IEEE transactions on neural networks and learning systems最新文献

Model-based offline reinforcement learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learning state transitions through ensemble models, rolling out conservative estimation to mitigate extrapolation errors. However, the static data makes it challenging to develop a robust policy, and offline agents cannot access the environment to gather new data. To address these challenges, we introduce Model-based Offline Reinforcement learning with AdversariaL data augmentation (MORAL). In MORAL, we replace the fixed horizon rollout by employing adversarial data augmentation to execute alternating sampling with ensemble models to enrich training data. Specifically, this adversarial process dynamically selects ensemble models against policy for biased sampling, mitigating the optimistic estimation of fixed models, thus robustly expanding the training data for policy optimization. Moreover, a differential factor (DF) is integrated into the adversarial process for regularization, ensuring error minimization in extrapolations. This data-augmented optimization adapts to diverse offline tasks without rollout horizon tuning, showing remarkable applicability. Extensive experiments on the D4RL benchmark demonstrate that MORAL outperforms other model-based offline RL methods in terms of policy learning and sample efficiency.

In the rapidly evolving field of AI research, foundational models like BERT and GPT have significantly advanced language and vision tasks. The advent of pretrain-prompting models, such as ChatGPT and segment anything model (SAM), has further revolutionized image segmentation. However, their applications in specialized areas, particularly in nuclei segmentation within medical imaging, reveal a key challenge: the generation of high-quality, informative prompts is as crucial as applying state-of-the-art (SOTA) fine-tuning techniques on foundation models. To address this, we introduce segment any cell (SAC), an innovative framework that enhances SAM specifically for nuclei segmentation. SAC integrates a low-rank adaptation (LoRA) within the attention layer of the Transformer to improve the fine-tuning process, outperforming existing SOTA methods. It also introduces an innovative auto-prompt generator that produces effective prompts to guide segmentation, a critical factor in handling the complexities of nuclei segmentation in biomedical imaging. Our extensive experiments demonstrate the superiority of SAC in nuclei segmentation tasks, proving its effectiveness as a tool for pathologists and researchers. Our contributions include a novel prompt generation strategy, automated adaptability for diverse segmentation tasks, the innovative application of low-rank attention adaptation in SAM, and a versatile framework for semantic and instance segmentation challenges.

In recent years, bidirectional convolutional recurrent neural networks (RNNs) have made significant breakthroughs in addressing a wide range of challenging problems related to time series and prediction applications. However, the performance of the models is highly dependent on the hyperparameters chosen. Hence, we propose an automatic method for hyperparameter optimization and apply a bidirectional convolutional RNN based on the improved swarm intelligence optimization (sparrow search) to solve regression prediction problems. Specifically, a parallel multiscale dilated convolution (PMDC) module was designed to capture both local and global spatial correlations. This method utilizes convolution with different dilation rates to expand the receptive field without increasing the complexity of the model. Meanwhile, it integrates parallel multiscale structures to extract features at different scales and enhance the model's understanding of the input data. Then, the bidirectional gated recurrent units (BGRUs) learn temporal information from the convolutional features. To address the limitations of empirical hyperparameter selection, such as slow training and low efficiency, a novel PMDC-BGRU model integrated with a pretrained sparrow search algorithm (SSA) was proposed for hyperparameter optimization. Finally, experiments on multiple datasets verified the superiority of the algorithm and explained the flexibility of intelligent optimization algorithms in solving model parameter optimization.

Recent advances in deep-learning-based remote sensing image super-resolution (RSISR) have garnered significant attention. Conventional models typically perform upsampling at the end of the architecture, which reduces computational effort but leads to information loss and limits image quality. Moreover, the structural complexity and texture diversity of remote sensing images pose challenges in detail preservation. While transformer-based approaches improve global feature capture, they often introduce redundancy and overlook local details. To address these issues, we propose a novel progressive structure preservation and detail refinement super-resolution (PSPDR-SR) model, designed to enhance both structural integrity and fine details in RSISR. The model comprises two primary subnetworks: the structure-aware super-resolution (SaSR) subnetwork and the detail recovery and refinement (DR&R) subnetwork. To efficiently leverage multilayer and multiscale feature representations, we introduce coarse-to-fine dynamic information transmission (C2FDIT) and fine-to-coarse dynamic information transmission (F2CDIT) modules, which facilitate the extraction of richer details from low-resolution (LR) remote sensing images. These modules integrate transformers and convolutional long short-term memory (ConvLSTM) blocks to form dynamic information transmission modules (DITMs), enabling effective bidirectional feature transmission both horizontally and vertically. This method ensures comprehensive feature fusion, mitigates redundant information, and preserves essential extracted features within the deep network. Experimental results demonstrate that PSPDR-SR outperforms the state-of-the-art approaches on two benchmark datasets in both quantitative and qualitative evaluations, excelling in structure preservation and detail enhancement across various metrics, including SSIM, MS_SSIM, learned perceptual image patch similarity (LPIPS), deep image structure and texture similarity (DISTS), spatial correlation coefficient (SCC), and spectral angle mapper (SAM).