Related papers: Urban Region Embedding via Multi-View Contrastive …

Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…

While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity decomposition. We develop a measure-theoretic framework in which representation measures…

Conformal prediction provides distribution-free coverage guarantees, but in many-class classification it may still under-cover specific classes or subpopulations, preventing safe deployment in high-stakes applications. We propose Cluster…

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…

Vision-based bird's-eye-view (BEV) 3D object detection has advanced significantly in autonomous driving by offering cost-effectiveness and rich contextual information. However, existing methods often construct BEV representations by…

Typical methods for pedestrian detection focus on either tackling mutual occlusions between crowded pedestrians, or dealing with the various scales of pedestrians. Detecting pedestrians with substantial appearance diversities such as…

We consider learning from labeled data collected across multiple environments, where the data distribution may vary across these environments. This problem is commonly approached from a causal perspective, seeking invariant representations…

Recent contrastive representation learning methods rely on estimating mutual information (MI) between multiple views of an underlying context. E.g., we can derive multiple views of a given image by applying data augmentation, or we can…

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained…

We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a…

Accurately predicting the likelihood of interaction between two objects (compound-protein sequence, user-item, author-paper, etc.) is a fundamental problem in Computer Science. Current deep-learning models rely on learning accurate…

Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure. Although the spectral clustering based methods achieve promotion in multi-view clustering, their…

In many applications, the pairwise constraint is a kind of weaker supervisory information which can be collected easily. The constraint propagation has been proved to be a success of exploiting such side-information. In recent years, some…

Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically aligned shared space. This paradigm shows remarkable generalization ability on numerous downstream tasks across various modalities.…

Representing urban regions accurately and comprehensively is essential for various urban planning and analysis tasks. Recently, with the expansion of the city, modeling long-range spatial dependencies with multiple data sources plays an…

In multi-contrast magnetic resonance imaging (MRI), compressed sensing theory can accelerate imaging by sampling fewer measurements within each contrast. The conventional optimization-based models suffer several limitations: strict…

With the increasing availability of geospatial datasets, researchers have explored region representation learning (RRL) to analyze complex region characteristics. Recent RRL methods use contrastive learning (CL) to capture shared…

Computer vision can be understood as the ability to perform inference on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques. This thesis proposes novel inference schemes and…

Multi-view representation learning captures comprehensive information from multiple views of a shared context. Recent works intuitively apply contrastive learning (CL) to learn representations, regarded as a pairwise manner, which is still…

Understanding how cities visually differ from each others is interesting for planners, residents, and historians. We investigate the interpretation of deep features learned by convolutional neural networks (CNNs) for city recognition. Given…