Related papers: Consistent Supervised-Unsupervised Alignment for G…

Traditional sparse and dense retrieval methods struggle to leverage general world knowledge and often fail to capture the nuanced features of queries and products. With the advent of large language models (LLMs), industrial search systems…

Existing deep learning models have achieved promising performance in recognizing skin diseases from dermoscopic images. However, these models can only recognize samples from predefined categories, when they are deployed in the clinic, data…

In the field of continual learning, relying on so-called oracles for novelty detection is commonplace albeit unrealistic. This paper introduces CONCLAD ("COntinuous Novel CLAss Detector"), a comprehensive solution to the under-explored…

Discovering novel classes in open-world settings is crucial for real-world applications. Traditional explicit representations, such as object descriptors or 3D segmentation maps, are constrained by their discrete, hole-prone, and noisy…

Out-of-distribution (OOD) detection is paramount to ensuring the reliability and robustness of learning models in real-world applications. Existing post-hoc OOD detection methods detect OOD samples by leveraging their features and logits…

Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction.…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging problem due to the lack of…

Recent studies on Neural Collapse (NC) reveal that, under class-balanced conditions, the class feature means and classifier weights spontaneously align into a simplex equiangular tight frame (ETF). In long-tailed regimes, however, severe…

We present Generalized Contrastive Divergence (GCD), a novel objective function for training an energy-based model (EBM) and a sampler simultaneously. GCD generalizes Contrastive Divergence (Hinton, 2002), a celebrated algorithm for…

Automatic emotion recognition based on multichannel Electroencephalography (EEG) holds great potential in advancing human-computer interaction. However, several significant challenges persist in existing research on algorithmic emotion…

Despite the success of deep neural networks in medical image classification, the problem remains challenging as data annotation is time-consuming, and the class distribution is imbalanced due to the relative scarcity of diseases. To address…

This paper studies the problem of graph-level clustering, which is a novel yet challenging task. This problem is critical in a variety of real-world applications such as protein clustering and genome analysis in bioinformatics. Recent years…

One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the…

Deep neural network (DNN) models have shown remarkable success in many real-world scenarios, such as object detection and classification. Unfortunately, these models are not yet widely adopted in health monitoring due to exceptionally high…

Clustering is a widely-used data mining tool, which aims to discover partitions of similar items in data. We introduce a new clustering paradigm, \emph{accordant clustering}, which enables the discovery of (predefined) group level insights.…

Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributions. In practice, annotations are scarce, and images are…

Semi-supervised learning addresses label scarcity and high annotation costs in medical image segmentation by exploiting the latent information in unlabeled data to enhance model performance. Traditional discriminative segmentation relies on…

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the original graph structures;…

Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of local models as the key bottleneck. Previous attempts have used classifier…