Overfitting remains a persistent challenge in deep learning. It is primarily attributed to data outliers, noise, and limited training set sizes. This paper presents Divide2Conquer (D2C), a novel technique designed to address this issue. D2C proposes partitioning the training data into multiple subsets and training separate identical models on them. To avoid overfitting on any specific subset, the trained parameters from these models are aggregated and averaged periodically throughout the training phase, enabling the model to learn from the entire dataset while mitigating the impact of individual outliers or noise. Empirical evaluations on multiple benchmark datasets across various deep learning tasks demonstrate that D2C effectively improves generalization performance, particularly for larger datasets. This study verifies D2C’s ability to achieve significant performance gains both as a standalone technique and when used in conjunction with other overfitting reduction methods through a series of experiments, including analysis of decision boundaries, loss curves, and other performance metrics. It also provides valuable insights into the implementation and hyperparameter tuning of D2C. Our codes are publicly available at: https://github.com/Saiful185/Divide2Conquer.

With the continuous growth of internet users and media content, it is very hard to track down hateful speech in audio and video. Converting video or audio into text does not detect hate speech accurately as human sometimes uses hateful words as humorous or pleasant in sense and also uses different voice tones or show different action in the video. The state-of-the-art hate speech detection models were mostly developed on a single modality. In this research, a combined approach of multi-modal system has been proposed to detect hate speech from video contents by extracting feature images, feature values extracted from the audio, text and used machine learning and Natural language processing.