OSCR

Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition.

Code ↔ Paper

4 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 4 matches · 2 of them tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted
  1. [1] § 4. Experiments › 4.2. Implementation Details ↔ config.py, the whole file · a weak match · score 0.93 · Aircraft Fewshot, weight decay, decay step, TieredImagenet, miniImageNet, FS
  2. [2] § 4. Experiments › 4.4. Ablation Study ↔ config.py, the whole file · a weak match · score 0.65 · Expand Ratio, Confidence Ratio, TieredImagenet, algorithm, BPIAL, class
  3. [3] § 4. Experiments › 4.2. Implementation Details ↔ main.py, lines 45–138 · score 0.63 · weight decay, meta training, epochs, optimizer, benchmarks, accuracy
  4. [4] § 3. Methodology › 3.3. Binocular Sensing Extractor Module (BSEM) ↔ models/vision_res12_le.py, lines 124–183 · score 0.52 · vision layer, vision res12, batch, Module

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 120 lines · 7.2 KB · CC-BY-NC-4.0 · 2 matches

  1. # +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
  2. # Author: CHAOFEI QI
  3. # Email: [email hidden]
  4. # Address： Harbin Institute of Technology
  5. #
  6. # Copyright (c) 2024
  7. # This source code is licensed under the MIT-style license found in the
  8. # LICENSE file in the root directory of this source tree
  9. # +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
  10. import argparse
  12. def config():
  13. parser = argparse.ArgumentParser(description='Train image model with cross entropy loss')
  14. # ************************************************************
  15. # Datasets (general)
  16. # ************************************************************
  17. parser.add_argument('-d', '--dataset', type=str, default='miniImageNet')
  18. parser.add_argument('--load', default=False)
  19. parser.add_argument('-j', '--workers', default=8, type=int, help="number of data loading workers (default: 4)") # 11-2
  20. parser.add_argument('--height', type=int, default=84, help="height of an image (default: 84)")
  21. parser.add_argument('--width', type=int, default=84, help="width of an image (default: 84)")
  23. # ************************************************************
  24. # Miscs
  25. # ************************************************************
  26. parser.add_argument('--scale_cls', type=int, default=7)
  27. parser.add_argument('--save-dir', type=str)
  28. parser.add_argument('--resume', type=str, default=None, metavar='PATH')
  29. parser.add_argument('-g', '--gpu-devices', default='0', type=str)
  30. parser.add_argument('--checkpoint', default=False)
  32. # ************************************************************
  33. # BPIAL parameters
  34. # ************************************************************
  35. parser.add_argument('--classifier', type=str, default='lr')
  36. parser.add_argument('--disparity', type=str, default='js')
  37. parser.add_argument("--T", type=float, default=4.0)
  38. parser.add_argument('--lembed', type=str, default='se')
  39. parser.add_argument('--rembed', type=str, default='se')
  40. parser.add_argument('--emb_dim', type=int, default=5)
  41. parser.add_argument('--logit_penalty', type=float, default=0.5)
  42. parser.add_argument('--confidence_ratio', type=float, default=0.6)
  43. parser.add_argument("--method", type=str, choices=['1','2','3'], default='2') # Input method
  44. parser.add_argument("--FFT_sign", default=False) # Input method
  45. parser.add_argument("--Elastic", type=str, default='1', choices=['0','1'], help='elastic_constraint') # [0(Flase),1(True)]
  47. parser.add_argument("--weights", type=str, default="1-1-1")
  48. parser.add_argument("--fit_mode", type=str, default="db", choices=['db'])
  49. parser.add_argument('--expand_ratio', type=float, default=0.5)
  50. parser.add_argument("--stereopsis", type=str, default="intersection", choices=['intersection','union','le','re'])
  51. parser.add_argument("--expand_style", type=str, default="linear", choices=['linear'])
  53. # ************************************************************
  54. # FewShot settting
  55. # ************************************************************
  56. parser.add_argument('--mode', type=str, default='train')
  57. parser.add_argument('--phase', default='test', type=str, help='use test or val dataset to early stop')
  59. parser.add_argument('--n_train_ways', type=int, default=15, metavar='N', help='Number of classes for doing each classification run')
  60. parser.add_argument('--train_nTestNovel', type=int, default=7 * 15, help='number of test examples for all the novel category when training')
  62. parser.add_argument('--nKnovel', type=int, default=5, help='number of novel categories')
  63. parser.add_argument('--meta_nTestNovel', type=int, default=7 * 5, help='number of test examples for all the novel category when training')
  64. parser.add_argument('--nExemplars', type=int, default=5, help='number of training examples per novel category.')
  65. parser.add_argument('--unlabel', type=int, default=0)
  66. parser.add_argument('--nTestNovel', type=int, default=15 * 5, help='number of test examples for all the novel category')
  68. parser.add_argument('--start-epoch', default=0, type=int, help="manual epoch number (useful on restarts)")
  69. parser.add_argument('--max-epoch', default=90, type=int, help="maximum epochs to run")
  70. parser.add_argument('--stepsize', default=[60], nargs='+', type=int, help="stepsize to decay learning rate")
  72. parser.add_argument('--train_epoch_size', type=int, default=1200, help='number of batches per epoch when training')
  73. parser.add_argument('--epoch_size', type=int, default=2000, help='number of batches per epoch')
  75. parser.add_argument('--test-batch', default=1, type=int, help="test batch size")
  76. parser.add_argument('--train-batch', default=2, type=int, help="train batch size") # 11-11
  78. # ************************************************************
  79. # Optimization options
  80. # ************************************************************
  81. parser.add_argument('--optim', type=str, default='SGD', help="optimization algorithm (see optimizers.py)") # sgd,SGD
  82. parser.add_argument('--lr', '--learning-rate', default=0.1, type=float, help="initial learning rate") # 初始学习率
  83. parser.add_argument("--decay_step", type=int, default=40)
  84. parser.add_argument('--LUT_lr', default=[(60, 0.1), (80, 0.006), (90, 0.0012)], help="multistep to decay learning rate") # optim='sgd'时使用
  85. parser.add_argument('--weight-decay', default=5e-04, type=float, help="weight decay (default: 5e-04)")
  87. # ************************************************************
  88. # DistributedDataParallel
  89. # ************************************************************
  90. parser.add_argument('--amp_opt_level', type=str, default='O0', choices=['O0', 'O1', 'O2'], help='mixed precision opt level, if O0, no amp is used')
  91. parser.add_argument("--seed", default='1', type=str)
  93. # ***********************************************************
  94. args = parser.parse_args()
  96. args.w = [float(i) for i in args.weights.split('-')]
  97. args.train_epoch_size= int(600*args.train_batch)
  99. if args.dataset=='CIFARFS':
  100. args.num_classes = 64
  101. args.dataset_dir = '/home/ssdData/qcfData/fs_benchmarks/CIFARFS/'
  102. elif args.dataset=='CUB_Croped':
  103. args.num_classes = 100
  104. args.dataset_dir = '/home/ssdData/qcfData/fs_benchmarks/CUB_fewshot_cropped'
  105. elif args.dataset=='Aircraft':
  106. args.num_classes = 50
  107. args.dataset_dir = '/home/ssdData/qcfData/fs_benchmarks/Aircraft_fewshot/'
  108. elif args.dataset=='TieredImagenet':
  109. args.num_classes = 351
  110. args.train_epoch_size = 13980
  111. args.max_epoch = 120
  112. args.LUT_lr = [(30, 0.1), (60, 0.01), (90, 0.001),(120, 0.0001)]
  113. args.dataset_dir = '/home/ssdData/qcfData/fs_benchmarks/TieredImagenet_224'
  114. elif args.dataset=='MiniImagenet':
  115. args.num_classes = 64
  116. args.dataset_dir = '/home/ssdData/qcfData/fs_benchmarks/mini_imagenet_full_size/mini_imagenet_full_size'
  117. else:
  118. print("No dataset supported.")
  120. return args

