SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.05085 · ICCV · 2023

TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception

Wei-Chen Chiu, Chia-Hao Kao, Cheng Chien, Yi-Hsin Chen, Wen-Hsiao Peng, Ying-Chieh Weng

arXiv · PDF · Open in the Atlas

Code that ran

2 of 8 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; 0 failures of our instrument; 6 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/2306.05085.json · badge: /api/ran/2306.05085.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
NYCU-MAPL/TransTIC marked official in Papers with Code
Papers with Code archive
2 ran · 6 no recorded run
FunctionStatusWhere it lives
Mask_Gen_Shallow Ran
ran on a synthesized input · constructed an object; no result was computed
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("0d052438a099d116")
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, Mask_Gen_Shallow: 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function is Mask_Gen_Shallow.__init__, which takes:
# - out_channel: int (default=1)
# - mid_channel: int (default=64)

# Create a small input tensor to verify the model works
# Input should be (batch, channels, height, width)
# The model expects 3 input channels (RGB image)
input_img = torch.randn(2, 3, 32, 32)

ARGS = {
    'out_channel': 1,
    'mid_channel': 64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Mask_Gen_Shallow — 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 Mask_Gen_Shallow 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
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("0655c193d6ef7868")
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) and returned Tensor, ndim 1, dtype family float, shape (64,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 math
import torch

SCALES_LEVELS = 64
SCALES_MAX = 256
SCALES_MIN = 0.11

def get_scale_table(min=SCALES_MIN, max=SCALES_MAX, levels=SCALES_LEVELS):
    return torch.exp(torch.linspace(math.log(min), math.log(max), levels))

torch.manual_seed(0)

ARGS = {
    "min": 0.11,
    "max": 256,
    "levels": 64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (64,) — shape (64,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
EntropyBottleneck Not yet run
unverified (harvested, no recorded run)
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("213033cdc1197aec")
How it ran

no invocation recorded.

EntropyModel Not yet run
unverified (harvested, no recorded run)
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("834d0b288545ca81")
How it ran

no invocation recorded.

GaussianConditional Not yet run
unverified (harvested, no recorded run)
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("821c50b43b127f67")
How it ran

no invocation recorded.

TIC_PromptModel_first2 Not yet run
unverified (harvested, no recorded run)
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("98a9717711fd4c58")
How it ran

no invocation recorded.

_EntropyCoder Not yet run
unverified (harvested, no recorded run)
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("c88f24038c7eeb3a")
How it ran

no invocation recorded.

_forward Not yet run
unverified (harvested, no recorded run)
NYCU-MAPL/TransTIC/compressai/models/tic_promptmodel.py
code served (permissive licence) · get_code("03f1aebf64f96ace")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 7 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
brick of this paper's assembly: helper
16 other papers
10 dated earlier, 6 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

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

This work aims for transferring a Transformer-based image compression codec from human perception to machine perception without fine-tuning the codec. We propose a transferable Transformer-based image compression framework, termed TransTIC. Inspired by visual prompt tuning, TransTIC adopts an instance-specific prompt generator to inject instance-specific prompts to the encoder and taskspecific prompts to the decoder. Extensive experiments show that our proposed method is capable of transferring the base codec to various machine tasks and outperforms the competing methods significantly. To our best knowledge, this work is the first attempt to utilize prompting on the low-level image compression task.

For agents

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

get_harvested_code_for_paper("2306.05085")
get_code_for_paper("2306.05085")
have("2306.05085")

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

curl https://syntology.ai/api/ran/2306.05085.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.05085.svg)](https://syntology.ai/paper/2306.05085)

Connect an agent — have() is free.