Papers › Bridging the Gap Between End-to-End and Two-Step Text Spotting

Bridging the Gap Between End-to-End and Two-Step Text Spotting

6 Apr 2024CVPR 2024 1arXiv:2404.04624archive 2025-07-28

Mingxin Huang, Hongliang Li, Yuliang Liu, Xiang Bai, Lianwen Jin

Modularity plays a crucial role in the development and maintenance of complex systems. While end-to-end text spotting efficiently mitigates the issues of error accumulation and sub-optimal performance seen in traditional two-step methodologies, the two-step methods continue to be favored in many competitions and practical settings due to their superior modularity. In this paper, we introduce Bridging Text Spotting, a novel approach that resolves the error accumulation and suboptimal performance issues in two-step methods while retaining modularity. To achieve this, we adopt a well-trained detector and recognizer that are developed and trained independently and then lock their parameters to preserve their already acquired capabilities. Subsequently, we introduce a Bridge that connects the locked detector and recognizer through a zero-initialized neural network. This zero-initialized neural network, initialized with weights set to zeros, ensures seamless integration of the large receptive field features in detection into the locked recognizer. Furthermore, since the fixed detector and recognizer cannot naturally acquire end-to-end optimization features, we adopt the Adapter to facilitate their efficient learning of these features. We demonstrate the effectiveness of the proposed method through extensive experiments: Connecting the latest detector and recognizer through Bridging Text Spotting, we achieved an accuracy of 83.3% on Total-Text, 69.8% on CTW1500, and 89.5% on ICDAR 2015. The code is available at https://github.com/mxin262/Bridging-Text-Spotting.

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 37 code samples: 36 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 37: 27 ran (of which 5 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 8 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 30 samples from 3 repositories, 21 ran (14 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

mxin262/bridging-text-spotting officialmentioned in papermentioned on GitHubpytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
husterpzh/pssr mentioned on GitHubpytorchSyntology: 14 samples, 10 ran (0 instrument-failed) · 4 unverified report
mxin262/estextspotter mentioned on GitHubpytorchSyntology: 8 samples, 6 ran (3 instrument-failed) · 2 unverified report
mxin262/swintextspotter mentioned on GitHubpytorchSyntology: 8 samples, 5 ran (4 instrument-failed) · 3 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

37 samples harvested: 27 ran (of which 5 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 8 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
6ran · our draft was wrong
2ran; the contract check could not run
17ran
10unverified

Licence: 23 of the 37 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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 3 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.

