Related papers: S2S2: Semantic Stacking for Robust Semantic Segmen…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Deep learning-based nuclei segmentation and classification in pathology images typically rely on large-scale pixel-level manual annotations, which are costly and difficult to obtain across diverse tissues and staining conditions. To address…

Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…

Deep neural networks are susceptible to learn biased models with entangled feature representations, which may lead to subpar performances on various downstream tasks. This is particularly true for under-represented classes, where a lack of…

Spiking neural networks (SNNs) are rich in spatio-temporal dynamics and are suitable for processing event-based neuromorphic data. However, event-based datasets are usually less annotated than static datasets. This small data scale makes…

Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…

Traditional supervised medical image segmentation models require large amounts of labeled data for training; however, obtaining such large-scale labeled datasets in the real world is extremely challenging. Recent semi-supervised…

Semantic segmentation is a critical task in computer vision aiming to identify and classify individual pixels in an image, with numerous applications in for example autonomous driving and medical image analysis. However, semantic…

Semantic image segmentation is an important computer vision task that is difficult because it consists of both recognition and segmentation. The task is often cast as a structured output problem on an exponentially large output-space, which…

Unsupervised image-to-image (I2I) translation learns cross-domain image mapping that transfers input from the source domain to output in the target domain while preserving its semantics. One challenge is that different semantic statistics…

Deep neural networks usually require accurate and a large number of annotations to achieve outstanding performance in medical image segmentation. One-shot segmentation and weakly-supervised learning are promising research directions that…

Medical experts often manually segment images to obtain diagnostic statistics and discard the resulting annotations. We aim to train segmentation models to alleviate this burden, but constrained to the retained summary statistics (e.g., the…

In recent years, neural networks have proven to be effective in Chinese word segmentation. However, this promising performance relies on large-scale training data. Neural networks with conventional architectures cannot achieve the desired…

Deep learning-based medical image segmentation typically requires large amount of labeled data for training, making it less applicable in clinical settings due to high annotation cost. Semi-supervised learning (SSL) has emerged as an…

Recent years have witnessed a growing academic and industrial interest in deep learning (DL) for medical imaging. To perform well, DL models require very large labeled datasets. However, most medical imaging datasets are small, with a…

Models based on U-like structures have improved the performance of medical image segmentation. However, the single-layer decoder structure of U-Net is too "thin" to exploit enough information, resulting in large semantic differences between…

Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization. The success of semantic segmentation algorithms is contingent on the availability of high-quality imaging data…

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…

Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and…

Current trends in scientific imaging are challenged by the emerging need of integrating sophisticated machine learning with Big Data analytics platforms. This work proposes an in-memory distributed learning architecture for enabling…