Related papers: Unsupervised learning for local structure detectio…
Most classification algorithms used in high energy physics fall under the category of supervised machine learning. Such methods require a training set containing both signal and background events and are prone to classification errors…
This paper introduces a fine-grained contrastive learning scheme for unsupervised node clustering. Previous clustering methods only focus on a small feature set (class-dependent features), which demonstrates explicit clustering…
We propose a computationally lean, two-stage approach that reliably predicts self-assembly behavior of complex charged molecules on a metallic surfaces under electrochemical conditions. Stage one uses ab initio simulations to provide…
We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces. In contrast to previous attempts, our model runs without the aid of spectral…
Spherically-symmetric atom-centered descriptors of atomic environments have been widely used for constructing potential or free energy surfaces of atomistic and colloidal systems and to characterize local structures using machine learning…
In many applications, data come with a natural ordering. This ordering can often induce local dependence among nearby variables. However, in complex data, the width of this dependence may vary, making simple assumptions such as a constant…
This paper presents a new self-supervised system for learning to detect novel and previously unseen categories of objects in images. The proposed system receives as input several unlabeled videos of scenes containing various objects. The…
This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different datasets. The training procedure uses homographic…
We show that neural networks trained by evolutionary reinforcement learning can enact efficient molecular self-assembly protocols. Presented with molecular simulation trajectories, networks learn to change temperature and chemical potential…
Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering,…
Unsupervised learning, a branch of machine learning that can operate on unlabelled data, has proven to be a powerful tool for data exploration and discovery in astronomy. As large surveys and new telescopes drive a rapid increase in data…
Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…
During the last ten years, a considerable amount of effort has been made to develop algorithms for automatic classification of variable stars. That has been primarily achieved by applying machine learning methods to photometric datasets…
Macromolecular and biomolecular folding landscapes typically contain high free energy barriers that impede efficient sampling of configurational space by standard molecular dynamics simulation. Biased sampling can artificially drive the…
Like fingerprints, cortical folding patterns are unique to each brain even though they follow a general species-specific organization. Some folding patterns have been linked with neurodevelopmental disorders. However, due to the high…
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly…
Local learning of sparse image models has proven to be very effective to solve inverse problems in many computer vision applications. To learn such models, the data samples are often clustered using the K-means algorithm with the Euclidean…
An important challenge in texture recognition is the limited amount of data for training frequently found in real-world applications. In computer vision in general, a successful strategy to mitigate this issue is the use of a pretraining…
In this paper we introduce a realistic and challenging, multi-source and multi-room acoustic environment and an improved algorithm for the estimation of source-dominated microphone clusters in acoustic sensor networks. Our proposed…
We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classified, and localized…