config.py at commit 6257dff, under CC-BY-NC-4.0 · at the source

Overview

Authors: Chaofei Qi1, Peng Li2, Weiyang Lin3
ORCID iDs: Chaofei Qi, Weiyang Lin
  1. Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China
  2. School of Mechanical Engineering and Automation, Harbin Institute of Technology Shenzhen, Shenzhen 518055, China
  3. Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150001, China
Institutions: Harbin Institute of Technology (China)
Journal: Biomimetics (Basel, Switzerland), volume 11, issue 7, article 505
Dates: received 4 June 2026; accepted 15 July 2026; published online 18 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/biomimetics11070505 · PMID 42505538 · PMCID PMC13406620 · OpenAlex W4416286067
Open access: gold, a free copy (OpenAlex)
Preprint: doi:10.2139/ssrn.5760726
Status: code verified
Categories: human (organism), cognitive (subfield)
Methods: Statistics, Spectral & time-frequency, Physiology & signal measures
Keywords: Machine visual Meta-Learning, humanoid visual meta-learning, binocular sensing, instance authentication, few-shot learning
Topic: Domain Adaptation and Few-Shot Learning (Artificial Intelligence, Computer Science), according to OpenAlex
Funding: Key Science & Technology Project of Anhui Province (202423h08050002); National Natural Science Foundation of China (62473116)
Citations: not cited yet (Europe PMC); 70 references in the paper

Abstract

Humans possess unique advantages in dealing with few-shot visual recognition scenarios, inspiring the development of meta-learning methods aimed at emulating these abilities. Current mainstream meta-learning primarily utilizes the monocular vision or the dual asymmetric complementary architectures, collectively referred to as Machine-visual Meta-Learning (MvML). Nevertheless, research has not yet developed an architecture for simulating the human binocular visual system, named Humanoid-visual Meta-Learning (HvML). This paper innovatively proposes an excellent paradigm BPIAL belonging to the HvML: Binocular Perception Instance Authentication Learning, which can alleviate the monocular shallowness and dual-branch processing instability of MvML. Structurally, our BPIAL comprises two interconnected binocular perception and information processing modules: BSEM and IAPM. The former module can simulate binocular visual field extraction, feature extraction and compression, and channel dimension reduction, while IAPM can simulate the logic, reasoning, and judgment processes of the two human visual branches and the brain. We have demonstrated the feasibility and correctness of BPIAL on five benchmarks. Sufficient and comparative experiments with the state-of-the-art methods have proved its superiority and effectiveness.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above, with 4 matches between paragraphs and lines of code.

