Related papers: Disentangling Polysemantic Neurons with a Null-Cal…

Speech-based clinical tools are increasingly deployed in multilingual settings, yet whether pathological speech markers remain geometrically separable from accent variation remains unclear. Systems may misclassify healthy non-native…

Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes. Traditional methods address this by sequentially connecting a powerful mask proposal generator, such as the Segment…

Presently, self-training stands as a prevailing approach in cross-domain semantic segmentation, enhancing model efficacy by training with pixels assigned with reliable pseudo-labels. However, we find two critical limitations in this…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the…

Deep Convolutional Neural Networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful…

Semantic concept hierarchy is still under-explored for semantic segmentation due to the inefficiency and complicated optimization of incorporating structural inference into dense prediction. This lack of modeling semantic correlations also…

We introduce a method that takes advantage of high-quality pretrained multimodal representations to explore fine-grained semantic networks in the human brain. Previous studies have documented evidence of functional localization in the…

Deep learning has shown significant potential in diagnosing neurodegenerative diseases from MRI data. However, most existing methods rely heavily on large volumes of labeled data and often yield representations that lack interpretability.…

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced in WSSS.…

In recent years, the availability of digitized Whole Slide Images (WSIs) has enabled the use of deep learning-based computer vision techniques for automated disease diagnosis. However, WSIs present unique computational and algorithmic…

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep…

In neural networks, task-relevant information is represented jointly by groups of neurons. However, the specific way in which this mutual information about the classification label is distributed among the individual neurons is not well…

The success of supervised deep learning models in medical image segmentation relies on detailed annotations. However, labor-intensive manual labeling is costly and inefficient, especially in dense object segmentation. To this end, we…

Multi-sensor clues have shown promise for object segmentation, but inherent noise in each sensor, as well as the calibration error in practice, may bias the segmentation accuracy. In this paper, we propose a novel approach by mining the…

Understanding how neurons coordinate their activity is a fundamental question in neuroscience, with implications for learning, memory, and neurological disorders. Calcium imaging has emerged as a powerful method to observe large-scale…

The popularity and diffusion of wearable devices provides new opportunities for sensor-based human activity recognition that leverages deep learning-based algorithms. Although impressive advances have been made, two major challenges remain.…

Training deep models for semantic scene completion (SSC) is challenging due to the sparse and incomplete input, a large quantity of objects of diverse scales as well as the inherent label noise for moving objects. To address the…

The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification…

Open-vocabulary semantic segmentation aims to assign semantic labels to each pixel without being constrained by a predefined set of categories. While Contrastive Language-Image Pre-training (CLIP) excels in zero-shot classification, it…