SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1901.02446 · 2019

Panoptic Feature Pyramid Networks

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 7 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/1901.02446.json · badge: /api/ran/1901.02446.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
Shun14/panopticFPN-paddle community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
ashwath007/amenity-detection community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
add_extras Ran
ran; our contract draft was wrong, not the code
ashwath007/amenity-detection/Algo/SSD/ssd.py
code served (permissive licence) · get_code("2a8545e480332b47")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 expects:
# - cfg: a list/tuple that can contain integers and 'S' strings
# - i: an integer representing initial in_channels
# - batch_norm: a boolean (default False)

# Looking at the function logic:
# - It iterates over cfg with enumerate
# - cfg elements can be 'S' or integers (representing out_channels)
# - When v == 'S', it looks at cfg[k+1] for the next value
# - in_channels starts as i and gets updated to v in each iteration
# - flag alternates between False and True to choose kernel_size (1 or 3)

# A valid cfg would be a list with integers and 'S' markers
# Example: [256, 'S', 512, 128, 'S', 256, 128]
# This means: 
# - First layer: in_channels=i, out_channels=256, kernel_size=1
# - Second layer: in_channels=256, out_channels=512 (from cfg[k+1]), kernel_size=3, stride=2
# - Third layer: in_channels=512, out_channels=128, kernel_size=1
# - Fourth layer: in_channels=128, out_channels=256 (from cfg[k+1]), kernel_size=3, stride=2
# - Fifth layer: in_channels=256, out_channels=128, kernel_size=1

cfg = [256, 'S', 512, 128, 'S', 256, 128]
i = 1024
batch_norm = False

ARGS = {
    'cfg': cfg,
    'i': i,
    'batch_norm': batch_norm
}
Setup block drafted by
a language model, Claude Sonnet 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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
flip_combination Ran
ran on a synthesized input
Shun14/panopticFPN-paddle/paddleseg/core/infer.py
code served (permissive licence) · get_code("95bccf5957a196e4")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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.

# Setup code for flip_combination function

ARGS = {
    "flip_horizontal": False,
    "flip_vertical": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
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
get_image_list Ran
ran on a synthesized input
Shun14/panopticFPN-paddle/predict.py
code served (permissive licence) · get_code("c8f710d7401e0006")
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 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 os
import tempfile
import shutil

# Create a temporary directory with test images
temp_dir = tempfile.mkdtemp()

# Create a few test image files
test_image_path1 = os.path.join(temp_dir, "image1.jpg")
test_image_path2 = os.path.join(temp_dir, "image2.png")
with open(test_image_path1, 'w') as f:
    f.write("dummy image content")
with open(test_image_path2, 'w') as f:
    f.write("dummy image content")

# Test with directory path
image_path_dir = temp_dir

ARGS = {
    "image_path": image_path_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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: none by the harness; any seed is in the setup block
get_reverse_list Ran
ran on a synthesized input
Shun14/panopticFPN-paddle/paddleseg/core/infer.py
code served (permissive licence) · get_code("026fee631ce4a66c")
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 list. 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


class Resize:
    def __init__(self, target_size):
        self.target_size = target_size


class ResizeByLong:
    def __init__(self, long_size):
        self.long_size = long_size


class Padding:
    def __init__(self, target_size):
        self.target_size = target_size


class PaddingByAspectRatio:
    def __init__(self, aspect_ratio):
        self.aspect_ratio = aspect_ratio


class LimitLong:
    def __init__(self, max_long=None, min_long=None):
        self.max_long = max_long
        self.min_long = min_long


ARGS = {
    "ori_shape": [480, 640],
    "transforms": [
        Resize((256, 256)),
        ResizeByLong(512),
        Padding((512, 512)),
        PaddingByAspectRatio(1.5),
        LimitLong(max_long=1024, min_long=256),
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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: none by the harness; any seed is in the setup block
get_test_config Ran
ran; our contract draft was wrong, not the code
Shun14/panopticFPN-paddle/val.py
code served (permissive licence) · get_code("20eb3e6b0aba73e4")
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 dict. 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

class SimpleArgs:
    def __init__(self):
        self.aug_eval = True
        self.scales = [0.5, 1.0, 1.5]
        self.flip_horizontal = True
        self.flip_vertical = False
        self.is_slide = True
        self.crop_size = 512
        self.stride = 256

class SimpleConfig:
    def __init__(self):
        self.test_config = {
            'aug_eval': False,
            'scales': [1.0],
            'flip_horizontal': False,
            'flip_vertical': False,
            'is_slide': False,
            'crop_size': 256,
            'stride': 128
        }

cfg = SimpleConfig()
args = SimpleArgs()

