TY - JOUR AU - Kundu, Soumya S AU - Patel, Sheel AU - Srivastava, Shaswat AU - Chaube, Aarsh AU - Moorthy, Vaishnavi PY - 2022/04/08 Y2 - 2024/03/28 TI - Handling Colors in Image Classification JF - Journal of Computational Vision and Imaging Systems JA - J. Comp. Vis. Imag. Sys. VL - 7 IS - 1 SE - Articles DO - 10.15353/jcvis.v7i1.4889 UR - https://openjournals.uwaterloo.ca/index.php/vsl/article/view/4889 SP - 22-24 AB - <p>The presence of bias in a dataset has been a long standing bottleneck in the task of image classification. While supervised methods have shown to overcome these biases, self-supervised methods have managed to overcome benchmarks set by supervised learning methods. This paper shows that self-supervised methods can maintain their ability to outperform supervised methods even when introduced to color bias. Two experimentation pipelines are presented. One focuses on the capability of a model to handle artificially induced color bias and the other gauges the ability of a model to incorporate naturally occurring color differences present in vision datasets.</p> ER -