Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188834,
        author = {Rishabh Agrawal and Dr. Surjeet Dalal},
        title = {Role of Deep Learning in Image Recognition},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {3648-3652},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188834},
        abstract = {Deep learning has transformed image recognition over the past decade, transferring the sector from hand crafted functions and shallow models to relatively accurate, statistics-driven structures. This overview strains that evolution, summarizes key architectures and education paradigms (convolutional neural networks, residual networks, transformers, and self-supervised strategies), surveys foremost datasets and benchmarks, highlights important packages, lists middle challenges (information, robustness, fairness, compute), and descriptions in all likelihood future guidelines. Key breakthroughs: AlexNet (2012), ResNets (2015/2016), vision Transformers (2020), and modern self-supervised frameworks - are emphasized as turning points that reshaped research and exercise.},
        keywords = {deep learning, image recognition, CNN, ResNet, Vision Transformer, self-supervised learning, ImageNet, benchmarks},
        month = {December},
        }