This paper introduces a hybrid learning framework that combines convolutional neural networks (CNNs) and physics-informed neural networks (PINNs) to address the challenging problem of full-inverse electrical impedance tomography (EIT). EIT is a noninvasive imaging technique that reconstructs the spatial distribution of internal conductivity based on boundary voltage measurements from injected currents. This method has applications across medical imaging, multiphase flow detection, and tactile sensing. However, solving EIT involves a nonlinear partial differential equation (PDE) derived from Maxwell's equations, posing significant computational challenges as an ill-posed inverse problem. Existing PINN approaches primarily address semi-inverse EIT, assuming full access to internal potential data, which limits practical applications in realistic, full-inverse scenarios. Our framework employs a forward CNN-based supervised network to map differential boundary voltage measurements to a discrete potential distribution under fixed Neumann boundary conditions, while an inverse PINN-based unsupervised network enforces PDE constraints for conductivity reconstruction. Instead of traditional automatic differentiation, we introduce discrete numerical differentiation to bridge the forward and inverse networks, effectively decoupling them, enhancing modularity, and reducing computational demands. We validate our framework under realistic conditions, using a 16-electrode setup and rigorous testing on complex conductivity distributions with sharp boundaries, without Gaussian smoothing. This approach demonstrates robust flexibility and improved applicability in full-inverse EIT, establishing a practical solution for real-world imaging challenges.

With the emerging trend of large generative models, ControlNet is introduced to enable users to fine-tune pre-trained models with their own data for various use cases. A natural question arises: how can we train ControlNet models while ensuring users' data privacy across distributed devices? Exploring different distributed training schemes, we find conventional federated learning and split learning unsuitable. Instead, we propose a new distributed learning structure that eliminates the need for the server to send gradients back. Through a comprehensive evaluation of existing threats, we discover that in the context of training ControlNet with split learning, most existing attacks are ineffective, except for two mentioned in previous literature. To counter these threats, we leverage the properties of diffusion models and design a new timestep sampling policy during forward processes. We further propose a privacy-preserving activation function and a method to prevent private text prompts from leaving clients, tailored for image generation with diffusion models. Our experimental results demonstrate that our algorithms and systems greatly enhance the efficiency of distributed training for ControlNet while ensuring users' data privacy without compromising image generation quality.

Hyperspectral imagery (HSI) is an established technique with an array of applications, but its use is limited due to both practical and technical issues associated with spectral devices. The goal of the ICASSP 2024 'Hyper-Skin' Challenge is to extract skin HSI from matching RGB images and an infrared band. To address this problem we propose a model using features of the scattering transform - a type of convolutional neural network with predefined filters. Our model matches and inverts those features, rather than the pixel values, reducing the complexity of matching while grouping similar features together, resulting in an improved learning process.

In this paper, we propose a pre-trained-combined neural network (PTCN) as a comprehensive solution to the inverse design of an integrated photonic circuit. By utilizing both the initially pre-trained inverse and forward model with a joint training process, our PTCN model shows remarkable tolerance to the quantity and quality of the training data. As a proof of concept demonstration, the inverse design of a wavelength demultiplexer is used to verify the effectiveness of the PTCN model. The correlation coefficient of the prediction by the presented PTCN model remains greater than 0.974 even when the size of training data is decreased to 17%. The experimental results show a good agreement with predictions, and demonstrate a wavelength demultiplexer with an ultra-compact footprint, a high transmission efficiency with a transmission loss of -2dB, a low reflection of -10dB, and low crosstalk around -7dB simultaneously.