ARGS = {
    'cfg': cfg,
    'args': args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_test_config Ran
ran on a synthesized input
Shun14/panopticFPN-paddle/predict.py
code served (permissive licence) · get_code("32d2a7cc8725e25e")
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 dict. 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

torch.manual_seed(0)

# Stand-in class for cfg parameter
class Config:
    def __init__(self):
        self.test_config = {
            'model': 'resnet50',
            'batch_size': 8,
            'num_workers': 4
        }

# Stand-in class for args parameter
class Args:
    def __init__(self):
        self.aug_pred = True
        self.scales = [0.5, 1.0, 1.5]
        self.flip_horizontal = True
        self.flip_vertical = False
        self.is_slide = True
        self.crop_size = 512
        self.stride = 256

ARGS = {
    'cfg': Config(),
    'args': Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
intersect Ran
ran; our contract draft was wrong, not the code
ashwath007/amenity-detection/Algo/SSD/layers/box_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from NVlabs/AL-MDN, is pointer only (licence: NOASSERTION) · get_code("f01c5f73515770a5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from NVlabs/AL-MDN, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

multibox Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ashwath007/amenity-detection/Algo/SSD/ssd.py
code served (permissive licence) · get_code("40dc7296d52276ff")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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 torch.nn as nn

torch.manual_seed(0)

# Build a VGG configuration and create vgg layers
vgg_cfg = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M', 512, 512, 512]
i = 3  # input channels (RGB)
batch_norm = False

# Create vgg layers using the vgg function from the code
def vgg_func(cfg, i, batch_norm=False):
    layers = []
    in_channels = i
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        elif v == 'C':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    pool5 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
    conv6 = nn.Conv2d(512, 1024, kernel_size=3, padding=6, dilation=6)
    conv7 = nn.Conv2d(1024, 1024, kernel_size=1)
    layers += [pool5, conv6, nn.ReLU(inplace=True), conv7, nn.ReLU(inplace=True)]
    return layers

vgg_layers = vgg_func(vgg_cfg, i, batch_norm)

# Create extra_layers
# extra_layers should have alternating structure (e.g., conv, relu, conv, relu, ...)
# We need extra_layers[1::2] to have .out_channels attribute
extra_layers = nn.ModuleList([
    nn.Conv2d(1024, 256, kernel_size=1),
    nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1),
    nn.Conv2d(512, 128, kernel_size=1),
    nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1),
    nn.Conv2d(256, 128, kernel_size=1),
    nn.Conv2d(128, 256, kernel_size=3),
    nn.Conv2d(256, 128, kernel_size=1),
    nn.Conv2d(128, 256, kernel_size=3),
])

# cfg for multibox: number of default boxes per feature map
# We need len(cfg) = 2 (for vgg_source) + len(extra_layers[1::2])
# extra_layers[1::2] has 4 elements (indices 1, 3, 5, 7)
# So cfg should have 2 + 4 = 6 elements
cfg = [4, 6, 6, 6, 4, 4]

# num_classes
num_classes = 21

ARGS = {
    'vgg': vgg_layers,
    'extra_layers': extra_layers,
    'cfg': cfg,
    'num_classes': num_classes
}
Setup block drafted by
a language model, Claude Sonnet 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 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: none by the harness; any seed is in the setup block
partition_list Ran
ran; our contract draft was wrong, not the code
Shun14/panopticFPN-paddle/paddleseg/core/predict.py
code served (permissive licence) · get_code("2f75a098ce9f7b0e")
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 list. 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 math

def partition_list(arr, m):
    """split the list 'arr' into m pieces"""
    n = int(math.ceil(len(arr) / float(m)))
    return [arr[i:i + n] for i in range(0, len(arr), n)]

