SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.09903 · IJCAI · 2022

Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

Junwei Han, Chunbo Lang, Binfei Tu

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 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; 8 failures of our instrument; 1 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/2204.09903.json · badge: /api/ran/2204.09903.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
chunbolang/DCP marked official in Papers with Code
Papers with Code archive
11 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
ASPP Ran
ran on a synthesized input · constructed an object; no result was computed
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("deb925d25beba09d")
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, ASPP: 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 torch import nn

torch.manual_seed(0)

# ASPP only takes out_channels as a parameter
# Looking at the forward method, it expects input x to be a 4D tensor (batch, channels, height, width)
# The out_channels parameter determines the number of input/output channels for all conv layers

ARGS = {
    'out_channels': 256,
}
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 ASPP — 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 ASPP 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 Ran
ran on a synthesized input · constructed an object; no result was computed
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("9b6cbc9dee558bd7")
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, Bottleneck: 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)

# Create a small downsample module that will be used in the forward pass
# The downsample is called with x and should return a tensor of matching shape
downsample_module = nn.Sequential(
    nn.Conv2d(64, 256, kernel_size=1, stride=2, bias=False),
    nn.BatchNorm2d(256)
)

ARGS = {
    "inplanes": 64,
    "planes": 64,
    "stride": 2,
    "downsample": downsample_module
}
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 Bottleneck — 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 Bottleneck 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
ResNet Ran
ran on a synthesized input · constructed an object; no result was computed
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("2da49133aa591f02")
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

torch.manual_seed(0)

# Define a minimal block class that ResNet expects
class BasicBlock(nn.Module):
    expansion = 1
    
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(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

ARGS = {
    'block': BasicBlock,
    'layers': [2, 2, 2, 2],
    'num_classes': 1000,
    'deep_base': True,
}
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
VGG Ran
ran on a synthesized input · constructed an object; no result was computed
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("7aefeb45456c2c53")
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, VGG: 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)

# Build a minimal features module that outputs 512 channels
# The VGG.forward expects features to output a tensor with 512 channels
# since classifier expects 512 * 7 * 7 input features
features = nn.Sequential(
    nn.Conv2d(3, 64, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(64, 128, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(128, 256, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(256, 512, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(512, 512, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
)

ARGS = {
    "features": features,
    "num_classes": 1000,
    "init_weights": True,
}
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 VGG — 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 VGG 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
Weighted_GAP Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from YanFangCS/CyCTR-Pytorch
pointer only; the stored copy get_code serves, from YanFangCS/CyCTR-Pytorch, is pointer only (licence: NONE) · get_code("df77cb77dfe58d6d")
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.

get_vgg16_layer Ran
ran; our contract draft was wrong, not the code
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("ad7ba6c4e516607e")
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 torch
from torch import nn

torch.manual_seed(0)

# Create a minimal VGG16-like model with a features attribute
# The function accesses model.features[idx] for idx in range(0, 43)
# So we need at least 43 layers in the features module

class MinimalVGG16(nn.Module):
    def __init__(self):
        super().__init__()
        # Create 43 simple layers to satisfy the indexing requirements
        layers = []
        for i in range(43):
            layers.append(nn.Conv2d(3, 3, kernel_size=3, padding=1))
        self.features = nn.Sequential(*layers)
    
    def forward(self, x):
        return self.features(x)

model = MinimalVGG16()

ARGS = {
    "model": model
}
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 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
make_layers Ran
ran; our contract draft was wrong, not the code
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("3817cebff2add9fb")
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 Sequential. 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 torch import nn

torch.manual_seed(0)

BatchNorm = nn.BatchNorm2d

cfg_dict = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M']
}

ARGS = {
    'cfg': cfg_dict['A'],
    'batch_norm': 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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
resnet101 Ran
ran; our contract draft was wrong, not the code
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("ae93e3b60685c29d")
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 ResNet. 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 torch import nn

torch.manual_seed(0)

