https://theusajournals.com/index.php/ajast <p><strong>American Journal Of Applied Science And Technology (<span class="ng-scope"><span class="ng-binding ng-scope">2771-2745</span></span>)</strong></p> <p><strong>Open Access International Journal</strong></p> <p><strong>Last Submission:- 25th of Every Month</strong></p> <p><strong>Frequency: 12 Issues per Year (Monthly)</strong></p> <p> </p> Oscar Publishing Services en-US American Journal of Applied Science and Technology 2771-2745 https://theusajournals.com/index.php/ajast/article/view/5004 <p>Fine-grained image classification (FGIC) presents a challenge due to the high similarity between visually similar categories, requiring precise feature extraction. Traditional supervised methods demand large amounts of labeled data, which is often unavailable. This paper introduces a local diversity-guided weakly supervised method to address these challenges by leveraging weakly annotated data, thus alleviating the dependence on fully labeled datasets. The approach focuses on fine-grained object recognition by combining local diversity features with weak labels, which significantly improves classification performance. Experimental results on several benchmark datasets demonstrate the method's effectiveness in enhancing the precision of fine-grained classification tasks.</p> Antonio Pedro Copyright (c) 2025 Antonio Pedro https://creativecommons.org/licenses/by/4.0 2025-04-01 2025-04-01 5 04 1 5