# Setup code
arr = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
m = 3

ARGS = {
    "arr": arr,
    "m": m
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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: none by the harness; any seed is in the setup block
point_form Ran
ran; our contract draft was wrong, not the code
ashwath007/amenity-detection/Algo/SSD/layers/box_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from NVlabs/AL-MDN, is pointer only (licence: NOASSERTION) · get_code("3bea1addc1e14162")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from NVlabs/AL-MDN, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

vgg Ran
ran; our contract draft was wrong, not the code
ashwath007/amenity-detection/Algo/SSD/ssd.py
code served (permissive licence) · get_code("6921f7ed00595a4f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 expects:
# - cfg: a list/tuple containing integers (number of channels) and strings 'M' or 'C' for pooling
# - i: integer representing input channels
# - batch_norm: boolean flag

# Looking at the function body, cfg is iterated over and can contain:
# - 'M' or 'C' for MaxPool2d layers
# - integers for Conv2d output channels
# The function builds a VGG-style network

# Create a simple configuration
cfg = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M', 512, 512, 512]

# Input channels (typically 3 for RGB images)
i = 3

# Batch normalization flag
batch_norm = False

ARGS = {
    'cfg': cfg,
    'i': i,
    'batch_norm': batch_norm
}
Setup block drafted by
a language model, Claude Sonnet 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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
center_size Not yet run
unverified (harvested, no recorded run)
ashwath007/amenity-detection/Algo/SSD/layers/box_utils.py
code served (permissive licence) · get_code("aa1d78402838820a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 0 the same month, 11 later) and 0 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
intersect 14 other papers
5 dated earlier, 9 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
and 11 more not named here
point_form 12 other papers
3 dated earlier, 9 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
and 9 more not named here
vgg 11 other papers
4 dated earlier, 7 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1611.08563 (2016-11)
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
and 8 more not named here
center_size 9 other papers
3 dated earlier, 6 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
and 6 more not named here
partition_list 8 other papers
6 dated earlier, 2 later
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1803.06815 (2018-03)
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
and 5 more not named here
flip_combination 7 other papers
6 dated earlier, 1 later
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1803.06815 (2018-03)
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
and 4 more not named here
add_extras 6 other papers
2 dated earlier, 4 later
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1611.08563 (2016-11)
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
and 3 more not named here
get_test_config 6 other papers
5 dated earlier, 1 later
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1803.06815 (2018-03)
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
1803.08904 (2018-03)
Context Encoding for Semantic Segmentation
and 3 more not named here
get_reverse_list 4 other papers
3 dated earlier, 1 later
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1811.11431 (2018-11)
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
and 1 more not named here
get_image_list 3 other papers
2 dated earlier, 1 later
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1912.08193 (2019-12)
PointRend: Image Segmentation as Rendering
get_test_config 3 other papers
2 dated earlier, 1 later
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1912.08193 (2019-12)
PointRend: Image Segmentation as Rendering
multibox 2 other papers
2 dated earlier
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1611.08563 (2016-11)
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

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 2026-11-21.

Repositories linked to this paper

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

Abstract

The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentation (for stuff classes). However, current state-of-the-art methods for this joint task use separate and dissimilar networks for instance and semantic segmentation, without performing any shared computation. In this work, we aim to unify these methods at the architectural level, designing a single network for both tasks. Our approach is to endow Mask R-CNN, a popular instance segmentation method, with a semantic segmentation branch using a shared Feature Pyramid Network (FPN) backbone. Surprisingly, this simple baseline not only remains effective for instance segmentation, but also yields a lightweight, top-performing method for semantic segmentation. In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks. Given its effectiveness and conceptual simplicity, we hope our method can serve as a strong baseline and aid future research in panoptic segmentation.

For agents

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

get_harvested_code_for_paper("1901.02446")
get_code_for_paper("1901.02446")
have("1901.02446")

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

curl https://syntology.ai/api/ran/1901.02446.json

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

[![Syntology run record](https://syntology.ai/api/ran/1901.02446.svg)](https://syntology.ai/paper/1901.02446)

Connect an agent — have() is free.