Exploring the Unexplored: Understanding the Impact of Layer Adjustments on Image Classification
This provides incremental insights for researchers optimizing deep learning models in image classification.
This paper investigated how adjustments to deep learning architectures impact model performance in image classification, finding that image filtering before pre-processing yields better results and that layer choices and filter placement significantly affect performance.
This paper investigates how adjustments to deep learning architectures impact model performance in image classification. Small-scale experiments generate initial insights although the trends observed are not consistent with the entire dataset. Filtering operations in the image processing pipeline are crucial, with image filtering before pre-processing yielding better results. The choice and order of layers as well as filter placement significantly impact model performance. This study provides valuable insights into optimizing deep learning models, with potential avenues for future research including collaborative platforms.