QuIC: A Quantum-Inspired Interaction Classifier for Revitalizing Shallow CNNs in Fine-Grained Recognition

• URL: http://arxiv.org/abs/2601.02189v1
• Date: Mon, 05 Jan 2026 15:09:18 GMT
• Title: QuIC: A Quantum-Inspired Interaction Classifier for Revitalizing Shallow CNNs in Fine-Grained Recognition
• Abstract summary: QuIC is a lightweight, plug-and-play module that supports stable, single-stage end-to-end training without exploding feature dimensions.<n>It boosts the Top-1 accuracy of VGG16 by nearly 20% and outperforms state-of-the-art attention mechanisms (SE-Block) on ResNet18.
• Score: 1.2747974581480312
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying deep learning models for Fine-Grained Visual Classification (FGVC) on resource-constrained edge devices remains a significant challenge. While deep architectures achieve high accuracy on benchmarks like CUB-200-2011, their computational cost is often prohibitive. Conversely, shallow networks (e.g., AlexNet, VGG) offer efficiency but fail to distinguish visually similar sub-categories. This is because standard Global Average Pooling (GAP) heads capture only first-order statistics, missing the subtle high-order feature interactions required for FGVC. While Bilinear CNNs address this, they suffer from high feature dimensionality and instability during training. To bridge this gap, we propose the Quantum-inspired Interaction Classifier (QuIC). Drawing inspiration from quantum mechanics, QuIC models feature channels as interacting quantum states and captures second-order feature covariance via a learnable observable operator. Designed as a lightweight, plug-and-play module, QuIC supports stable, single-stage end-to-end training without exploding feature dimensions. Experimental results demonstrate that QuIC significantly revitalizes shallow backbones: it boosts the Top-1 accuracy of VGG16 by nearly 20% and outperforms state-of-the-art attention mechanisms (SE-Block) on ResNet18. Qualitative analysis, including t-SNE visualization, further confirms that QuIC resolves ambiguous cases by explicitly attending to fine-grained discriminative features and enforcing compact intra-class clustering.

Related papers

• Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations [0.431493144418712]
  Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices.<n>This study presents a systematic evaluation on how static PTQ affects the interpretability / explainability of five widely used CNN architectures.
  arXiv  Detail & Related papers  (2026-07-24T19:26:47Z)
• Beyond Barren Plateaus: A Scalable Quantum Convolutional Architecture for High-Fidelity Image Classification [0.0]
  Quantum Convolutional Neural Networks (QCNNs) offer a theoretical paradigm for quantum machine learning.<n>However, implementation is bottlenecked by barren plateaus -- the exponential vanishing of gradients -- and poor empirical accuracy.<n>We propose a novel QCNN architecture utilizing localized cost functions and a hardware-efficient tensor-network.<n>We evaluate our scalable QCNN on the MNIST dataset, demonstrating a significant performance leap.
  arXiv  Detail & Related papers  (2026-03-11T15:57:42Z)
• Neural quantum support vector data description for one-class classification [0.19116784879310023]
  One-class classification (OCC) is a fundamental problem in machine learning with numerous applications.<n>We introduce Neural Quantum Support Vector Data Description (NQSVDD), a classical-quantum hybrid framework for OCC.<n>NQSVDD integrates a classical neural network with trainable quantum data encoding and a variational quantum circuit, enabling the model to learn nonlinear feature transformations tailored to the OCC objective.
  arXiv  Detail & Related papers  (2026-03-03T07:45:32Z)
• Dual-Qubit Hierarchical Fuzzy Neural Network for Image Classification: Enabling Relational Learning via Quantum Entanglement [27.317371900372127]
  This paper proposes a dual-qubit hierarchical fuzzy neural network (DQ-HFNN)<n>It encodes feature pairs onto a pair of entangled qubits, which extends the single-feature fuzzy model to a joint fuzzy representation.<n> Experiments under noisy conditions suggest that it is robust against noise and has the potential to be implemented on noisy intermediate-scale quantum devices.
  arXiv  Detail & Related papers  (2025-12-15T12:35:53Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer [2.6610943214001765]
  We introduce a Transformer-based autoencoder trained with a two-stage paradigm: self-supervised pre-training followed by supervised fine-tuning.<n>The encoder learns latent representations directly from unlabeled HIC data, providing a compact and information-rich feature space.<n>Results establish our two-stage framework as a general and robust foundation for feature learning in HIC, opening the door to more powerful analyses of quark--gluon plasma properties.
  arXiv  Detail & Related papers  (2025-10-08T06:27:10Z)
• Quantum Graph Attention Network: A Novel Quantum Multi-Head Attention Mechanism for Graph Learning [0.0]
  Quantum Graph Attention Network (QGAT) is a hybrid graph neural network that integrates variational quantum circuits into the attention mechanism.<n>We show QGAT's effectiveness in capturing complex structural dependencies and improved generalization in inductive scenarios.<n>Experiments confirm that quantum embedding enhances robustness against feature and structural noise, suggesting advantages in handling real-world noisy data.
  arXiv  Detail & Related papers  (2025-08-25T03:25:48Z)
• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• Hybrid Quantum-Classical Feature Extraction approach for Image Classification using Autoencoders and Quantum SVMs [0.0]
  NISQ-era quantum computers have limitations, which include noise, scalability, read-in and read-out times, and gate operation times. strategies should be devised to mitigate the impact that complex datasets can have on the overall efficiency of a quantum machine learning pipeline. We apply a classical feature extraction method using a ResNet10-inspired convolutional autoencoder to both reduce the dimensionality of the dataset and extract meaningful features.
  arXiv  Detail & Related papers  (2024-10-24T15:02:05Z)
• Learning Feature Matching via Matchable Keypoint-Assisted Graph Neural Network [52.29330138835208]
  Accurately matching local features between a pair of images is a challenging computer vision task. Previous studies typically use attention based graph neural networks (GNNs) with fully-connected graphs over keypoints within/across images. We propose MaKeGNN, a sparse attention-based GNN architecture which bypasses non-repeatable keypoints and leverages matchable ones to guide message passing.
  arXiv  Detail & Related papers  (2023-07-04T02:50:44Z)
• Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification [83.20479832949069]
  Quantum neural networks (QNNs) have become an important tool for understanding the physical world, but their advantages and limitations are not fully understood. Here we investigate the problem-dependent power of QCs on multi-class classification tasks. Our work sheds light on the problem-dependent power of QNNs and offers a practical tool for evaluating their potential merit.
  arXiv  Detail & Related papers  (2022-12-29T10:46:40Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.