SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.05293 · 2021

Few-Shot Segmentation with Global and Local Contrastive Learning

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 10 failures of our instrument; 2 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/2108.05293.json · badge: /api/ran/2108.05293.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
liuweide01/GQNet-Few-shot-segmentation canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
FunctionStatusWhere it lives
Weighted_GAP Ran
ran; our contract draft was wrong, not the code
liuweide01/GQNet-Few-shot-segmentation/model/PFENet.py
pointer only (licence: MIT); 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 link allows the body inline (MIT), but get_code serves the stored copy, first harvested from YanFangCS/CyCTR-Pytorch, and GitHub detected no licence in that repository when it was checked. 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.

colorize Ran
ran, honoured the contract we drafted
liuweide01/GQNet-Few-shot-segmentation/util/util.py
pointer only (licence: MIT); the stored copy get_code serves, from Cavendish518/SFPNet, is pointer only (licence: NOASSERTION) · get_code("1dad93b61e98c32e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Cavendish518/SFPNet, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
liuweide01/GQNet-Few-shot-segmentation/model/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. 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
liuweide01/GQNet-Few-shot-segmentation/model/PFENet.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
intersectionAndUnion Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liuweide01/GQNet-Few-shot-segmentation/util/util.py
pointer only (licence: MIT); the stored copy get_code serves, from Cavendish518/SFPNet, is pointer only (licence: NOASSERTION) · get_code("2a66f4ab6863908c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Cavendish518/SFPNet, 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.

is_image_file Ran
ran, violated the contract we drafted
liuweide01/GQNet-Few-shot-segmentation/util/dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from sam1224/aenet, is pointer only (licence: NOASSERTION) · get_code("0684a938c70bf564")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sam1224/aenet, 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.

load_cfg_from_cfg_file Ran
ran; our contract draft was wrong, not the code
liuweide01/GQNet-Few-shot-segmentation/util/config.py
code served (permissive licence) · get_code("277a13798d6d6981")
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 CfgNode. 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 tempfile
import os
import yaml

# Create a temporary YAML file for testing
temp_dir = tempfile.mkdtemp()
yaml_file = os.path.join(temp_dir, "config.yaml")

# Create a valid YAML config file with the expected structure
config_data = {
    "model": {
        "name": "test_model",
        "layers": 3,
        "hidden_dim": 64
    },
    "training": {
        "learning_rate": 0.001,
        "batch_size": 32,
        "epochs": 10
    },
    "data": {
        "dataset": "cifar10",
        "split": 0.8
    }
}

with open(yaml_file, 'w') as f:
    yaml.dump(config_data, f)

ARGS = {
    "file": yaml_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
make_dataset Ran
ran on a synthesized input
liuweide01/GQNet-Few-shot-segmentation/util/dataset.py
code served (permissive licence) · get_code("2b6740339633d440")
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 numpy as np
import cv2

# Create a temporary directory and files for testing
temp_dir = tempfile.mkdtemp()

# Create a dummy data list file
data_list_file = os.path.join(temp_dir, "data_list.txt")
with open(data_list_file, 'w') as f:
    f.write("image1.png label1.png\n")
    f.write("image2.png label2.png\n")

# Create dummy image and label files
image1_path = os.path.join(temp_dir, "image1.png")
label1_path = os.path.join(temp_dir, "label1.png")
image2_path = os.path.join(temp_dir, "image2.png")
label2_path = os.path.join(temp_dir, "label2.png")

# Create sample label images with specific class values
# Label 1: contains class 1 and 2 with enough pixels (>= 2*32*32 = 2048)
label1 = np.zeros((256, 256), dtype=np.uint8)
label1[0:100, 0:100] = 1  # 10000 pixels of class 1
label1[100:200, 100:200] = 2  # 10000 pixels of class 2
cv2.imwrite(label1_path, label1)

# Label 2: contains class 3 with enough pixels
label2 = np.zeros((256, 256), dtype=np.uint8)
label2[0:150, 0:150] = 3  # 22500 pixels of class 3
cv2.imwrite(label2_path, label2)

# Create dummy image files (content doesn't matter for this function)
image1 = np.zeros((256, 256, 3), dtype=np.uint8)
cv2.imwrite(image1_path, image1)

image2 = np.zeros((256, 256, 3), dtype=np.uint8)
cv2.imwrite(image2_path, image2)

ARGS = {
    'split': 0,
    'data_root': temp_dir,
    'data_list': data_list_file,
    'sub_list': [1, 2, 3]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, tqdm — 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
liuweide01/GQNet-Few-shot-segmentation/model/vgg.py
code served (permissive licence) · get_code("e31250b969b51841")
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
import torch.nn as nn

torch.manual_seed(0)

# Define the cfg dict from the function
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']
}

# Test with a simple configuration list
test_cfg = [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M']

ARGS = {
    'cfg': test_cfg,
    '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
resnet18 Ran
ran; our contract draft was wrong, not the code
liuweide01/GQNet-Few-shot-segmentation/model/resnet.py
code served (permissive licence) · get_code("0d5305ea0adc2098")
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
import torch.nn as 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
resnet34 Ran
ran; our contract draft was wrong, not the code
liuweide01/GQNet-Few-shot-segmentation/model/resnet.py
code served (permissive licence) · get_code("f8bf3c22835aea80")
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
import torch.nn as 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
vgg11 Ran
ran; our contract draft was wrong, not the code
liuweide01/GQNet-Few-shot-segmentation/model/vgg.py
pointer only (licence: MIT); the stored copy get_code serves, from sam1224/hmnet, is pointer only (licence: NOASSERTION) · get_code("2067e75510fbe85e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sam1224/hmnet, 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.