ChaofeiQI/BPIAL

License: CC-BY-NC-4.0
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 6257dffa14c0f77d4eefec363ff86d7921f6d14a, 30 July 2025
Languages: Python (32), Shell (2)
Size: 57 files, 34 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README, license file
Not found: CITATION.cff, environment file, tests, continuous integration, documentation
Tools: PyTorch (22 files), NumPy (6 files), Pillow (5 files), scikit-learn (2 files), SciPy (2 files)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
36 files
At the source: github.com/ChaofeiQI/BPIAL

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 34 scripts, each with its path and the digest of its content;
  • 4 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The data is available at https://github.com/ChaofeiQI/BPIAL (accessed on 14 July 2026).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 5 keywords, 2 funders, 49 references.

Cite

This paper

Qi, C., Li, P., & Lin, W. (2026). Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition. Biomimetics (Basel, Switzerland), 11(7), 505. https://doi.org/10.3390/biomimetics11070505

BibTeX

@article{qi2026binocular,
author = {Qi, Chaofei and Li, Peng and Lin, Weiyang},
title = {{Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition}},
journal = {Biomimetics (Basel, Switzerland)},
year = {2026},
month = jul,
volume = {11},
number = {7},
pages = {505},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2313-7673},
doi = {10.3390/biomimetics11070505},
url = {https://doi.org/10.3390/biomimetics11070505},
pmid = {42505538},
pmcid = {PMC13406620}
}

RIS

TY - JOUR
AU - Qi, Chaofei
AU - Li, Peng
AU - Lin, Weiyang
TI - Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition
T2 - Biomimetics (Basel, Switzerland)
J2 - Biomimetics (Basel)
PY - 2026
DA - 2026/07/18
VL - 11
IS - 7
SP - 505
SN - 2313-7673
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/biomimetics11070505
UR - https://doi.org/10.3390/biomimetics11070505
LA - en
ER -

CSL-JSON

{
"id": "10.3390/biomimetics11070505",
"type": "article-journal",
"title": "Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition",
"container-title": "Biomimetics (Basel, Switzerland)",
"author": [
{
"family": "Qi",
"given": "Chaofei"
},
{
"family": "Li",
"given": "Peng"
},
{
"family": "Lin",
"given": "Weiyang"
}
],
"container-title-short": "Biomimetics (Basel)",
"volume": "11",
"issue": "7",
"page": "505",
"DOI": "10.3390/biomimetics11070505",
"PMID": "42505538",
"PMCID": "PMC13406620",
"ISSN": "2313-7673",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/biomimetics11070505",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
18
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1371/journal.pcbi.1014656 [code]
Contrastive learning to fine-tune feature extraction models for the visual cortex.
Journal: PLoS computational biology
In common: Pillow, PyTorch, scikit-learn, 2 other tools, 1 reference
[2] doi:10.1038/s41597-025-05174-7 [code]
A large-scale MEG and EEG dataset for object recognition in naturalistic scenes
Journal: n/a
In common: Pillow, PyTorch, scikit-learn, 2 other tools, 1 reference
[3] doi:10.1167/jov.26.8.1 [code]
MAME: Multidimensional adaptive metamer exploration with human perceptual feedback.
Journal: Journal of vision
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive
[4] doi:10.1038/s41467-026-75653-x [code]
Concept2Brain: an AI model for predicting neurophysiological responses to text and pictures.
Journal: Nature communications
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive
[5] doi:10.1038/s41467-026-74358-5 [code]
Brain-inspired spatial intelligence for embodied agents.
Journal: Nature communications
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive
[6] doi:10.1038/s41467-026-74462-6 [code]
Neural similarity between choice options predicts group-level context effects.
Journal: Nature communications
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive
[7] doi:10.1038/s41593-026-02285-1 [code]
Fixation duration on natural scenes is explained by memory encoding not processing demand.
Journal: Nature neuroscience
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive
[8] doi:10.1038/s41467-026-73153-6 [code]
Latent neural architecture organising shared aesthetic evaluations of visual artworks.
Journal: Nature communications
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive
[9] doi:10.1038/s42003-026-10011-7 [code]
Learning brain dynamics across distinct scaling regimes reveals psychiatric signatures.
Journal: Communications biology
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive
[10] doi:10.1038/s42003-026-10169-0 [code]
Shared representations in brains and models reveal a two-route cortical organization during scene perception.
Journal: Communications biology
In common: Pillow, PyTorch, scikit-learn, 2 other tools, cognitive

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.