Papers › Edge Augmentation for Large-Scale Sketch Recognition without Sketches
Edge Augmentation for Large-Scale Sketch Recognition without Sketches
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.
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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