Papers › Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform

Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform

21 Aug 2021ICCV 2021 10arXiv:2108.09551archive 2025-07-28

Myungseo Song, Jinyoung Choi, Bohyung Han

We propose a versatile deep image compression network based on Spatial Feature Transform (SFT arXiv:1804.02815), which takes a source image and a corresponding quality map as inputs and produce a compressed image with variable rates. Our model covers a wide range of compression rates using a single model, which is controlled by arbitrary pixel-wise quality maps. In addition, the proposed framework allows us to perform task-aware image compressions for various tasks, e.g., classification, by efficiently estimating optimized quality maps specific to target tasks for our encoding network. This is even possible with a pretrained network without learning separate models for individual tasks. Our algorithm achieves outstanding rate-distortion trade-off compared to the approaches based on multiple models that are optimized separately for several different target rates. At the same level of compression, the proposed approach successfully improves performance on image classification and text region quality preservation via task-aware quality map estimation without additional model training. The code is available at the project website: https://github.com/micmic123/QmapCompression

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 23 code samples harvested from 1 repository linked to this paper: 14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 14 ran (10 with no instrument failure; 4 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.

micmic123/qmapcompression officialmentioned in papermentioned on GitHubpytorchSyntology: 23 samples, 14 ran (4 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

23 samples harvested: 14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 4 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
4ran · our draft was wrong
8ran
9unverified

Licence: 23 of the 23 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 micmic123/qmapcompression. “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.

micmic123/qmapcompression official repository 23 samples, 14 ran (4 instrument-failed) · 9 unverified
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
models/models.py ran · our draft was wrong no licence file found · pointer only · 57912304b19e055b · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding_mode:str/0/str · returned Conv2d · level recorded 2026-09-22
EntropyModel models/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9c1f1cc448e0664d · report fixture: returned EntropyModel · level recorded 2026-09-22
GDN in 5 papers models/models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · c39451487c43c591 · report fixture: returned GDN · level recorded 2026-09-22
GDN1 models/models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · be5888fab6d676bd · report fixture: returned GDN1 · level recorded 2026-09-22
LowerBound models/models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · bf1b22bbc577d39b · report fixture: returned LowerBound · level recorded 2026-09-22
LowerBoundFunction models/models.py ran no licence file found · pointer only · 1cd37f07f26da419 · report fixture: returned LowerBoundFunction · level recorded 2026-09-22
NonNegativeParametrizer models/models.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 1640fa653b057731 · report fixture: returned NonNegativeParametrizer · level recorded 2026-09-22
SFT models/models.py ran no licence file found · pointer only · 4c9e4068d6df44c1 · report fixture: signature x:Tensor/4/float, qmap:Tensor/4/float · returned Tensor · level recorded 2026-09-24
SFTResblk models/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 21e656d9f3eb6bb6 · report fixture: returned SFTResblk · level recorded 2026-09-22
UpConv2d models/models.py ran · our draft was wrong no licence file found · pointer only · c32ca457818c1366 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned ConvTranspose2d · level recorded 2026-09-22
conv in 178 papers models/models.py ran · our draft was wrong no licence file found · pointer only · f2cea3e9848ae52d · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
deconv in 48 papers models/models.py ran · our draft was wrong no licence file found · pointer only · 1afd37c576493fea · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned ConvTranspose2d · level recorded 2026-09-22
find_named_buffer in 9 papers models/models.py ran · honoured contract no licence file found · pointer only · a94389b554ddc179 · report fixture: signature module:callable/0/?, query:str/0/str · returned Tensor · level recorded 2026-09-22
get_scale_table in 21 papers models/models.py ran · honoured contract no licence file found · pointer only · d1e39fa98bee2cb7 · report fixture: signature min:float/0/float, max:int/0/int, levels:int/0/int · returned Tensor · level recorded 2026-09-22
CompressionModel models/models.py unverified no licence file found · pointer only · 3bc52cfb7b786786 · report
EntropyBottleneck models/models.py unverified no licence file found · pointer only · 148cb7a629823ea7 · report
GaussianConditional models/models.py unverified no licence file found · pointer only · 2474ed1b08d571c3 · report
ScaleHyperprior models/models.py unverified no licence file found · pointer only · dc293862477823c8 · report
SpatiallyAdaptiveCompression models/models.py unverified no licence file found · pointer only · 9732c184d3a8e96b · report
_EntropyCoder models/models.py unverified no licence file found · pointer only · d05821ea9fe6037d · report
_update_registered_buffer models/models.py unverified no licence file found · pointer only · 5612db1b73ea390d · report
default_entropy_coder models/models.py unverified no licence file found · pointer only · faadfa6193587d6c · report
update_registered_buffers models/models.py unverified no licence file found · pointer only · a089d0be0293d735 · 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 Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform (graph method: Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform). 23 bricks; individually on a fixture: 14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. SpatiallyAdaptiveCompression entry · level 0 · unverified · 9732c184d3a8e96b
  2. Conv2d helper · level 1 · ran · our draft was wrong · 57912304b19e055b
  3. GDN1 model · level 1 · ran · be5888fab6d676bd
  4. SFT model · level 1 · ran · 4c9e4068d6df44c1
  5. SFTResblk model · level 1 · ran · 21e656d9f3eb6bb6
  6. ScaleHyperprior helper · level 0 · unverified · dc293862477823c8
  7. UpConv2d helper · level 1 · ran · our draft was wrong · c32ca457818c1366
  8. conv helper · level 1 · ran · our draft was wrong · f2cea3e9848ae52d
  9. GDN model · level 1 · ran · c39451487c43c591
  10. CompressionModel helper · level 0 · unverified · 3bc52cfb7b786786
  11. GaussianConditional helper · level 0 · unverified · 2474ed1b08d571c3
  12. deconv helper · level 1 · ran · our draft was wrong · 1afd37c576493fea
  13. get_scale_table helper · level 1 · ran · honoured contract · d1e39fa98bee2cb7
  14. update_registered_buffers helper · level 0 · unverified · a089d0be0293d735
  15. NonNegativeParametrizer helper · level 1 · ran · 1640fa653b057731
  16. EntropyBottleneck helper · level 0 · unverified · 148cb7a629823ea7
  17. EntropyModel helper · level 1 · ran · 9c1f1cc448e0664d
  18. LowerBound helper · level 1 · ran · bf1b22bbc577d39b
  19. _update_registered_buffer helper · level 0 · unverified · 5612db1b73ea390d
  20. _EntropyCoder helper · level 0 · unverified · d05821ea9fe6037d
  21. default_entropy_coder helper · level 0 · unverified · faadfa6193587d6c
  22. LowerBoundFunction helper · level 1 · ran · 1cd37f07f26da419
  23. find_named_buffer helper · level 1 · ran · honoured contract · a94389b554ddc179

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="2108.09551") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationImage Compressionimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Spatial Feature Transform

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