In recent years, with changes in dietary structure, beef has become the third most consumed meat in China after pork and chicken, with its consumption increasing by approximately 50%. The quality and commercial value of beef vary considerably across different muscles. However, due to the high similarity in the appearance of beef cuts and strong background interference, traditional image features are often insufficient for accurate classification. In this study, an improved convolutional neural network based on YOLOv11 was proposed. Four beef muscles were categorized: sirloin (longissimus dorsi), fillet/tenderloin (psoas major), oyster blade (infraspinatus), and ribeye (longissimus thoracis). A dataset comprising 3598 images was established to support model training and validation. We divided the dataset into training, testing, and validation sets in a 6:2:2 ratio. To enhance model performance, wavelet convolution (WTConv) was employed to effectively expand the receptive field and improve image understanding, while a large separable kernel attention (LSKA) module was introduced to strengthen local feature representation and reduce background interference. Comparative experiments were conducted with other deep learning models as well as ablation tests to validate the proposed model’s effectiveness. Experimental results demonstrated that the proposed model achieved a classification accuracy of 98.50%, with Macro-Precision and Macro-Recall reaching 97.38% and 97.38%, respectively, and a detection speed of 147.66 FPS. These findings confirm the potential of the YOLOv11n-cls model for accurate beef classification and its practical application in intelligent meat recognition and processing within the Chinese beef industry.