{
  "abstract": "Attention mechanisms improve convolutional neural networks (CNNs) by emphasizing informative features, but many existing modules introduce additional parameters, convolutional or fully connected layers, and non-negligible computational overhead. These costs may limit their use in lightweight or plug-and-play CNN architectures. To address this issue, this paper proposes a parameter-free spatial attention fusion module (PSAFM). Specifically, the pointwise average- and max-pooling branches are combined by deterministic weighted fusion, after which channel statistics and a Tanh activation are used to compute adaptive three-dimensional attention weights. This enables the module to strengthen feature responses without adding trainable parameters. We evaluate PSAFM on CIFAR-10 and CIFAR-100 using ResNet, Pre-ResNet, and MobileNetV2 backbones. On CIFAR-10, PSAFM achieves the best accuracy in 8 of 9 tested backbone settings and improves the original backbones by 0.32 to 1.81 percentage points. On CIFAR-100, PSAFM achieves the best accuracy in 6 of 9 settings and improves the original backbones by 0.05 to 1.68 percentage points. In these experiments, PSAFM is compared with representative attention modules. The results show that its parameter count remains essentially unchanged and that only a small FLOPs overhead is introduced. In other words, when model compactness is important, PSAFM is a simple and efficient attention module that improves CNN feature representation.",
  "abstract_shown": true,
  "affiliations": [
    "School of Ecological Environment and Chemical Engineering, Xi’an University of Technology, Xi’an, P. R. China",
    "School of Mathematics, Xi’an University of Technology, Xi’an, P. R. China",
    "School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, P. R. China",
    "Department of Thyroid and Breast Surgery, Xijing Hospital of Air Force Military Medical University, Xi’an, P. R. China"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Guangjun Liu"
    },
    {
      "affs": [
        1
      ],
      "name": "Xiaoping Xu"
    },
    {
      "affs": [
        2
      ],
      "name": "Bingkun Zhou"
    },
    {
      "affs": [
        3
      ],
      "name": "Feng Wang"
    },
    {
      "name": "Yike Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2f0tfqgg6m8kx.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0357958",
  "fulltext_url": null,
  "id": "2f0tfqgg6m8kx",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0357958",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1707|Advanced Neural Network Applications"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Attention"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Perception/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Learning and memory/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Neural networks"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Attention"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Perception/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Deep learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Computer architecture"
    ],
    [
      "plos",
      "/Computer and information sciences/Neural networks"
    ],
    [
      "plos",
      "/Computer and information sciences/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Engineering and technology/Industrial engineering/Quality control/Visual inspection"
    ],
    [
      "plos",
      "/Engineering and technology/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Attention"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Learning"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Perception/Sensory perception/Vision"
    ]
  ],
  "openalex": "W7213283891",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0357958&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/2f0tfqgg6m8kx.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:49Z",
      "native_id": "10.1371/journal.pone.0357958",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0357958"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "PSAFM: A parameter-free spatial attention fusion module",
  "title_text": "PSAFM: A parameter-free spatial attention fusion module",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:49Z",
  "url": "https://research.draconitic.com/paper/2f0tfqgg6m8kx",
  "venue": "PLOS One",
  "versions": []
}