SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.15306 · CVPR · 2021

Checkerboard Context Model for Efficient Learned Image Compression

Yan Wang, Dailan He, Hongwei Qin, Yaoyan Zheng, Baocheng Sun

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2103.15306.json · badge: /api/ran/2103.15306.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
Nikolai10/Checkerboard-Context-Model community
Papers with Code archive
1 ran · 0 no recorded run
JiangWeibeta/Checkerboard-Context-Model-for-Efficient-Learned-Image-Compression community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
CheckerboardContext Ran
ran on a synthesized input · constructed an object; no result was computed
Nikolai10/Checkerboard-Context-Model/hzswq2021.py
code served (permissive licence) · get_code("7658c8b087db49e1")
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, CheckerboardContext: 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
import numpy as np

# Create a small input tensor for testing
# Shape: (batch_size=2, height=4, width=4, channels=3)
input_tensor = tf.random.normal((2, 4, 4, 3))

# Define arguments for CheckerboardContext
# CheckerboardContext inherits from tf.keras.layers.Conv2D
# Conv2D signature: Conv2D(filters, kernel_size, strides=1, padding='valid', ...)

ARGS = {
    'filters': 8,  # number of output filters
    'kernel_size': (3, 3),  # kernel size - tuple of 2 ints
    'strides': 1,  # stride size
    'padding': 'same',  # padding mode
    'activation': None,  # activation function (None for linear)
    'use_bias': True,  # whether to use bias
    'kernel_initializer': 'glorot_uniform',  # kernel initializer
    'bias_initializer': 'zeros',  # bias initializer
    'kernel_regularizer': None,  # regularizer for kernel weights
    'bias_regularizer': None,  # regularizer for bias
    'activity_regularizer': None,  # regularizer for output
    'kernel_constraint': None,  # constraint for kernel
    'bias_constraint': None,  # constraint for bias
    'data_format': 'channels_last',  # data format
    'dilation_rate': (1, 1),  # dilation rate
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CheckerboardContext — 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 CheckerboardContext 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
CheckerboardContext Ran
ran on a synthesized input
JiangWeibeta/Checkerboard-Context-Model-for-Efficient-Learned-Image-Compression/layers/CheckerboardContext.py
code served (permissive licence) · get_code("3c22a46404021749")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 8, 8) 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 torch
import torch.nn as nn

class CheckerboardContext(nn.Conv2d):
    """
    if kernel_size == (5, 5)
    then mask:
        [[0., 1., 0., 1., 0.],
        [1., 0., 1., 0., 1.],
        [0., 1., 0., 1., 0.],
        [1., 0., 1., 0., 1.],
        [0., 1., 0., 1., 0.]]
    0: non-anchor
    1: anchor
    """

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.register_buffer('mask', torch.zeros_like(self.weight.data))
        self.mask[:, :, 0::2, 1::2] = 1
        self.mask[:, :, 1::2, 0::2] = 1

    def forward(self, x):
        self.weight.data *= self.mask
        out = super().forward(x)
        return out


INIT_ARGS = {
    'in_channels': 3,
    'out_channels': 4,
    'kernel_size': (5, 5),
    'stride': 1,
    'padding': 2,
}

ARGS = {
    'x': torch.randn(2, 3, 8, 8),
}

if __name__ == '__main__':
    model = CheckerboardContext(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Mask shape: {model.mask.shape}")
    print(f"Weight shape: {model.weight.shape}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 4, dtype family float, shape (2, 4, 8, 8) — shape (2, 4, 8, 8) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

For learned image compression, the autoregressive context model is proved effective in improving the ratedistortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process must be done in a strict scan order, which breaks the parallelization. We propose a parallelizable checkerboard context model (CCM) to solve the problem. Our two-pass checkerboard context calculation eliminates such limitations on spatial locations by re-organizing the decoding order. Speeding up the decoding process more than 40 times in our experiments, it achieves significantly improved computational efficiency with almost the same rate-distortion performance. To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.

For agents

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

get_harvested_code_for_paper("2103.15306")
get_code_for_paper("2103.15306")
have("2103.15306")

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

curl https://syntology.ai/api/ran/2103.15306.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.15306.svg)](https://syntology.ai/paper/2103.15306)

Connect an agent — have() is free.