Papers › Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations

Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations

14 Mar 2023CVPR 2023 1arXiv:2303.08085archive 2025-07-28

Hagay Michaeli, Tomer Michaeli, Daniel Soudry

Although CNNs are believed to be invariant to translations, recent works have shown this is not the case, due to aliasing effects that stem from downsampling layers. The existing architectural solutions to prevent aliasing are partial since they do not solve these effects, that originate in non-linearities. We propose an extended anti-aliasing method that tackles both downsampling and non-linear layers, thus creating truly alias-free, shift-invariant CNNs. We show that the presented model is invariant to integer as well as fractional (i.e., sub-pixel) translations, thus outperforming other shift-invariant methods in terms of robustness to adversarial translations.

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 27 code samples harvested from 1 repository linked to this paper: 18 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 27 samples from 1 repository, 18 ran (11 with no instrument failure; 7 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hmichaeli/alias_free_convnets officialmentioned in papermentioned on GitHubpytorchSyntology: 27 samples, 18 ran (7 instrument-failed) · 9 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

27 samples harvested: 18 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 9 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 · honoured contract
6ran · our draft was wrong
1ran; the contract check could not run
9ran
9unverified

Licence: 27 of the 27 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 hmichaeli/alias_free_convnets. “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 8 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.

hmichaeli/alias_free_convnets official repository 27 samples, 18 ran (7 instrument-failed) · 9 unverified
Filter models/convnext_afc.py ran fingerprinted no licence file found · pointer only · 5b73484f18f99b44 · report fixture: returned Filter · level recorded 2026-09-22
LPFPolyActPerChannel models/convnext_afc.py ran no licence file found · pointer only · 3c703464bdfa351a · report fixture: returned LPFPolyActPerChannel · level recorded 2026-09-22
LPF_RECON_RFFT models/convnext_afc.py ran no licence file found · pointer only · 24ccb431a72c048a · report fixture: returned LPF_RECON_RFFT · 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
models/convnext_afc.py ran · our draft was wrong no licence file found · pointer only · d818f9ab61a2968a · report fixture: signature normalized_shape:int/0/int, eps:float/0/float, data_format:str/0/str, normalization_type:str/0/str · returned LayerNorm_C · level recorded 2026-09-22
LayerNorm_AF models/convnext_afc.py ran no licence file found · pointer only · d48bf69372a83c41 · report fixture: returned LayerNorm_AF · level recorded 2026-09-22
LayerNorm_C models/convnext_afc.py ran fingerprinted no licence file found · pointer only · c3c59332b2098444 · report fixture: returned LayerNorm_C · level recorded 2026-09-22
PolyAct models/convnext_afc.py ran fingerprinted no licence file found · pointer only · 1ce86ab6920a66aa · report fixture: returned PolyAct · level recorded 2026-09-22
PolyActPerChannel models/convnext_afc.py ran fingerprinted no licence file found · pointer only · 7435ce53fce5eac0 · report fixture: returned PolyActPerChannel · level recorded 2026-09-22
UpsampleRFFT models/convnext_afc.py ran no licence file found · pointer only · b6b68b920844ef01 · report fixture: returned UpsampleRFFT · level recorded 2026-09-22
circular_pad models/convnext_afc.py ran fingerprinted no licence file found · pointer only · 489aaa429596294f · report fixture: returned circular_pad · level recorded 2026-09-22
conv2x2 models/convnext_afc.py ran · our draft was wrong no licence file found · pointer only · f26671f59ef75381 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, padding:int/0/int, stride:int/0/int, groups:int/0/int, bias:bool/0/bool, conv_pad_type:str/0/str · returned Sequential · level recorded 2026-09-22
conv4x4 models/convnext_afc.py ran · our draft was wrong no licence file found · pointer only · 367ddf61c744f06a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, padding:int/0/int, stride:int/0/int, groups:int/0/int, bias:bool/0/bool, conv_pad_type:str/0/str · returned Sequential · level recorded 2026-09-22
conv7x7 models/convnext_afc.py ran · our draft was wrong no licence file found · pointer only · 6378a31d003903eb · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, padding:int/0/int, stride:int/0/int, groups:int/0/int, bias:bool/0/bool, conv_pad_type:str/0/str · returned Sequential · level recorded 2026-09-22
