SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.12400 · ICCV · 2023

UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework

Guang Chen, Alois Knoll, Kai Chen, Bo Zhang, Changjun Jiang, Tianhang Wang, Zhengfa Liu

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 1 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/2303.12400.json · badge: /api/ran/2303.12400.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
ispc-lab/umc community
Papers with Code archive
6 ran · 1 no recorded run
FunctionStatusWhere it lives
ClassificationHead Ran
ran on a synthesized input · constructed an object; no result was computed
ispc-lab/umc/utils/CoDetModel.py
code served (permissive licence) · get_code("4891ac0025599128")
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, ClassificationHead: 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)

class Config:
    def __init__(self):
        self.category_num = 5
        self.use_map = True
        self.use_vis = True
        self.anchor_size = [(1, 2), (2, 3), (3, 4)]

config = Config()

ARGS = {
    "config": config
}
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 ClassificationHead — 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 ClassificationHead 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
CompressNet Ran
ran on a synthesized input · constructed an object; no result was computed
ispc-lab/umc/utils/CoDetModel.py
code served (permissive licence) · get_code("4f0c32727807309f")
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, CompressNet: 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)

ARGS = {
    "channel": 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 CompressNet — 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 CompressNet 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
GRU_R_Z Ran
ran on a synthesized input
ispc-lab/umc/utils/CoDetModel.py
code served (permissive licence) · get_code("4aa3648e2e6d661d")
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 tuple. 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 numpy as np

INIT_ARGS = {
    "input_channel": 4,
}

# Construct tensors for forward call
hidden_f = torch.randn(1, 4, 3, 5)  # (batch=1, channels=4, height=3, width=5)
tg = torch.randn(4, 3, 5)           # (channels=4, height=3, width=5)

ARGS = {
    "hidden_f": hidden_f,
    "tg": tg,
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ModulationLayer3 Ran
ran on a synthesized input · constructed an object; no result was computed
ispc-lab/umc/utils/CoDetModel.py
code served (permissive licence) · get_code("0db9a50bf2be899b")
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, ModulationLayer3: 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)

class ModulationLayer3(nn.Module):
    def __init__(self, config):
        super(ModulationLayer3, self).__init__()
        self.conv1_1 = nn.Conv2d(512, 256, kernel_size=1, stride=1, padding=0)
        self.bn1_1 = nn.BatchNorm2d(256)

    def forward(self, x):
        x = x.view(-1, x.size(-3), x.size(-2), x.size(-1))
        x_1 = torch.nn.functional.relu(self.bn1_1(self.conv1_1(x)))
        return x_1

config = {}

ARGS = {
    'config': config
}
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 ModulationLayer3 — 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 ModulationLayer3 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
PixelWeightedFusionSoftmax Ran
ran on a synthesized input · constructed an object; no result was computed
ispc-lab/umc/utils/CoDetModel.py
code served (permissive licence) · get_code("2440f417686e025e")
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, PixelWeightedFusionSoftmax: 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 PixelWeightedFusionSoftmax.__init__ takes 'channel' parameter
# The forward method expects input tensor x with shape that can be reshaped to 4D (batch, channels, height, width)
# Looking at the forward: x.view(-1, x.size(-3), x.size(-2), x.size(-1))
# This means input should have at least 3 dimensions after the batch dimension
# The first conv layer expects 'channel' input channels

# Create a small instance with channel=16
channel = 16

# Create sample input tensor
# After view(-1, x.size(-3), x.size(-2), x.size(-1)), it should have shape (batch, channel, height, width)
# So we need input with shape (batch, channel, height, width) or similar
# Let's create (batch=2, channel=16, height=4, width=3)
sample_input = torch.randn(2, 16, 4, 3)

ARGS = {
    "channel": channel
}
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 PixelWeightedFusionSoftmax — 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 PixelWeightedFusionSoftmax 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
SingleRegressionHead Ran
ran on a synthesized input · constructed an object; no result was computed
ispc-lab/umc/utils/CoDetModel.py
code served (permissive licence) · get_code("8793f7e1d13adc82")
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, SingleRegressionHead: 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)

class Config:
    def __init__(self):
        self.category_num = 10
        self.use_map = True
        self.use_vis = True
        self.anchor_size = [(1.0, 2.0), (2.0, 3.0)]  # 2 anchors per location
        self.box_code_size = 5
        self.pred_len = 3
        self.only_det = False
        self.binary = True

config = Config()

ARGS = {
    "config": config
}
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 SingleRegressionHead — 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 SingleRegressionHead 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
UMC Not yet run
unverified (harvested, no recorded run)
ispc-lab/umc/utils/CoDetModel.py
code served (permissive licence) · get_code("f60c4b3f97441303")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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, 0 later) and 6 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
ClassificationHead
brick of this paper's assembly: model
1 other paper
1 dated earlier
2111.00643 (2021-11)
Learning Distilled Collaboration Graph for Multi-Agent Perception

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

Multi-agent collaborative perception (MCP) has recently attracted much attention. It includes three key processes: communication for sharing, collaboration for integration, and reconstruction for different downstream tasks. Existing methods pursue designing the collaboration process alone, ignoring their intrinsic interactions and resulting in suboptimal performance. In contrast, we aim to propose a Unified Collaborative perception framework named UMC, optimizing the communication, collaboration, and reconstruction processes with the Multi-resolution technique. The communication introduces a novel trainable multi-resolution and selective-region (MRSR) mechanism, achieving higher quality and lower bandwidth. Then, a graph-based collaboration is proposed, conducting on each resolution to adapt the MRSR. Finally, the reconstruction integrates the multi-resolution collaborative features for downstream tasks. Since the general metric can not reflect the performance enhancement brought by MCP systematically, we introduce a brand-new evaluation metric that evaluates the MCP from different perspectives. To verify our algorithm, we conducted experiments on the V2X-Sim and OPV2V datasets. Our quantitative and qualitative experiments prove that the proposed UMC outperforms the state-of-the-art collaborative perception approaches.

For agents

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

get_harvested_code_for_paper("2303.12400")
get_code_for_paper("2303.12400")
have("2303.12400")

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

curl https://syntology.ai/api/ran/2303.12400.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.12400.svg)](https://syntology.ai/paper/2303.12400)

Connect an agent — have() is free.