mxin262/bridging-text-spotting official repository 6 samples, 5 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
adet/modeling/bridge.py ran · metamorphic tier: deterministic licence not identified · pointer only · f07a7b5124daa4d3 · report fixture: returned Attention · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
adet/modeling/bridge.py ran licence not identified · pointer only · 5ad9f4a5115fc2c9 · report fixture: signature x:Tensor/3/float, att_mask:NoneType/0/?, return_attn_map:bool/0/bool · returned Tensor · level recorded 2026-09-24
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
adet/modeling/bridge.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 7d9a8a01e3d8b2af · report fixture: returned DropPath · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
adet/modeling/bridge.py ran · metamorphic tier: deterministic licence not identified · pointer only · 36ec904c3b4e4e27 · report fixture: returned PatchEmbed · level recorded 2026-09-22
get_sinusoid_encoding_table in 51 papers adet/modeling/bridge.py ran · honoured contract fingerprinted licence not identified · pointer only · e270b1e0375e984c · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-22
Bridge adet/modeling/bridge.py unverified licence not identified · pointer only · 179df4b05daa85e4 · report
husterpzh/pssr community (archive-listed) 14 samples, 10 ran (0 instrument-failed) · 4 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model.py ran fingerprinted Apache-2.0 (permissive) · a55e20272adb06c8 · report fixture: signature batch_H:Tensor/3/float, text:Tensor/2/int, is_train:bool/0/bool, batch_max_length:int/0/int · returned Tensor · level recorded 2026-09-24
AttentionCell model.py ran Apache-2.0 (permissive) · 87ec0a6342858e38 · report fixture: signature prev_hidden:tuple/1/Tensor, batch_H:Tensor/3/float, char_onehots:Tensor/2/float · returned tuple · level recorded 2026-09-24
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
model.py ran fingerprinted Apache-2.0 (permissive) · a06d957836eecfd1 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
BidirectionalLSTM model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 0a490b941ecc0d0b · report fixture: signature input:Tensor/3/float · returned Tensor · level recorded 2026-09-22
GRCL model.py ran fingerprinted Apache-2.0 (permissive) · ad2aab77e017ae44 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
GRCL_unit model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 2d06924d44e4a05f · report fixture: signature wgf_u:Tensor/4/float, wgr_x:Tensor/4/float, wf_u:Tensor/4/float, wr_x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
GridGenerator model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 345b61e3a6a59f12 · report fixture: signature batch_C_prime:Tensor/3/float · returned Tensor · level recorded 2026-09-22
LocalizationNetwork model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · e3f116bb52340904 · report fixture: signature batch_I:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ResNet in 139 papers model.py ran Apache-2.0 (permissive) · f0555475dca7332a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
VGG_FeatureExtractor model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 2ac69ad6b536be49 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Model in 227 papers model.py unverified Apache-2.0 (permissive) · e3d0360e5fe8ab89 · report
RCNN_FeatureExtractor model.py unverified Apache-2.0 (permissive) · ef5e9a2a130e79ff · report
ResNet_FeatureExtractor model.py unverified Apache-2.0 (permissive) · 5a4873d904275392 · report
TPS_SpatialTransformerNetwork model.py unverified Apache-2.0 (permissive) · 6717e6516dabf3ca · report
mxin262/estextspotter community (archive-listed) 8 samples, 6 ran (3 instrument-failed) · 2 unverified
MLP in 375 papers models/ests/ests.py ran · metamorphic tier: deterministic no licence file found · pointer only · d71ab24dd4408288 · report fixture: returned MLP · level recorded 2026-09-22
NestedTensor in 24 papers models/ests/ests.py ran · metamorphic tier: deterministic no licence file found · pointer only · 6efd3189a09cd0af · report fixture: returned NestedTensor · level recorded 2026-09-22
_max_by_axis models/ests/ests.py ran · honoured contract no licence file found · pointer only · ef393284ce3c9ea1 · report fixture: signature the_list:list/1/list · returned list · level recorded 2026-09-22
dn_post_process in 15 papers models/ests/ests.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 5bcf7dfb561bb961 · report fixture: signature outputs_class:Tensor/4/float, outputs_coord:Tensor/4/float, outputs_beziers:Tensor/4/float, outputs_rec_list:Tensor/5/float, dn_meta:dict/0/?, aux_loss:bool/0/bool, _set_aux_loss:callable/0/? · returned tuple · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers models/ests/ests.py ran · our draft was wrong no licence file found · pointer only · 6309c6cf50423938 · report fixture: signature tensor_list:list/1/Tensor · returned NestedTensor · level recorded 2026-09-22
prepare_for_cdn models/ests/ests.py ran; the contract check could not run (RAISES) no licence file found · pointer only · ac9fc8884bc0cd7d · report fixture: returned tuple · level recorded 2026-09-22
ESTS models/ests/ests.py unverified no licence file found · pointer only · 2402a1a05761b00a · report
_onnx_nested_tensor_from_tensor_list in 9 papers models/ests/ests.py unverified no licence file found · pointer only · 5772986b5d3cd55c · report
mxin262/swintextspotter community (archive-listed) 8 samples, 5 ran (4 instrument-failed) · 3 unverified
batched_nms in 29 papers detectron2/layers/nms.py ran no licence file found · pointer only · 5a3c7069b28e9ffb · report fixture: signature boxes:Tensor/2/float, scores:Tensor/1/float, idxs:Tensor/1/int, iou_threshold:float/0/float · returned Tensor · level recorded 2026-09-24
convert_basic_c2_names in 46 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong no licence file found · pointer only · e8526a516b4f9206 · report fixture: signature original_keys:list/1/str · returned list · level recorded 2026-09-24
convert_c2_detectron_names in 45 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong no licence file found · pointer only · e36f87059208bb7e · report fixture: signature weights:dict/0/? · returned tuple · level recorded 2026-09-24
pad_masks in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 406f84cf799ed34d · report fixture: signature masks:Tensor/3/float, padding:int/0/int · returned tuple · level recorded 2026-09-24
paste_mask_in_image_old in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong no licence file found · pointer only · d03592674030077f · report fixture: signature mask:Tensor/2/float, box:Tensor/1/float, img_h:int/0/int, img_w:int/0/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-24
align_and_update_state_dicts in 21 papers detectron2/checkpoint/c2_model_loading.py unverified no licence file found · pointer only · ac2638463572c152 · report
batched_nms_rotated in 22 papers detectron2/layers/nms.py unverified no licence file found · pointer only · b112e6eead8331b7 · report
nms_rotated in 22 papers detectron2/layers/nms.py unverified no licence file found · pointer only · ca61f088e7266086 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
inverse_sigmoid in 80 papers
census: 9 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 6897880b6ce14c94 · report fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Bridging Text Spotting (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Bridging Text Spotting (graph method: Bridging Text Spotting). 9 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ESTS entry · level 0 · unverified · 2402a1a05761b00a
  2. MLP helper · level 1 · ran · d71ab24dd4408288
  3. NestedTensor helper · level 1 · ran · 6efd3189a09cd0af
  4. dn_post_process helper · level 1 · ran; the contract check could not run (RAISES) · 5bcf7dfb561bb961
  5. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 6897880b6ce14c94
  6. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 6309c6cf50423938
  7. prepare_for_cdn helper · level 1 · ran; the contract check could not run (RAISES) · ac9fc8884bc0cd7d
  8. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  9. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 5772986b5d3cd55c

