Face and Expression Recognition

Últimos artículos

• Which Tasks Survive Self-Supervised Learning?

  Achleshwar Luthra, Lucas Bryant, Tracy Zhu, Tomer Galanti · 1 de octubre de 2026

  Same-instance self-supervised learning (SSL) learns representations by enforcing consistency across two views of the same underlying instance. This principle alone, however, does not determine which downstream tasks remain recoverable from the learned representation. We study this question through \…

• Paired Multimodal Scaling Laws

  Marcus Ma, Shrikanth Narayanan · 30 de septiembre de 2026

  Existing multimodal scaling laws fit multimodality terms empirically after testing and never vary how much data is multimodally paired at fixed data budgets. We investigate how, under the same total data per modality, changing the number of paired data affects loss curves in multimodal classificatio…

• Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration

  Tavor Z. Baharav, Phillip B. Nicol, Rafael A. Irizarry, Rong Ma · 25 de septiembre de 2026

  Modern data analysis increasingly requires identifying shared latent structure across multiple high-dimensional datasets. A commonly used model assumes that the data matrices are noisy observations of low-rank matrices with a shared singular subspace. In this case, two primary methods have emerged f…

• When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection

  Mehmet Yama\c{c}, Yagmur Mustu, Muhammad Numan Yousaf, Lei Xu, Marcel van Gerven · 25 de septiembre de 2026

  Reconstruction-based unsupervised learning can fail in two opposing ways: a model may reconstruct anomalies too accurately or discard valid nominal variation. Using the Pursuit of Subspaces hypothesis, we characterize these failures through the meet, union, and join geometries induced by the nominal…

• Beyond Accuracy: Centroid-Guided Contrastive Loss for Structured Fraudulent Job Posting Detection

  Syed Ali Ahmed (National University of Computer and Emerging Sciences, Karachi, Pakistan), Malaika Raza (National University of Computer and Emerging Sciences, Karachi, Pakistan), Muhammad Shoaib Siddiqui (Islamic University of Madinah, Madinah, Saudi Arabia), Muhammad Rafi (National University of Computer and Emerging Sciences, Karachi, Pakistan) · 21 de septiembre de 2026

  Fraudulent job posting detection aims to identify job advertisements that are corrupted either through fake content, misleading information, or negative intent, disrupting the online eco-system of job-seekers and employers. Existing studies in this domain lack effective methods to simultaneously ach…

• Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs

  Zhenlin Yao, Wei Xiong · 18 de septiembre de 2026

  Accurate optimization of a supervised spectral objective need not produce an accurate population subspace or a better predictive representation. We investigate these distinctions for Online Kernel Supervised Principal Component Analysis (OKSPCA), which combines a centered cross-moment in finite rand…

• Learning Submanifolds for Subsequent Inference on Random Dot Product Graphs, Part 1: Theory

  Michael W. Trosset, Carey E. Priebe · 18 de septiembre de 2026

  We propose a framework for restricted inference on random dot product graphs whose latent positions lie on an unknown low-dimensional support manifold. For general decision problems, we propose semisupervised decision rules that use auxiliary data to learn the support manifold. Specifically, our rul…

• Subdomain-aware representation compression for pretrained image embeddings

  Poowanut Niamluang, Jittat Fakcharoenphol · 18 de septiembre de 2026

  Dimensionality reduction is a well-known technique for improving space efficiency, typically applied uniformly across an entire dataset. This paper investigates the possibilities of using dimensionality reduction techniques for subdomain representation compression. We explore standard techniques suc…

• Alliance Beats Isolation: Unifying Heterogeneous Allied Datasets Improves Classifier Performance

  Girish Keshav Palshikar · 18 de septiembre de 2026

  In many application domains, such as student dropout, insurance fraud, loan approval, and machine failures, several labelled public datasets are available where (i) data is about the same type of objects but the set of actual underlying objects are disjoint; and (ii) the class labels are same; and (…

• The Rank the Task Demands: A Causal Rank Law for Matrix Memories Trained on Group Composition

  Samuel Larson · 14 de septiembre de 2026

  Matrix-valued memories make rank the natural budget of a learned representation: the number of independent directions a state spans bounds what it can bind, compose, and track. We report causal evidence, on a group-composition testbed trained under a hard single-state bottleneck with a fixed decoder…

• Predicting Privacy Leakage from Weight Spectral Density

  Richard J. Preen, Jim Smith · 11 de septiembre de 2026

  Membership inference attacks (MIAs) are widely used to audit the privacy disclosure risk of machine learning models, however current state-of-the-art attacks require training computationally expensive shadow models, making large-scale privacy evaluation impractical. In this work, we investigate whet…

• A Kernel-Based Modular Discriminant Analysis Framework for Small-Sample Learning

  Lingxiao Qu, Yan Pei · 10 de septiembre de 2026

  The small-sample-size (SSS) problem remains a fundamental challenge in machine learning when labeled data are scarce due to cost, accessibility, or ethical constraints. While numerous approaches have been proposed, existing methods often struggle to maintain stable and discriminative representations…

