Related papers: Model-Free Cluster Analysis of Physical Property D…

This paper presents an automatic method for data classification in nuclear physics experiments based on evolutionary computing and vector quantization. The major novelties of our approach are the fully automatic mechanism and the use of…

In this paper, we consider the problem of autonomous driving using imitation learning in a semi-supervised manner. In particular, both labeled and unlabeled demonstrations are leveraged during training by estimating the quality of each…

Many datasets have been shown to contain incidental correlations created by idiosyncrasies in the data collection process. For example, sentence entailment datasets can have spurious word-class correlations if nearly all contradiction…

We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches resort to the meta-learning paradigm, where the model…

Self-training is a simple yet effective method within semi-supervised learning. The idea is to iteratively enhance training data by adding pseudo-labeled data. Its generalization performance heavily depends on the selection of these…

Multiple instance data are sets or multi-sets of unordered elements. Using metrics or distances for sets, we propose an approach to several multiple instance learning tasks, such as clustering (unsupervised learning), classification…

Constrained clustering allows the training of classification models using pairwise constraints only, which are weak and relatively easy to mine, while still yielding full-supervision-level model performance. While they perform well even in…

Estimating the number of clusters and cluster structures in unlabeled, complex, and high-dimensional datasets (like images) is challenging for traditional clustering algorithms. In recent years, a matrix reordering-based algorithm called…

In this paper, a novel semi-supervised dictionary learning and sparse representation (SS-DLSR) is proposed. The proposed method benefits from the supervisory information by learning the dictionary in a space where the dependency between the…

In the last few years, unpaired image-to-image translation has witnessed remarkable progress. Although the latest methods are able to generate realistic images, they crucially rely on a large number of labeled images. Recently, some methods…

Recent developments in self-supervised learning (SSL) have made it possible to learn data representations without the need for annotations. Inspired by the non-contrastive SSL approach (SimSiam), we introduce a novel framework SIMSAM to…

Creating separable representations via representation learning and clustering is critical in analyzing large unstructured datasets with only a few labels. Separable representations can lead to supervised models with better classification…

Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which…

Building generalizable medical AI systems requires pretraining strategies that are data-efficient and domain-aware. Unlike internet-scale corpora, clinical datasets such as MIMIC-CXR offer limited image counts and scarce annotations, but…

Semi-supervised learning techniques are gaining popularity due to their capability of building models that are effective, even when scarce amounts of labeled data are available. In this paper, we present a framework and specific tasks for…

Costly, noisy, and over-specialized, labels are to be set aside in favor of unsupervised learning if we hope to learn cheap, reliable, and transferable models. To that end, spectral embedding, self-supervised learning, or generative…

To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous…

We present TWIST, a simple and theoretically explainable self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to…

We present PhISM, a physics-informed deep learning architecture that learns without supervision to explicitly disentangle hyperspectral observations and model them with continuous basis functions. PhISM outperforms prior methods on several…

We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios. The key idea is to leverage the spatiotemporal nature of a dynamic point cloud sequence and introduce drastically…