harvested Assembly for Bridging Text Spotting (graph method: Bridging Text Spotting). 8 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. Bridge entry · level 0 · unverified · 179df4b05daa85e4
  2. Block model · level 1 · ran · 5ad9f4a5115fc2c9
  3. PatchEmbed model · level 1 · ran · 36ec904c3b4e4e27
  4. get_sinusoid_encoding_table helper · level 1 · ran · honoured contract · e270b1e0375e984c
  5. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  6. Attention model · level 1 · ran · f07a7b5124daa4d3
  7. DropPath model · level 1 · ran · 7d9a8a01e3d8b2af
  8. Mlp model · level 1 · ran · e71525ebf968c4c3

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

one of 3 siblings

  1. Model entry · level 0 · unverified · e3d0360e5fe8ab89
  2. Attention helper · level 1 · ran · a55e20272adb06c8
  3. BidirectionalLSTM helper · level 1 · ran · 0a490b941ecc0d0b
  4. RCNN_FeatureExtractor helper · level 0 · unverified · ef5e9a2a130e79ff
  5. ResNet_FeatureExtractor helper · level 0 · unverified · 5a4873d904275392
  6. TPS_SpatialTransformerNetwork helper · level 0 · unverified · 6717e6516dabf3ca
  7. VGG_FeatureExtractor helper · level 1 · ran · 2ac69ad6b536be49
  8. AttentionCell helper · level 1 · ran · 87ec0a6342858e38
  9. GRCL helper · level 1 · ran · ad2aab77e017ae44
  10. BasicBlock helper · level 1 · ran · a06d957836eecfd1
  11. ResNet helper · level 1 · ran · f0555475dca7332a
  12. GridGenerator helper · level 1 · ran · 345b61e3a6a59f12
  13. LocalizationNetwork helper · level 1 · ran · e3f116bb52340904
  14. GRCL_unit helper · level 1 · ran · 2d06924d44e4a05f

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="2404.04624") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Text Spotting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterSET

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