Extensive experiments and analyses have been conducted to characterize and demonstrate the effectiveness of the proposed DivOE.

Convolutional Neural Networks (CNNs) are computation intensive, making their deployment on resource-constrained devices (e.g., Microcontrollers equipped with 2MB memory) challenging.

Existing deep learning based solutions typically restore the target layers individually, or with some concerns at the end of the output, barely taking into account the interaction across thetwostreams/branches. Inorder toutilize information more efficiently, this work presents a general yet simple interactive strategy, namely your trash is my treasure(YTMT), for constructing dual-stream decomposition networks.

Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly symmetric losses.