SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.05722 · ICCV · 2021

MT-ORL: Multi-Task Occlusion Relationship Learning

Qi She, Changhu Wang, Lin Zhang, Lei Zhu, Jiaxin Li, Zijian Feng, Xuejing Kang, Anlong Ming, Panhe Feng, Chunpeng Li

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 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; 3 failures of our instrument; 3 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/2108.05722.json · badge: /api/ran/2108.05722.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
fengpanhe/MT-ORL community
Papers with Code archive
8 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("7d84d60f38fb0d41")
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, BasicBlock: 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)

# BasicBlock parameters
inplanes = 4
planes = 8
stride = 1

# Create a simple downsample module (Sequential with Conv2d and BatchNorm2d)
# This is used when stride > 1 or inplanes != planes
downsample = nn.Sequential(
    nn.Conv2d(inplanes, planes, kernel_size=1, stride=stride, bias=True),
    nn.BatchNorm2d(planes)
)

groups = 1
base_width = 64
dilation = 1
norm_layer = nn.BatchNorm2d

ARGS = {
    "inplanes": inplanes,
    "planes": planes,
    "stride": stride,
    "downsample": downsample,
    "groups": groups,
    "base_width": base_width,
    "dilation": dilation,
    "norm_layer": norm_layer
}
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 BasicBlock — 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 BasicBlock 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
BasicDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("4599862b7af845ff")
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, BasicDecoder: 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 collections import OrderedDict

torch.manual_seed(0)

class ConvBnRelu(torch.nn.Sequential):

    def __init__(self, in_planes, out_planes, kernel_size, bias=False, stride=1, groups=1):
        padding = (kernel_size - 1) // 2
        super(ConvBnRelu, self).__init__(OrderedDict([('conv', torch.nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding=padding, groups=groups, bias=bias)), ('bn', torch.nn.BatchNorm2d(out_planes)), ('relu', torch.nn.ReLU(inplace=True))]))

ARGS = {
    'feature_channels': [512, 256, 128, 64, 32],
    'half_feature_channels': True,
    'feature_scales': [16, 8, 4, 2, 1],
    'path_name': 'boundary',
    'num_end_out': 1,
    'use_pixel_shuffle': False,
    'lite': False
}
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 BasicDecoder — 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 BasicDecoder 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
ConvBnRelu Ran
ran on a synthesized input · constructed an object; no result was computed
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("393cb9bed080f6d1")
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, ConvBnRelu: 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
from collections import OrderedDict

torch.manual_seed(0)

ARGS = {
    'in_planes': 3,
    'out_planes': 16,
    'kernel_size': 3,
    'bias': False,
    'stride': 1,
    'groups': 1
}
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 ConvBnRelu — 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 ConvBnRelu output the recorded ndim 1 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
ResNet Ran
ran on a synthesized input · constructed an object; no result was computed
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("4b06e193d47a0bfe")
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, ResNet: 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 typing import List, Optional, Callable, Type, Union

torch.manual_seed(0)

def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=True)

def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=True)

class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(self, inplanes: int, planes: int, stride: int=1, downsample: Optional[nn.Module]=None, groups: int=1, base_width: int=64, dilation: int=1, norm_layer: Optional[Callable[..., nn.Module]]=None) -> None:
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError('Dilation > 1 not supported in BasicBlock')
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out

class Bottleneck(nn.Module):
    expansion: int = 4

    def __init__(self, inplanes: int, planes: int, stride: int=1, downsample: Optional[nn.Module]=None, groups: int=1, base_width: int=64, dilation: int=1, norm_layer: Optional[Callable[..., nn.Module]]=None) -> None:
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.0)) * groups
        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride, groups, dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.bn3(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out

ARGS = {
    "block": BasicBlock,
    "layers": [2, 2, 2, 2],
    "zero_init_residual": False,
    "groups": 1,
    "width_per_group": 64,
    "replace_stride_with_dilation": None,
    "norm_layer": None,
    "deep_stem": False,
}
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 ResNet — 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 ResNet 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from sajaddarabi/BiRealNet
pointer only; the stored copy get_code serves, from sajaddarabi/BiRealNet, is pointer only (licence: NONE) · get_code("d5cd7ffe2dc51b21")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("1907f2ae25449f39")
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 Conv2d. 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 = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
crop Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("e46e7885a2f69495")
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 4) 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

torch.manual_seed(0)

# Create two 4D tensors (batch_size, channels, height, width)
# data1: batch=2, channels=4, height=5, width=6
data1 = torch.randn(2, 4, 5, 6)

# data2: batch=2, channels=4, height=3, width=4
data2 = torch.randn(2, 4, 3, 4)

ARGS = {
    "data1": data1,
    "data2": data2,
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 4) — shape (2, 4, 3, 4) 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
opm Ran
ran on a synthesized input
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("f3e25256bbd3d5b9")
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; 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 numpy as np

