The considerable prospecting depth and accurate subsurface characteristics can be obtained by the transient electromagnetic method (TEM) in geophysics. Nevertheless, the time-domain TEM signal received by the coil is easily disturbed by environmental background noise, artificial noise, and electronic noise of the equipment. Recently, deep neural networks (DNNs) have been used to solve the TEM denoising problem and have achieved better performance than traditional methods. However, the existing denoising method with DNN adopts fully connected neural networks and is therefore not flexible enough to deal with various signal scales. To address these issues, a novel denoising framework with deep convolutional neural networks (CNNs) of transforming the TEM signal denoising task into an image denoising task (namely, TEMDnet) is proposed in this article. Specifically, a novel signal-to-image transformation method is developed first to preserve the structural features of TEM signals. Then, a novel deep CNN-based denoiser is proposed to further perform feature learning, in which the residual learning mechanism is adopted to model the noise estimation image for different signal features. Extensive experiments demonstrate that the proposed framework can achieve much better performance compared with other state-of-the-art approaches on both simulated signals and real-world signals from a landfill leachate treatment plant in Chengdu, Sichuan, China. Models and code are available at https://github.com/tonyckc/TEMDnet_demo.

Transient electromagnetic (TEM) method is a widely adopted technology in geophysics. TEM signals received by coils will be disturbed by complex noises. Compared with traditional filtering-based methods, deep-learning-based TEM signal denoising methods achieved impressive denoising performance. However, the existing deep-learning-based methods rely heavily on simulated noise with a certain distribution to construct paired datasets for supervised learning. In real scenarios, if the noise distribution of acquired TEM signals has a huge difference (e.g., the type of noise distribution, the level of noise) with that of the simulated datasets, the trained model may not always be valid. To address this issue, a novel noise-learning-inspired deep denoising network (namely, TEM-NLnet) is proposed for TEM signal denoising. Specifically, instead of inserting the simulated noise, we first learn the noise appeared in real-world signals through generative adversarial networks (GANs), such that the generator can produce the learned noise to construct paired datasets for training. Then, a deep-neural-network-based denoiser is imposed to learn mapping from the noise TEM signal to the corresponding noise-free one. Extensive experiments on the simulated and actual geological datasets show that compared with other state-of-the-art TEM denoising methods, our proposed method achieves better performance in terms of quantitative and visual results. Models and code are available at https://github.com/wmyCDUT/TEM-NLnet_demo .

Generalizable medical image segmentation enables models to generalize to unseen target domains under domain shift issues. Recent progress demonstrates that the shape of the segmentation objective, with its high consistency and robustness across domains, can serve as a reliable regularization to aid the model for better cross-domain performance, where existing methods typically seek a shared framework to render segmentation maps and shape prior concurrently. However, due to the inherent texture and style preference of modern deep neural networks, the edge or silhouette of the extracted shape will inevitably be undermined by those domain-specific texture and style interferences of medical images under domain shifts. To address this limitation, we devise a novel framework with a separation between the shape regularization and the segmentation map. Specifically, we first customize a novel whitening transform-based probabilistic shape regularization extractor namely WT-PSE to suppress undesirable domain-specific texture and style interferences, leading to more robust and high-quality shape representations. Second, we deliver a Wasserstein distance-guided knowledge distillation scheme to help the WT-PSE to achieve more flexible shape extraction during the inference phase. Finally, by incorporating domain knowledge of medical images, we propose a novel instance-domain whitening transform method to facilitate a more stable training process with improved performance. Experiments demonstrate the performance of our proposed method on both multi-domain and single-domain generalization.

In this work, we propose to tackle the problem of domain generalization in the context of insufficient samples. Instead of extracting latent feature embeddings based on deterministic models, we propose to learn a domain-invariant representation based on the probabilistic framework by mapping each data point into probabilistic embeddings. Specifically, we first extend empirical maximum mean discrepancy (MMD) to a novel probabilistic MMD that can measure the discrepancy between mixture distributions (i.e., source domains) consisting of a series of latent distributions rather than latent points. Moreover, instead of imposing the contrastive semantic alignment (CSA) loss based on pairs of latent points, a novel probabilistic CSA loss encourages positive probabilistic embedding pairs to be closer while pulling other negative ones apart. Benefiting from the learned representation captured by probabilistic models, our proposed method can marriage the measurement on the distribution over distributions (i.e., the global perspective alignment) and the distribution-based contrastive semantic alignment (i.e., the local perspective alignment). Extensive experimental results on three challenging medical datasets show the effectiveness of our proposed method in the context of insufficient data compared with state-of-the-art methods.