<p>One fascinating and challenging research topic in the field of computer vision and image processing is the classification of mushroom images into multiple categories. Mushrooms fall into many categories worldwide. While some varieties of mushrooms are edible, others are toxic or not edible, and the shapes and color combinations present an intriguing challenge for their classification from images. This challenge is becoming easier to solve because of the recent success of deep learning (DL)-based models, particularly convolutional neural networks (CNN), on images for feature extraction and classification. Furthermore, the integration of transfer learning approaches with different attention mechanisms significantly improves classification accuracy over time. Even so, there is still a huge potential for improved performance by experimenting with more sophisticated DL-based approaches and introducing more mushroom categories, each with more images. In this work, we achieved validation accuracies of 95.85% and 93.68% on two different mushroom image datasets, outperforming other comparable DL-based systems by integrating the convolutional block attention module (CBAM) with a transfer learning-based Xception architecture. A 5-fold cross-validation approach is employed to enhance the model’s generalizability and ensure greater robustness and consistency in the results. The novelty of our model lies in integrating the convolutional block attention module (CBAM) with a transfer learning-based Xception architecture, selectively unfreezing the last 4 blocks to enhance feature extraction. This unique combination improves the model’s attention to critical spatial and channel information, resulting in superior performance compared to conventional transfer learning approaches.</p>