mlsanityData to 14 Oct 2026

Enhancing Vehicle Make and Model Recognition with 3D Attention Modules

arXiv 2502.15398 ↗First posted 21 Feb 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Vehicle make and model recognition (VMMR) is a crucial component of the Intelligent Transport System, garnering significant attention in recent years. VMMR has been widely utilized for detecting suspicious vehicles, monitoring urban traffic, and autonomous driving systems. The complexity of VMMR arises from the subtle visual distinctions among vehicle models and the wide variety of classes produced by manufacturers. Convolutional Neural Networks (CNNs), a prominent type of deep learning model, have been extensively employed in various computer vision tasks, including VMMR, yielding remarkable results. As VMMR is a fine-grained classification problem, it primarily faces inter-class similarity and intra-class variation challenges. In this study, we implement an attention module to address these challenges and enhance the model's focus on critical areas containing distinguishing features. This module, which does not increase the parameters of the original model, generates three-dimensional (3-D) attention weights to refine the feature map. Our proposed model integrates the attention module into two different locations within the middle section of a convolutional model, where the feature maps from these sections offer sufficient information about the input frames without being overly detailed or overly coarse. The performance of our proposed model, along with state-of-the-art (SOTA) convolutional and transformer-based models, was evaluated using the Stanford Cars dataset. Our proposed model achieved the highest accuracy, 90.69%, among the compared models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

18 of 25 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2017Squeeze-and-Excitation Networkscited by 4,789
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  9. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  10. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  11. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  12. 2022MaxViT: Multi-Axis Vision Transformercited by 476
6 more
  1. 2017Residual Attention Network for Image Classificationcited by 386
  2. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  3. 2020Global Context Networkscited by 35
  4. 2024BEFUnet: A Hybrid CNN-Transformer Architecture for Precise Medical Image Segmentationcited by 11
  5. 2023Dilated-UNet: A Fast and Accurate Medical Image Segmentation Approach using a Dilated Transformer and U-Net Architecturecited by 8
  6. 2025Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attentioncited by 5

Built on by

Not cited yet.