SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.07157 · CVPR · 2022

Joint Forecasting of Panoptic Segmentations with Difference Attention

Alexander Schwing, -Champaign, Wenjie Luo, Liangyan Gui, Colin Graber, Cyril Jazra

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2204.07157.json · badge: /api/ran/2204.07157.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
cgraber/psf-diffattn marked official in Papers with Code
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
_LinearWithBias Ran
ran on a synthesized input · constructed an object; no result was computed
cgraber/psf-diffattn/joint_panoptic_forecast/model_components/transformer_difference_general_layers.py
code served (permissive licence) · get_code("752a259e6e2d0be3")
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, _LinearWithBias: 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
from torch import Tensor
from torch.nn import Module, Parameter, Linear

torch.manual_seed(0)

class _LinearWithBias(Linear):
    bias: Tensor

    def __init__(self, in_features: int, out_features: int) -> None:
        super().__init__(in_features, out_features, bias=True)

ARGS = {
    "in_features": 4,
    "out_features": 3,
}
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 _LinearWithBias — 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 _LinearWithBias 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
MultiheadDifferenceGeneralAttention Not yet run
unverified (harvested, no recorded run)
cgraber/psf-diffattn/joint_panoptic_forecast/model_components/transformer_difference_general_layers.py
code served (permissive licence) · get_code("0933d6646e0645ba")
How it ran

no invocation recorded.

multi_head_difference_attention_forward Not yet run
unverified (harvested, no recorded run)
cgraber/psf-diffattn/joint_panoptic_forecast/model_components/transformer_difference_general_layers.py
code served (permissive licence) · get_code("eeaa83e4c1514eeb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Forecasting of a representation is important for safe and effective autonomy. For this, panoptic segmentations have been studied as a compelling representation in recent work. However, recent state-of-the-art on panoptic segmentation forecasting suffers from two issues: first, individual object instances are treated independently of each other; second, individual object instance forecasts are merged in a heuristic manner. To address both issues, we study a new panoptic segmentation forecasting model that jointly forecasts all object instances in a scene using a transformer model based on 'difference attention.' It further refines the predictions by taking depth estimates into account. We evaluate the proposed model on the Cityscapes and AIODrive datasets. We find difference attention to be particularly suitable for forecasting because the difference of quantities like locations enables a model to explicitly reason about velocities and acceleration. Because of this, we attain state-of-the-art on panoptic segmentation forecasting metrics.

For agents

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

get_harvested_code_for_paper("2204.07157")
get_code_for_paper("2204.07157")
have("2204.07157")

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

curl https://syntology.ai/api/ran/2204.07157.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.07157.svg)](https://syntology.ai/paper/2204.07157)

Connect an agent — have() is free.