INIT_ARGS = {
    'planes': 4,
    'kernel_size1': 1,
    'kernel_size2': 3
}

# Create input tensor with shape (batch_size=2, channels=4, height=8, width=6)
input_tensor = torch.randn(2, 4, 8, 6)

ARGS = {
    'a': input_tensor
}
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 Tensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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)
osm Ran
ran on a synthesized input · constructed an object; no result was computed
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("e41bfdefe9e57601")
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, osm: 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 collections import OrderedDict

torch.manual_seed(0)

class ConvBnRelu(torch.nn.Sequential):

    def __init__(self, in_planes, out_planes, kernel_size, bias=False, stride=1, groups=1):
        padding = (kernel_size - 1) // 2
        super(ConvBnRelu, self).__init__(OrderedDict([('conv', torch.nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding=padding, groups=groups, bias=bias)), ('bn', torch.nn.BatchNorm2d(out_planes)), ('relu', torch.nn.ReLU(inplace=True))]))

def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=True)

def crop(data1, data2):
    _, _, h1, w1 = data1.size()
    _, _, h2, w2 = data2.size()
    if h1 == h2 and w1 == w2:
        return data1
    if h1 < h2 or w1 < w2:
        pad_h = (h2 - h1) // 2 + 1
        pad_h = pad_h if pad_h > 0 else 0
        pad_w = (w2 - w1) // 2 + 1
        pad_w = pad_w if pad_w > 0 else 0
        data1 = torch.nn.ConstantPad2d((pad_w, pad_w, pad_h, pad_h), 0)(data1)
        _, _, h1, w1 = data1.size()
    assert h2 <= h1 and w2 <= w1
    offset_h = (h1 - h2) // 2
    offset_w = (w1 - w2) // 2
    data = data1[:, :, offset_h:offset_h + h2, offset_w:offset_w + w2]
    return data

class osm(nn.Module):

    def __init__(self, feature_channels=[2048, 1024], upsample_scale_factors=[2, 1]):
        super(osm, self).__init__()
        self.side_convs = nn.ModuleList()
        out_channels = feature_channels[-1]
        for channels, scale_factor in zip(feature_channels, upsample_scale_factors):
            layers = OrderedDict()
            layers['conv1'] = ConvBnRelu(channels, channels, 3)
            layers['conv2'] = ConvBnRelu(channels, channels, 3)
            layers['conv3'] = torch.nn.Sequential(conv1x1(channels, out_channels), nn.BatchNorm2d(out_channels))
            if scale_factor > 1:
                layers['upsample'] = nn.Upsample(scale_factor=scale_factor, mode='bilinear', align_corners=True)
            self.side_convs.append(nn.Sequential(layers))
        self.conv_end = nn.Sequential(ConvBnRelu(out_channels * len(feature_channels), out_channels, 1), ConvBnRelu(out_channels, out_channels, 3), ConvBnRelu(out_channels, out_channels, 3))

    def forward(self, inputs):
        x_list = [convs(feat) for feat, convs in zip(inputs, self.side_convs)]
        x_list = [crop(x, x_list[-1]) for x in x_list]
        x = self.conv_end(torch.cat(x_list, 1))
        return x

ARGS = {
    'feature_channels': [2048, 1024],
    'upsample_scale_factors': [2, 1]
}
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 osm — 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 osm 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
Bottleneck Not yet run
unverified (harvested, no recorded run)
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("f38bd74e313761e2")
How it ran

no invocation recorded.

OPNet Not yet run
unverified (harvested, no recorded run)
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("8748c711a5242771")
How it ran

no invocation recorded.

resnet Not yet run
unverified (harvested, no recorded run)
fengpanhe/MT-ORL/mtorl/models/opnet.py
code served (permissive licence) · get_code("a9f9489bc35bba93")
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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 8 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
conv3x3
brick of this paper's assembly: helper
74 other papers
27 dated earlier, 47 later · 5 only as an assembly brick
1605.07146 (2016-05)
Wide Residual Networks
1707.01629 (2017-07)
Dual Path Networks
1802.05668 (2018-02)
Model compression via distillation and quantization
and 71 more not named here
BasicBlock
brick of this paper's assembly: helper
9 other papers
1 dated earlier, 8 later · 4 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2303.15555 (2023-03)
Object Discovery from Motion-Guided Tokens
2304.03560 (2023-04)
DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium
and 6 more not named here
conv1x1
brick of this paper's assembly: helper
9 other papers
2 dated earlier, 7 later
1808.00278 (2018-08)
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
1812.11800 (2018-12)
Regularized Binary Network Training
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
and 6 more not named here
Bottleneck
brick of this paper's assembly: helper
8 other papers
1 dated earlier, 7 later · 4 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2303.15555 (2023-03)
Object Discovery from Motion-Guided Tokens
2306.10014 (2023-06)
Coaching a Teachable Student
and 5 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

Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image. We observe two key issues in existing works: firstly, lack of an architecture which can exploit the limited amount of coupling in the decoder stage between the two subtasks, namely occlusion boundary extraction and occlusion orientation prediction, and secondly, improper representation of occlusion orientation. In this paper, we propose a novel architecture called Occlusion-shared and Path-separated Network (OPNet), which solves the first issue by exploiting rich occlusion cues in shared high-level features and structured spatial information in task-specific low-level features. We then design a simple but effective orthogonal occlusion representation (OOR) to tackle the second issue. Our method surpasses the state-of-the-art methods by 6.1%/8.3% Boundary-AP and 6.5%/10% Orientation-AP on standard PIOD/BSDS ownership datasets. Code is available at https://github.com/fengpanhe/MT-ORL.

For agents

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

get_harvested_code_for_paper("2108.05722")
get_code_for_paper("2108.05722")
have("2108.05722")

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

curl https://syntology.ai/api/ran/2108.05722.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.05722.svg)](https://syntology.ai/paper/2108.05722)

Connect an agent — have() is free.