Related papers: Foundation Model Makes Clustering A Better Initial…

Neural Network-based active learning (NAL) is a cost-effective data selection technique that utilizes neural networks to select and train on a small subset of samples. While existing work successfully develops various effective or…

The task of clustering unlabeled time series and sequences entails a particular set of challenges, namely to adequately model temporal relations and variable sequence lengths. If these challenges are not properly handled, the resulting…

A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting…

The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this…

We address the problem of federated learning (FL) where users are distributed and partitioned into clusters. This setup captures settings where different groups of users have their own objectives (learning tasks) but by aggregating their…

Semantic and instance segmentation algorithms are two general yet distinct image segmentation solutions powered by Convolution Neural Network. While semantic segmentation benefits extensively from the end-to-end training strategy, instance…

Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-style latent…

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…

Cold-Start Active Learning (CSAL) aims to select informative samples for annotation without prior knowledge, which is important for improving annotation efficiency and model performance under a limited annotation budget in medical image…

Spectral clustering is a leading clustering method. Two of its major shortcomings are the disjoint optimization process and the limited representation capacity. To address these issues, we propose a deep spectral clustering model (named…

Large-scale datasets have been pivotal to the advancements of deep learning models in recent years, but training on such large datasets invariably incurs substantial storage and computational overhead. Meanwhile, real-world datasets often…

Recent advances in image clustering typically focus on learning better deep representations. In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and…

Time-series clustering serves as a powerful data mining technique for time-series data in the absence of prior knowledge about clusters. A large amount of time-series data with large size has been acquired and used in various research…

Recent studies of large-scale contrastive pretraining in the text embedding domain show that using single-source minibatches, rather than mixed-source minibatches, can substantially improve overall model accuracy. In this work, we explore…

Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addressed by clustering the sentences in a training corpus…

The structure of many complex networks includes edge directionality and weights on top of their topology. Network analysis that can seamlessly consider combination of these properties are desirable. In this paper, we study two important…

Clustering algorithms partition a dataset into groups of similar points. The clustering problem is very general, and different partitions of the same dataset could be considered correct and useful. To fully understand such data, it must be…

Efficient extraction of useful knowledge from these data is still a challenge, mainly when the data is distributed, heterogeneous and of different quality depending on its corresponding local infrastructure. To reduce the overhead cost,…

The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To mitigate this, the concept of active finetuning has emerged,…

We introduce a novel validation framework to measure the true robustness of learning models for real-world applications by creating source-inclusive and source-exclusive partitions in a dataset via clustering. We develop a robustness metric…