相关论文: Learning Permutation Invariant Representations usi…

Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…

The performance of existing supervised neuron segmentation methods is highly dependent on the number of accurate annotations, especially when applied to large scale electron microscopy (EM) data. By extracting semantic information from…

The progression of lung cancer implies the intrinsic ordinal relationship of lung nodules at different stages-from benign to unsure then to malignant. This problem can be solved by ordinal regression methods, which is between classification…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

We explore three representative lines of research and demonstrate the utility of our methods on a classification benchmark of brain cancer MRI data. First, we present a capsule network that explicitly learns a representation robust to…

Concept learning deals with learning description logic concepts from a background knowledge and input examples. The goal is to learn a concept that covers all positive examples, while not covering any negative examples. This non-trivial…

In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the…

During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results. Deep-learning models for aiding diagnosis have yet to meet this requirement. Here we report a…

Semiparametric language models (LMs) have shown promise in continuously learning from new text data by combining a parameterized neural LM with a growable non-parametric memory for memorizing new content. However, conventional…

The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced novel approaches for…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

This study presents a computer-aided diagnosis (CAD) system to assist early detection of lung metastases during endobronchial ultrasound (EBUS) procedures, significantly reducing follow-up time and enabling timely treatment. Due to limited…

In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt sentences with largely varied semantics or grammatical…

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance…

Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by aligning pretrained visual representations with the linguistic knowledge embedded in Large Language Models (LLMs). However, existing approaches typically rely…

Whole-slide images are central to digital pathology, yet their extreme size and scarce annotations make self-supervised learning essential. Masked Autoencoders (MAEs) with Vision Transformer backbones have recently shown strong potential…

Various work has suggested that the memorability of an image is consistent across people, and thus can be treated as an intrinsic property of an image. Using computer vision models, we can make specific predictions about what people will…

Live-cell imaging of multiple subcellular structures is essential for understanding subcellular dynamics. However, the conventional multi-color sequential fluorescence microscopy suffers from significant imaging delays and limited number of…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…