ARGS = {
    'pretrained': 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 — a ResNet output has no array shape of its own; none 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
resnet152 Ran
ran; our contract draft was wrong, not the code
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("bacf5d53a01d1e64")
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 ResNet. 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 torch import nn

torch.manual_seed(0)

# Define ARGS dict for resnet152 function
ARGS = {
    'pretrained': 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 — a ResNet output has no array shape of its own; none 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
resnet50 Ran
ran; our contract draft was wrong, not the code
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("a5b336b54939f4de")
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 ResNet. 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 torch import nn
import os
import tempfile

torch.manual_seed(0)

# Create a temporary directory for the mock model file
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, 'initmodel'), exist_ok=True)

# Create a mock pretrained weights file
mock_model_path = os.path.join(temp_dir, 'initmodel', 'resnet50_v2.pth')
mock_state_dict = {}
torch.save(mock_state_dict, mock_model_path)

# Patch the model path in the resnet50 function context
import sys
sys.path.insert(0, temp_dir)

ARGS = {
    'pretrained': 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 — a ResNet output has no array shape of its own; none 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
vgg16 Ran
ran; our contract draft was wrong, not the code
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("0902796de5cc0ba5")
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 VGG. 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 torch import nn

torch.manual_seed(0)

ARGS = {
    'pretrained': 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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
vgg16_bn Ran
ran; our contract draft was wrong, not the code
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("7495062bfa6820b8")
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 VGG. 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 torch import nn

torch.manual_seed(0)

ARGS = {
    'pretrained': 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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
OneModel Not yet run
unverified (harvested, no recorded run)
chunbolang/DCP/model/DCP.py
code served (permissive licence) · get_code("c7581a28a77f6859")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 4 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
Weighted_GAP
brick of this paper's assembly: helper
12 other papers
3 dated earlier, 9 later
2106.02320 (2021-06)
Few-Shot Segmentation via Cycle-Consistent Transformer
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
and 9 more not named here
get_vgg16_layer
brick of this paper's assembly: helper
6 other papers
2 dated earlier, 4 later
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
2311.17626 (2023-11)
Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation
and 3 more not named here
make_layers
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
2402.17726 (2024-02)
VRP-SAM: SAM with Visual Reference Prompt
and 2 more not named here
Bottleneck
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2104.02243 (2021-04)
3D-to-2D Distillation for Indoor Scene Parsing
2104.02613 (2021-04)
Mutual Graph Learning for Camouflaged Object Detection
resnet101
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2104.02243 (2021-04)
3D-to-2D Distillation for Indoor Scene Parsing
2104.02613 (2021-04)
Mutual Graph Learning for Camouflaged Object Detection
resnet152
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2104.02243 (2021-04)
3D-to-2D Distillation for Indoor Scene Parsing
2104.02613 (2021-04)
Mutual Graph Learning for Camouflaged Object Detection
VGG
brick of this paper's assembly: helper
1 other paper
1 later
2402.17726 (2024-02)
VRP-SAM: SAM with Visual Reference Prompt

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

Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasoning scheme is first implemented on the annotated support image, and then the coarse segmentation mask is divided into multiple regions with different properties. Leveraging effective masked average pooling operations, a series of support-induced proxies are thus derived, each playing a specific role in conquering the above challenges. Moreover, we devise a unique parallel decoder structure that integrates proxies with similar attributes to boost the discrimination power. Our proposed approach, named divideand-conquer proxies (DCP), allows for the development of appropriate and reliable information as a guide at the "episode" level, not just about the object cues themselves. Extensive experiments on PASCAL-5 i and COCO-20 i demonstrate the superiority of DCP over conventional prototype-based approaches (up to 5 ∼10% on average), which also establishes a new state-of-the-art. Code is available at github.com/chunbolang/DCP.

For agents

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

get_harvested_code_for_paper("2204.09903")
get_code_for_paper("2204.09903")
have("2204.09903")

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

curl https://syntology.ai/api/ran/2204.09903.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.09903.svg)](https://syntology.ai/paper/2204.09903)

Connect an agent — have() is free.