Papers › Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style

Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style

25 Mar 2023CVPR 2023 1arXiv:2303.14348archive 2025-07-28

Fengyin Lin, Mingkang Li, Da Li, Timothy Hospedales, Yi-Zhe Song, Yonggang Qi

This 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 datasets) of ZS-SBIR with just one network (``everything''), and (ii) we would really like to understand how this sketch-photo matching operates (``explainable''). Our key innovation lies with the realization that such a cross-modal matching problem could be reduced to comparisons of groups of key local patches -- akin to the seasoned ``bag-of-words'' paradigm. Just with this change, we are able to achieve both of the aforementioned goals, with the added benefit of no longer requiring external semantic knowledge. Technically, ours is a transformer-based cross-modal network, with three novel components (i) a self-attention module with a learnable tokenizer to produce visual tokens that correspond to the most informative local regions, (ii) a cross-attention module to compute local correspondences between the visual tokens across two modalities, and finally (iii) a kernel-based relation network to assemble local putative matches and produce an overall similarity metric for a sketch-photo pair. Experiments show ours indeed delivers superior performances across all ZS-SBIR settings. The all important explainable goal is elegantly achieved by visualizing cross-modal token correspondences, and for the first time, via sketch to photo synthesis by universal replacement of all matched photo patches. Code and model are available at https://github.com/buptLinfy/ZSE-SBIR.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

buptlinfy/zse-sbir officialmentioned in papermentioned on GitHubpytorchMITSyntology: 16 samples, 12 ran (2 instrument-failed) · 4 unverified 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

16 samples harvested: 12 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
10ran
4unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from buptlinfy/zse-sbir. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

buptlinfy/zse-sbir official repository 16 samples, 12 ran (2 instrument-failed) · 4 unverified
AddAndNorm model/model.py ran fingerprinted MIT (permissive) · afe81aa89974190e · report fixture: returned AddAndNorm · level recorded 2026-09-22
Encoder in 278 papers model/model.py ran fingerprinted MIT (permissive) · 88b2eaf4a0201422 · report fixture: signature img:Tensor/3/float, mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
Encoder1DBlock model/model.py ran MIT (permissive) · bfdf0d1287b4d60a · report fixture: returned Encoder1DBlock · level recorded 2026-09-22
EncoderLayer in 73 papers model/model.py ran MIT (permissive) · 6d34c0d54b4cd5cc · report fixture: returned EncoderLayer · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
model/model.py ran fingerprinted MIT (permissive) · 9f9b1604d01394b4 · report fixture: returned LayerNorm · level recorded 2026-09-22
MultiHeadDotProductAttention model/model.py ran MIT (permissive) · 31fe7ef87068a002 · report fixture: returned MultiHeadDotProductAttention · level recorded 2026-09-22
MultiHeadedAttention in 38 papers model/model.py ran MIT (permissive) · 8b6a335cd0939a66 · report fixture: returned MultiHeadedAttention · level recorded 2026-09-22
PositionwiseFeedForward in 36 papers model/model.py ran MIT (permissive) · 2d97255bca4d10bc · report fixture: returned PositionwiseFeedForward · level recorded 2026-09-22
Relation_Network model/model.py ran MIT (permissive) · f25396c41187c618 · report fixture: returned Relation_Network · level recorded 2026-09-22
Scale_Embedding model/model.py ran fingerprinted MIT (permissive) · 71497b370f236dea · report fixture: returned Scale_Embedding · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
model/model.py ran · our draft was wrong MIT (permissive) · 3eed1a7a6d48923a · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, dropout:callable/0/?, mask:Tensor/4/float, pos:NoneType/0/? · returned tuple · level recorded 2026-09-22
cos_similar model/model.py ran · our draft was wrong fingerprinted MIT (permissive) · a15a8757a1c2f059 · report fixture: signature p:Tensor/2/float, q:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Cross_Attention model/model.py unverified MIT (permissive) · f1822a4207bad8bd · report
Model in 227 papers model/model.py unverified MIT (permissive) · 36976ee282990c6e · report
Self_Attention model/model.py unverified MIT (permissive) · 83ad54e98125113e · report
ViTPatch model/model.py unverified MIT (permissive) · 5077295b3497cdc4 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Zero-Shot Everything Sketch-Based Image Retrieval (graph method: Zero-Shot Everything Sketch-Based Image Retrieval). 18 bricks; individually on a fixture: 14 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. Model entry · level 0 · unverified · 36976ee282990c6e
  2. Cross_Attention model · level 0 · unverified · f1822a4207bad8bd
  3. Relation_Network helper · level 1 · ran · f25396c41187c618
  4. Self_Attention helper · level 0 · unverified · 83ad54e98125113e
  5. cos_similar helper · level 1 · ran · our draft was wrong · a15a8757a1c2f059
  6. Encoder model · level 1 · ran · 88b2eaf4a0201422
  7. EncoderLayer helper · level 1 · ran · 6d34c0d54b4cd5cc
  8. MultiHeadedAttention helper · level 1 · ran · 8b6a335cd0939a66
  9. PositionwiseFeedForward helper · level 1 · ran · 2d97255bca4d10bc
  10. ViTPatch model · level 0 · unverified · 5077295b3497cdc4
  11. Encoder1DBlock model · level 1 · ran · bfdf0d1287b4d60a
  12. AddAndNorm helper · level 1 · ran · afe81aa89974190e
  13. clones helper · level 1 · ran · our draft was wrong · d2d810cddae9f875
  14. attention helper · level 1 · ran · our draft was wrong · 3eed1a7a6d48923a
  15. Scale_Embedding helper · level 1 · ran · 71497b370f236dea
  16. FeedForward helper · level 1 · ran · 450f5b303bbc3417
  17. MultiHeadDotProductAttention model · level 1 · ran · 31fe7ef87068a002
  18. LayerNorm helper · level 1 · ran · 9f9b1604d01394b4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.14348") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image RetrievalRelation NetworkRetrievalSketch-Based Image Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Concatenated Skip ConnectionSoftmax

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