A long-tailed distribution in a dataset is a particular kind of imbalance where data samples from several classes are distributed according to a long-tail distribution. As a result, the predictive ability of deep learning algorithms is heavily biased toward those classes that have high data samples (head classes), which results in subpar performance when classifying minority class (tail classes) data samples. In literature, there are several methods to solve class imbalance problems like resampling inputs and reweighting model parameters. However, these methods suffer heavy overfitting and are hard-to-solve optimization problems during training. The existing technique uses Shannon cross entropy as a loss function. In our approach, we use different loss functions, in particular Renyi entropy, to compare the classification accuracy of ResLT-based deep learning models. The results depict that Renyi entropy loss function outperforms any other loss function when it comes to classification tasks on long-tailed data distributions. We test our proposed approach on the long-tailed version of two standard datasets, Cifar-10 and Cifar-100. We achieved an accuracy of 84.15% on the Cifar-10 and 71.78% on the Cifar-100 dataset, which outperforms any state-of-the-art method for class imbalance tasks. Experimental results demonstrate improvement in the accuracy of residual.