SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.14978 · CVPR · 2023

Learned Image Compression with Mixed Transformer-CNN Architectures

Jinming Liu, Heming Sun, Jiro Katto

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2303.14978.json · badge: /api/ran/2303.14978.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jmliu206/lic_tcm canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
Nikolai10/LIC-TCM community
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
AttentionBlock Ran
ran on a synthesized input · constructed an object; no result was computed
Nikolai10/LIC-TCM/arch_ops.py
code served (permissive licence) · get_code("925746f55edae6b9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, AttentionBlock: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf

# Create the ARGS dictionary with the required parameter
ARGS = {
    "N": 8  # Number of channels - small integer for testing
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type AttentionBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a AttentionBlock output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv1x1 Ran
ran; our contract draft was wrong, not the code
Nikolai10/LIC-TCM/arch_ops.py
code served (permissive licence) · get_code("fa40b2e13b2d132d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2D. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf

ARGS = {
    'in_ch': 3,
    'out_ch': 64,
    'stride': 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2D — a Conv2D output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2D output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv1x1 Ran
ran; our contract draft was wrong, not the code
jmliu206/lic_tcm/models/tcm.py
pointer only (licence: MIT); the stored copy get_code serves, from UnoC-727/NeFIC, is pointer only (licence: NONE) · get_code("15eae621014906be")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from UnoC-727/NeFIC, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv3x3 Ran
ran; our contract draft was wrong, not the code
Nikolai10/LIC-TCM/arch_ops.py
code served (permissive licence) · get_code("c2107acec370b728")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2D. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf

ARGS = {
    'in_ch': 3,
    'out_ch': 64,
    'stride': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2D — a Conv2D output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2D output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_scale_table Ran
ran, honoured the contract we drafted
jmliu206/lic_tcm/models/tcm.py
pointer only (licence: MIT); the stored copy get_code serves, from xinjie-q/distributed-dvc, is pointer only (licence: NONE) · get_code("1eca81f63e28f103")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xinjie-q/distributed-dvc, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mlp_block Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Nikolai10/LIC-TCM/arch_ops.py
code served (permissive licence) · get_code("69863b1f57728eef")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
from tensorflow import keras
from typing import List

ARGS = {
    'dropout_rate': 0.1,
    'hidden_units': [64, 128, 32],
    'name': 'mlp_test'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ste_round Ran
ran; our contract draft was wrong, not the code
jmliu206/lic_tcm/models/tcm.py
pointer only (licence: MIT); the stored copy get_code serves, from qinsy123/2024-mambavc, is pointer only (licence: NONE) · get_code("cd3178f088f029d1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from qinsy123/2024-mambavc, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SWAtten Not yet run
unverified (harvested, no recorded run)
Nikolai10/LIC-TCM/arch_ops.py
code served (permissive licence) · get_code("363c55601de2fbf5")
How it ran

no invocation recorded.

SwinTransformerBlock Not yet run
unverified (harvested, no recorded run)
Nikolai10/LIC-TCM/arch_ops.py
code served (permissive licence) · get_code("7e1cf3efc00cbd79")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_scale_table 16 other papers
9 dated earlier, 7 later
1802.01436 (2018-02)
Variational image compression with a scale hyperprior
2011.03029 (2020-11)
CompressAI: a PyTorch library and evaluation platform for end-to-end compression research
2011.06294 (2020-11)
Real-Time Intermediate Flow Estimation for Video Frame Interpolation
and 13 more not named here
conv1x1 12 other papers
4 dated earlier, 8 later
aaai_19890 (2022 (year only))
OoDHDR-Codec: Out-of-Distribution Generalization for HDR Image Compression
2203.08450 (2022-03)
The Devil Is in the Details: Window-based Attention for Image Compression
2203.10886 (2022-03)
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
and 9 more not named here
ste_round 7 other papers
2 dated earlier, 5 later
aaai_19890 (2022 (year only))
OoDHDR-Codec: Out-of-Distribution Generalization for HDR Image Compression
2203.08450 (2022-03)
The Devil Is in the Details: Window-based Attention for Image Compression
2310.16387 (2023-10)
Frequency-Aware Transformer for Learned Image Compression
and 4 more not named here
mlp_block
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learned image compression (LIC) methods have exhibited promising progress and superior rate-distortion performance compared with classical image compression standards. Most existing LIC methods are Convolutional Neural Networks-based (CNN-based) or Transformer-based, which have different advantages. Exploiting both advantages is a point worth exploring, which has two challenges: 1) how to effectively fuse the two methods? 2) how to achieve higher performance with a suitable complexity? In this paper, we propose an efficient parallel Transformer-CNN Mixture (TCM) block with a controllable complexity to incorporate the local modeling ability of CNN and the non-local modeling ability of transformers to improve the overall architecture of image compression models. Besides, inspired by the recent progress of entropy estimation models and attention modules, we propose a channel-wise entropy model with parameter-efficient swin-transformer-based attention (SWAtten) modules by using channel squeezing. Experimental results demonstrate our proposed method achieves state-of-the-art rate-distortion performances on three different resolution datasets (i.e., Kodak, Tecnick, CLIC Professional Validation) compared to existing LIC methods. The code is at https://github.com/jmliu206/ LIC_TCM .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.14978")
get_code_for_paper("2303.14978")
have("2303.14978")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.14978.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.14978.svg)](https://syntology.ai/paper/2303.14978)

Connect an agent — have() is free.