Related papers: Symmetries, Safety, and Self-Supervision
Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones. We cast SSL…
While Contrastive Learning (CL) has revolutionized self-supervised representation learning, its latent representations remain highly entangled and opaque, limiting their interpretability in safety-critical applications. We identify that a…
In the image domain, excellent representations can be learned by inducing invariance to content-preserving transformations via noise contrastive learning. In this paper, we generalize contrastive learning to a wider set of transformations,…
Personalized search plays a crucial role in improving user search experience owing to its ability to build user profiles based on historical behaviors. Previous studies have made great progress in extracting personal signals from the query…
We investigate the role of symmetric quantum cloning machines (QCMs) in quantifying the mutual incompatibility of quantum observables. Specifically, we identify a cloning-based incompatibility measure whereby the incompatibility of a set of…
This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, namely NCLR, focuses on 2D-3D neural calibration, a novel pretext task that estimates the…
We present a systematic evaluation of representation learning objectives for particle physics within a unified framework. Our study employs a shared transformer-based particle-cloud encoder with standardized preprocessing, matched sampling,…
Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive…
Understanding the inner working of the quark-gluon plasma requires complete and precise jet substructure studies in heavy ion collisions. In this proceeding we discuss the use of quark and gluon jets as independent probes, and how their…
Perturbation Theory to Large Scale Structure Cosmology proposes corrections to the linearly evolved density contrast and velocity in terms of a series development in which all terms are integrals of powers of the linear density contrast…
We study complex-valued scaling as a type of symmetry natural and unique to complex-valued measurements and representations. Deep Complex Networks (DCN) extends real-valued algebra to the complex domain without addressing complex-valued…
The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level…
Unsupervised anomaly detection in medical imaging aims to detect and localize arbitrary anomalies without requiring annotated anomalous data during training. Often, this is achieved by learning a data distribution of normal samples and…
Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representations induced by the…
In this paper, we provide a computable characterization of the geometry of optimal representations in Contrastive Learning (CL) when the classes are imbalanced. When classes are balanced and the representation dimension is greater than the…
Unlike natural images with occlusion-based overlap, X-ray images exhibit depth-induced superimposition and semi-transparent appearances, where objects at different depths overlap and their features blend together. These characteristics…
High content imaging assays can capture rich phenotypic response data for large sets of compound treatments, aiding in the characterization and discovery of novel drugs. However, extracting representative features from high content images…
Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (closeness) of features from positive pairs, and (2) uniformity…
Data representation is usually a natural form with their attribute values. On this basis, data processing is an attribute-centered calculation. However, there are three limitations in the attribute-centered calculation, saying, inflexible…