create_fixed_lpf_rect models/convnext_afc.py ran · honoured contract fingerprinted no licence file found · pointer only · e74c53ae486e7dbe · report fixture: signature N:int/0/int, size:int/0/int · returned Tensor · level recorded 2026-09-22
create_lpf_rect models/convnext_afc.py ran · honoured contract no licence file found · pointer only · 0af016ff4b338555 · report fixture: signature N:int/0/int, cutoff:float/0/float · returned Tensor · level recorded 2026-09-22
get_norm_layer in 111 papers models/convnext_afc.py ran · our draft was wrong no licence file found · pointer only · 84c80beecf2f1507 · report fixture: signature normalization_type:str/0/str, dim:int/0/int, data_format:str/0/str · returned LayerNorm_C · level recorded 2026-09-22
get_pad_layer in 25 papers models/convnext_afc.py ran · our draft was wrong no licence file found · pointer only · 95c3ec7344a80d78 · report fixture: signature pad_type:str/0/str · returned type · level recorded 2026-09-22
pad_layer models/convnext_afc.py ran; the contract check could not run (RAISES) no licence file found · pointer only · d65a25667eea645f · report fixture: signature pad_type:str/0/str, padding:tuple/1/int · returned circular_pad · level recorded 2026-09-22
AALMLP models/convnext_afc.py unverified no licence file found · pointer only · 0ce72698b7fb0adb · report
BlurPool models/convnext_afc.py unverified no licence file found · pointer only · 95b5fee726c0126a · report
ConvNeXtAFC models/convnext_afc.py unverified no licence file found · pointer only · f70f888b93a8496b · report
MLP in 375 papers models/convnext_afc.py unverified no licence file found · pointer only · 1611d72305138d55 · report
Residual in 24 papers models/convnext_afc.py unverified no licence file found · pointer only · 6ba599fd0d2e6b0d · report
UpPolyAct models/convnext_afc.py unverified no licence file found · pointer only · 9177ccd544f90dae · report
UpPolyActPerChannel models/convnext_afc.py unverified no licence file found · pointer only · 27916faaf81b64db · report
get_activation in 218 papers models/convnext_afc.py unverified no licence file found · pointer only · 9df8d935d61014da · 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 Alias-Free Convnets (graph method: Alias-Free Convnets). 28 bricks; individually on a fixture: 19 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. ConvNeXtAFC entry · level 0 · unverified · f70f888b93a8496b
  2. Block model · level 0 · unverified · 02099da423590637
  3. BlurPool helper · level 0 · unverified · 95b5fee726c0126a
  4. Residual model · level 0 · unverified · 6ba599fd0d2e6b0d
  5. conv2x2 helper · level 1 · ran · our draft was wrong · f26671f59ef75381
  6. conv4x4 helper · level 1 · ran · our draft was wrong · 367ddf61c744f06a
  7. get_activation helper · level 0 · unverified · 9df8d935d61014da
  8. get_norm_layer helper · level 1 · ran · our draft was wrong · 84c80beecf2f1507
  9. AALMLP helper · level 0 · unverified · 0ce72698b7fb0adb
  10. MLP helper · level 0 · unverified · 1611d72305138d55
  11. conv7x7 helper · level 1 · ran · our draft was wrong · 6378a31d003903eb
  12. Filter helper · level 1 · ran · 5b73484f18f99b44
  13. get_pad_layer helper · level 1 · ran · our draft was wrong · 95c3ec7344a80d78
  14. pad_layer helper · level 1 · ran; the contract check could not run (RAISES) · d65a25667eea645f
  15. LPFPolyActPerChannel helper · level 1 · ran · 3c703464bdfa351a
  16. PolyAct helper · level 1 · ran · 1ce86ab6920a66aa
  17. PolyActPerChannel helper · level 1 · ran · 7435ce53fce5eac0
  18. UpPolyAct helper · level 0 · unverified · 9177ccd544f90dae
  19. UpPolyActPerChannel helper · level 0 · unverified · 27916faaf81b64db
  20. LayerNorm helper · level 1 · ran · our draft was wrong · d818f9ab61a2968a
  21. UpsampleRFFT helper · level 1 · ran · b6b68b920844ef01
  22. circular_pad helper · level 1 · ran · 489aaa429596294f
  23. LayerNorm_AF helper · level 1 · ran · d48bf69372a83c41
  24. LayerNorm_C helper · level 1 · ran · c3c59332b2098444
  25. LPF_RECON_RFFT helper · level 1 · ran · 24ccb431a72c048a
  26. create_recon_rect helper · level 1 · ran · honoured contract · ad77d8eb30462368
  27. create_fixed_lpf_rect helper · level 1 · ran · honoured contract · e74c53ae486e7dbe
  28. create_lpf_rect helper · level 1 · ran · honoured contract · 0af016ff4b338555

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="2303.08085") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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