Browse State-of-the-Art › Sketch-Based Image Retrieval
Sketch-Based Image Retrieval
40 papers with code · 3 benchmarks · 4 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Chairs (8 rows) | EdgeMAC + whitening | Deep Shape Matching | code | — | Compare |
| Handbags (8 rows) | EdgeMAC + whitening | Deep Shape Matching | code | — | Compare |
| Shoes (1 row) | EdgeMAC + whitening | Deep Shape Matching | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
4 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Most implemented papers archive 2025-07-28
30 shown of 40 papers with code (110 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling17 Jun 2024 2 repositories listedFine-Grained Sketch-Based Image Retrieval (FG-SBIR) aims to minimize the distance between sketches and corresponding images in the embedding space.
-
8 Dec 2020 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)Grounded in information theory, we cast the simultaneous learning of domain-invariant and domain-specific representations as a joint objective of multiple information constraints, which does not require adversarial…
-
11 Sep 2017 2 repositories listedWe cast shape matching as metric learning with convolutional networks.
-
12 Feb 2025 1 repository listedFurther, as a solution to this problem, we propose a pretrained multimodal transformer-based baseline, STNET (Sketch+Text Network), that uses a hand-drawn sketch to localize relevant objects in the natural scene image,…
-
5 Jul 2024 1 repository listedSpLIP implements a bi-directional prompt-sharing strategy that enables mutual knowledge exchange between CLIP's visual and textual encoders, fostering a more cohesive and synergistic prompt processing mechanism that…
-
12 Mar 2024 1 repository listedThis paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI.
-
10 Jan 2024 1 repository listedZero-shot learning offers an efficient solution for a machine learning model to treat unseen categories, avoiding exhaustive data collection.
-
16 Dec 2023 1 repository listedIn this paper, we propose a novel Symmetrical Bidirectional Knowledge Alignment for zero-shot sketch-based image retrieval (SBKA).
-
5 Apr 2023 1 repository listedTo our knowledge, this is the first publicly available instance-level logo sketch dataset.
-
25 Mar 2023 1 repository listed Syntology ran 12 of 16 samples · 4 unverifiedThis paper studies the problem of zero-short sketch-based image retrieval (ZS-SBIR), however with two significant differentiators to prior art (i) we tackle all variants (inter-category, intra-category, and cross…
-
14 Mar 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverifiedFor the first time, we identify that for data-scarce tasks like Sketch-Based Image Retrieval (SBIR), where the difficulty in acquiring paired photos and hand-drawn sketches limits data-dependent cross-modal learning…
-
1 Jan 2023 1 repository listedThis lack of sketch data has imposed on the community a few "peculiar" design choices -- the most representative of them all is perhaps the coerced utilisation of photo-based pre-training (i.
-
19 Oct 2022 1 repository listedRepresentation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information.
-
19 Aug 2022 1 repository listedImage retrieval under generalized test scenarios has gained significant momentum in literature, and the recently proposed protocol of Universal Cross-domain Retrieval is a pioneer in this direction.
-
27 Jul 2022 1 repository listed Syntology ran 10 of 16 samples · 6 unverified · 16 pointer-only (licence)Toward equipping machines with such capabilities, we propose the Primitive-based Sketch Abstraction task where the goal is to represent sketches using a fixed set of drawing primitives under the influence of a budget.
-
4 Jul 2022 1 repository listedTo solve this new problem, we introduce a novel model-agnostic meta-learning (MAML) based framework with several key modifications: (1) As a retrieval task with a margin-based contrastive loss, we simplify the MAML…
-
28 Mar 2022 1 repository listedWe first conducted a pilot study that revealed the secret lies in the existence of noisy strokes, but not so much of the "I can't sketch".
-
15 Dec 2021 1 repository listedBy combining two fundamental learning approaches in DML, e.
-
21 Nov 2021 1 repository listedFine-Grained Sketch-Based Image Retrieval (FG-SBIR) aims at finding a specific image from a large gallery given a query sketch.
-
22 Jun 2021 1 repository listedMost existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and…
-
15 Jun 2021 1 repository listedWe present an algorithm for searching image collections using free-hand sketches that describe the appearance and relative positions of multiple objects.
-
More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval25 Mar 2021 1 repository listedA fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs.
-
14 Aug 2020 1 repository listedWe refer to this problem as sketch-guided object localization.
-
29 Jul 2020 1 repository listedIn this paper, we study a further trait of sketches that has been overlooked to date, that is, they are hierarchical in terms of the levels of detail -- a person typically sketches up to various extents of detail to…
-
1 Jun 2020 1 repository listedFine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a particular photo instance given a user's query sketch.
-
24 Feb 2020 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)Sketchformer is a novel transformer-based representation for encoding free-hand sketches input in a vector form, i.
-
24 Feb 2020 1 repository listedFine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a particular photo instance given a user's query sketch.
-
18 Sep 2019 1 repository listed Syntology ran 4 of 11 samples · 7 unverifiedHumans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details.
-
27 Aug 2019 1 repository listedHistorical watermark recognition is a highly practical, yet unsolved challenge for archivists and historians.
-
6 Apr 2019 1 repository listedHighly abstract amateur human sketches are purposefully sourced to maximize the domain gap, instead of ones included in existing datasets that can often be semi-photorealistic.
Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.
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