Litho-NeuralODE 2.0: Improving hotspot detection accuracy with advanced data augmentation, DCT-based features, and neural ordinary differential equations

It has proved that the application of deep neural networks has advantage in lithographic hotspot detection, which is vital in the physical verification flow to reduce manufacturing yield loss. In this paper, we employ the discrete cosine transform (DCT)-based feature extraction method along with parameter search to compress the layout image to achieve higher classification accuracy and speed up the training process. To further improve the classification performance, data augmentation techniques addressing the imbalanced dataset problem along with neural ordinary differential equations based Litho-NeuralODE 2.0 framework with improved loss function have utilized in the work. Experimental results demonstrate that the proposed framework outperforms the state-of-the-art works with the lowest misses of 7 and the highest accuracy of 98.9% on average. •Optimizing Data Augmentation: helps to deal with the problem of dataset imbalance and improve the detection performance.•Parameter Search: helps to determine the optimal feature tensor size after discrete cosine transform (DCT) to minimize information loss and achieve better classification performance.•Litho-NeuralODE 2.0 model: is based on neural ordinary differential equation network along with an improved loss function, to improve the classification accuracy.•Experimental Performance: It achieves the highest average accuracy of 98.9% and smallest average misses of 7 compared to the state-of-the-art works.