000 fine-grained triplet ranking annotations. We then develop a deep triplet-ranking model for instance-level SBIR with a novel data augmentation and staged pre-training strategy to alleviate the issue of insufficient fine-grained training data. Extensive experiments are carried out to contribute a variety of insights into the challenges of data sufficiency and over-fitting avoidance when training deep networks for fine-grained cross-domain ranking tasks.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationImage RetrievalRetrievalSketch-Based Image Retrieval

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

ShoeV2

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sketch-Based Image Retrieval Chairs Chairs net + R@1 72.2 #3 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs Chairs net + R@10 99.0 #3 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs Shoes net + R@1 65.0 #4 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs Shoes net + R@10 92.8 #4 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs Dense-HOG + rankSVM R@1 52.6 #6 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs Dense-HOG + rankSVM R@10 93.8 #6 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs Sketch-a-Net + rankSVM R@1 47.4 #7 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs Sketch-a-Net + rankSVM R@10 82.5 #7 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs BoW-HOG + rankSVM R@1 28.9 #8 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Chairs BoW-HOG + rankSVM R@10 67.0 #8 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Chairs net + R@1 26.2 #4 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Chairs net + R@10 58.3 #4 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Shoes net + R@1 23.2 #5 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Shoes net + R@10 59.5 #5 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Dense-HOG + rankSVM R@1 15.5 #6 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Dense-HOG + rankSVM R@10 40.5 #6 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Sketch-a-Net + rankSVM R@1 9.5 #7 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags Sketch-a-Net + rankSVM R@10 44.1 #7 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags BoW-HOG + rankSVM R@1 2.4 #8 of 8 Archive leaderboard report
Sketch-Based Image Retrieval Handbags BoW-HOG + rankSVM R@10 10.7 #8 of 8 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.

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