Related papers: Towards Generalized Synapse Detection Across Inver…
Event cameras, with their high dynamic range and temporal resolution, are ideally suited for object detection, especially under scenarios with motion blur and challenging lighting conditions. However, while most existing approaches…
Automatic medical image segmentation has made great progress benefit from the development of deep learning. However, most existing methods are based on convolutional neural networks (CNNs), which fail to build long-range dependencies and…
Sparse vision transformers have gained popularity as efficient encoders for medical volumetric segmentation, with Swin emerging as a prominent choice. Swin uses local attention to reduce complexity and yields excellent performance for many…
The automated analysis of medical images is currently limited by technical and biological noise and bias. The same source tissue can be represented by vastly different images if the image acquisition or processing protocols vary. For an…
The density of synaptic receptors in front of presynaptic release sites is stabilized in the presence of scaffold proteins, but the receptors and scaffold molecules have local exchanges with characteristic times shorter than that of the…
Deep neural networks have incredible capacity and expressibility, and can seemingly memorize any training set. This introduces a problem when training in the presence of noisy labels, as the noisy examples cannot be distinguished from clean…
Advances in cellular imaging technologies, especially those based on fluorescence in situ hybridization (FISH) now allow detailed visualization of the spatial organization of human or bacterial cells. Quantifying this spatial organization…
Data synthesis and augmentation are essential for Sound Event Detection (SED) due to the scarcity of temporally labeled data. While augmentation methods like SpecAugment and Mix-up can enhance model performance, they remain constrained by…
Objective. Reliable, continuous neural sensing on wearable edge platforms is fundamental to long-term health monitoring; however, for electroencephalography (EEG)-based sleep monitoring, dense high-frequency processing is often…
Machine learning classifiers using surface electromyography are important for human-machine interfacing and device control. Conventional classifiers such as support vector machines (SVMs) use manually extracted features based on e.g.…
Reconstructing a synaptic wiring diagram, or connectome, from electron microscopy (EM) images of brain tissue currently requires many hours of manual annotation or proofreading (Kasthuri and Lichtman, 2010; Lichtman and Sanes, 2008; Seung,…
Most feedforward convolutional neural networks spend roughly the same efforts for each pixel. Yet human visual recognition is an interaction between eye movements and spatial attention, which we will have several glimpses of an object in…
Semantic image synthesis (SIS) shows good promises for sensor simulation. However, current best practices in this field, based on GANs, have not yet reached the desired level of quality. As latent diffusion models make significant strides…
The proliferation of deepfake technology poses significant challenges to the authenticity and trustworthiness of digital media, necessitating the development of robust detection methods. This study explores the application of Swin…
The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated…
In hyperspectral remote sensing field, some downstream dense prediction tasks, such as semantic segmentation (SS) and change detection (CD), rely on supervised learning to improve model performance and require a large amount of manually…
Detecting glass regions is a challenging task due to the inherent ambiguity in their transparency and reflective characteristics. Current solutions in this field remain rooted in conventional deep learning paradigms, requiring the…
Spikes can be easily detected inmostintracellular recordings as sharp peaks. However, insome experimental preparations,because of unipolar morphology or other characteristicsof the recorded neurons, the sizes of the spikes recorded from the…
Improving the quality of underwater images is essential for advancing marine research and technology. This work introduces a sparsity-driven interpretable neural network (SINET) for the underwater image enhancement (UIE) task. Unlike pure…
Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as…