vgg11_bn Ran
ran; our contract draft was wrong, not the code
liuweide01/GQNet-Few-shot-segmentation/model/vgg.py
pointer only (licence: MIT); the stored copy get_code serves, from sam1224/hmnet, is pointer only (licence: NOASSERTION) · get_code("bf96fb236a6b1683")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sam1224/hmnet, 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.

intersectionAndUnionGPU Not yet run
unverified (harvested, no recorded run)
liuweide01/GQNet-Few-shot-segmentation/util/util.py
pointer only (licence: MIT); the stored copy get_code serves, from Cavendish518/SFPNet, is pointer only (licence: NOASSERTION) · get_code("136834d66336e6b9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Cavendish518/SFPNet, 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. No invocation recorded.

merge_cfg_from_list Not yet run
unverified (harvested, no recorded run)
liuweide01/GQNet-Few-shot-segmentation/util/config.py
pointer only (licence: MIT); the stored copy get_code serves, from sam1224/aenet, is pointer only (licence: NOASSERTION) · get_code("b925dc5fd8492c34")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sam1224/aenet, 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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 14 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 3 the same month, 14 later) and 1 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 686 other papers
329 dated earlier, 3 the same month, 348 later, 6 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet18 89 other papers
35 dated earlier, 1 the same month, 51 later, 2 same year, order not determinable
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 86 more not named here
resnet34 53 other papers
28 dated earlier, 1 the same month, 22 later, 2 same year, order not determinable
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 50 more not named here
merge_cfg_from_list 23 other papers
1 dated earlier, 22 later
2003.13328 (2020-03)
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
2111.15174 (2021-11)
CRIS: CLIP-Driven Referring Image Segmentation
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
and 20 more not named here
load_cfg_from_cfg_file 22 other papers
1 dated earlier, 21 later
2003.13328 (2020-03)
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
2111.15174 (2021-11)
CRIS: CLIP-Driven Referring Image Segmentation
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
and 19 more not named here
Weighted_GAP 12 other papers
1 dated earlier, 11 later
2106.02320 (2021-06)
Few-Shot Segmentation via Cycle-Consistent Transformer
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
2204.09903 (2022-04)
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation
and 9 more not named here
intersectionAndUnion 11 other papers
1 dated earlier, 9 later, 1 same year, order not determinable
2004.01658 (2020-04)
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Huang_PrimitiveNet_Primitive_Instance_Segmentation_With_Local_Primitive_Embedding_Under_Adversarial_ICCV_2021_paper (2021 (year only))
PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric
2203.09065 (2022-03)
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
and 8 more not named here
vgg11 10 other papers
2 dated earlier, 8 later
1610.02391 (2016-10)
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
136780474 (2022 (year only))
Hourglass Attention Network for Image Inpainting
and 7 more not named here
intersectionAndUnionGPU 9 other papers
9 later
2203.14508 (2022-03)
Stratified Transformer for 3D Point Cloud Segmentation
2210.06780 (2022-10)
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
2212.02011 (2022-12)
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
and 6 more not named here
vgg11_bn 9 other papers
1 dated earlier, 8 later
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
136780474 (2022 (year only))
Hourglass Attention Network for Image Inpainting
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
and 6 more not named here
get_vgg16_layer 6 other papers
6 later
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
2204.09903 (2022-04)
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation
2311.17626 (2023-11)
Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation
and 3 more not named here
is_image_file 5 other papers
1 dated earlier, 4 later
2003.13328 (2020-03)
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
2210.06780 (2022-10)
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
and 2 more not named here
make_layers 5 other papers
5 later
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
2204.09903 (2022-04)
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation
2402.17726 (2024-02)
VRP-SAM: SAM with Visual Reference Prompt
and 2 more not named here
colorize 4 other papers
4 later
2203.14508 (2022-03)
Stratified Transformer for 3D Point Cloud Segmentation
2210.06780 (2022-10)
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
2303.12766 (2023-03)
Spherical Transformer for LiDAR-based 3D Recognition
and 1 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

In this work, we address the challenging task of few-shot segmentation. Previous few-shot segmentation methods mainly employ the information of support images as guidance for query image segmentation. Although some works propose to build cross-reference between support and query images, their extraction of query information still depends on the support images. We here propose to extract the information from the query itself independently to benefit the few-shot segmentation task. To this end, we first propose a prior extractor to learn the query information from the unlabeled images with our proposed global-local contrastive learning. Then, we extract a set of predetermined priors via this prior extractor. With the obtained priors, we generate the prior region maps for query images, which locate the objects, as guidance to perform cross interaction with support features. In such a way, the extraction of query information is detached from the support branch, overcoming the limitation by support, and could obtain more informative query clues to achieve better interaction. Without bells and whistles, the proposed approach achieves new state-of-the-art performance for the few-shot segmentation task on PASCAL-5$^{i}$ and COCO datasets.

For agents

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

get_harvested_code_for_paper("2108.05293")
get_code_for_paper("2108.05293")
have("2108.05293")

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

curl https://syntology.ai/api/ran/2108.05293.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.05293.svg)](https://syntology.ai/paper/2108.05293)

Connect an agent — have() is free.