Papers › Edge Augmentation for Large-Scale Sketch Recognition without Sketches

Edge Augmentation for Large-Scale Sketch Recognition without Sketches

26 Feb 2022arXiv:2202.13164archive 2025-07-28

Nikos Efthymiadis, Giorgos Tolias, Ondrej Chum

This work addresses scaling up the sketch classification task into a large number of categories. Collecting sketches for training is a slow and tedious process that has so far precluded any attempts to large-scale sketch recognition. We overcome the lack of training sketch data by exploiting labeled collections of natural images that are easier to obtain. To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images. Randomization is introduced in the parameters of edge detection and edge selection. Natural images are translated to a pseudo-novel domain called "randomized Binary Thin Edges" (rBTE), which is used as a training domain instead of natural images. The ability to scale up is demonstrated by training CNN-based sketch recognition of more than 2.5 times larger number of categories than used previously. For this purpose, a dataset of natural images from 874 categories is constructed by combining a number of popular computer vision datasets. The categories are selected to be suitable for sketch recognition. To estimate the performance, a subset of 393 categories with sketches is also collected.

PaperPDFCode

Code

nikosefth/im2rbte officialmentioned in papermentioned on GitHubpytorch report

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

Edge DetectionImage to sketch recognitionSketch Recognition

Datasets

Introduced by this paper, per the archive.

Im4Sketch

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image to sketch recognition Im4Sketch rBTE (ResNet101) Accuracy 11.3 #1 of 2 Archive leaderboard report
Image to sketch recognition Im4Sketch ResNet101 Accuracy 5.3 #2 of 2 Archive leaderboard report
Image to sketch recognition PACS rBTE (ResNet18) Accuracy 70.6 #2 of 7 Archive leaderboard report
Image to sketch recognition Sketchy rBTE (ResNet101) Accuracy 57.2 #1 of 2 Archive leaderboard report
Image to sketch recognition Sketchy ResNet101 Accuracy 11.4 #2 of 2 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