• Exact Degeneracy Under Balanced k-Shot Sampling:Consequences for Small-Sample Discriminant Analysis on LLM Embeddings

  Lingxiao Qu · 10 de septiembre de 2026

  Balanced k-shot sampling draws exactly k labeled examples per class. We show that it induces an exact, provable degeneracy in a family of small-sample discriminant estimators. Under balanced sampling, the within-class scatter operator of Kernelized Linear Principal Component Discriminant Analysis (K…

• Revisiting Thinning Methods for Kernel Learning Problems

  Blanca Cano-Camarero, Yago R. Aguado-Carrillo-de-Albornoz, \'Angela Fern\'andez-Pascual, Jos\'e R. Dorronsoro · 9 de septiembre de 2026

  Kernel methods are widely used because of their strong theoretical guarantees and empirical performance. However, their high computational cost limits their applicability to large-scale datasets. To address this shortcoming, several approaches use Maximum Mean Discrepancy to construct representative…

• Geometry-Aware Graph Construction via Adaptive Spectral Bandwidth Control

  Ecem Bozkurt, Antonio Ortega · 4 de septiembre de 2026

  Kernelized graph methods - spectral clustering, diffusion maps, and sparse kernel -regression graphs - that use Gaussian kernels depend on the choice of Gaussian bandwidth sigma, which governs the spectral character of the local kernel operator. When sigma is too small, the kernel overestimates loca…

• When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection

  Utsab Ghosh, Roshni Chakraborty · 2 de septiembre de 2026

  Unsupervised feature selection seeks a compact subset of informative features without access to class labels, making feature utility difficult to define. Existing UFS methods therefore rely on indirect structural criteria, such as similarity preservation, locality, sparsity, cluster geometry, or rec…

• A Deeper Analysis of Block-Sparse Featurizers

  Alexandru-Iulius Jerpelea, Amith Ananthram · 31 de agosto de 2026

  The recently introduced block-sparse featurizer (BSF; Fel et al., 2026) is similar to a sparse autoencoder (SAE), but its atomic unit is a small subspace (a block of directions) rather than a single direction. It is designed for features that live on low-dimensional manifolds, which are especially f…

• Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification

  Alexandre L. M. Levada · 31 de agosto de 2026

  Nearest neighbor classification relies fundamentally on how locality is defined, yet conventional $k$-NN imposes the same neighborhood cardinality throughout the feature space. This assumption can be inadequate for data whose local geometry varies substantially across the underlying manifold. We int…

• Efficient Estimation of High Information Projections using Nearest Neighbours

  David P. Hofmeyr · 27 de agosto de 2026

  An intuitive method for dimensionality reduction is proposed, which is highly effective for finding interesting projections of multivariate data. Following similar intuitive motivation to a number of existing techniques, the proposed method is based on enhancing the nearest neighbour relationships i…

• Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignment

  Huang Weiquan · 27 de agosto de 2026

  Multimodal regression suffers from the mean-collapse pathology: under squared loss, an unconstrained regressor converges to the conditional mean, which for K > 1 lies away from all modes. We attribute this failure to pairwise contradictions--samples with nearly identical inputs but distant outputs--…

• Why Can't I See My Clusters? A Precision-Recall Approach to Dimensionality Reduction Validation

  Diede P. M. van der Hoorn, Alessio Arleo, Fernando V. Paulovich · 21 de agosto de 2026

  Dimensionality Reduction (DR) is widely used for visualizing high-dimensional data, often with the goal of revealing expected cluster structure. However, such a structure may not always appear in the projections. Existing DR quality metrics assess projection reliability (to some extent) or cluster s…

• Fair Multi-View Determinantal Coresets via Adaptive NEPv

  Richard Yi Da Xu · 19 de agosto de 2026

  Selecting a small, diverse subset from a large candidate pool often means balancing several incompatible notions of diversity. In trademark curation, for instance, a subset should cover both the language used to describe marks and the visual space of their logos. A single determinantal point process…

• How smoothing the affinity matrix affects neighborhood preservation in t-SNE

  Shirin Mohebi, Guillaume Bied, Jefrey Lijffijt · 19 de agosto de 2026

  Dimensionality reduction methods are instrumental to visualize high-dimensional data, and t-SNE stands as one of the most widely used methods due to its emphasis on local neighborhood preservation. A central component of t-SNE is the affinity matrix, which expresses pairwise similarities in the form…

• Diagonal Multi-omics Integration of Heterogenous Datasets

  Maksim V. Kukushkin, Mikhail S. Arbatskiy, Dmitriy E. Balandin, Alexey V. Churov · 18 de agosto de 2026

  In this paper, we consider methods for the diagonal multi-omics integration of heterogeneous datasets. Several approaches to the nature of biological heterogeneity are analyzed and developed to comprehend more clearly the generated differences. Specifically, the extremal trace problems for the coupl…

• Online Learning of Correspondences between Images

  Michael Felsberg, Fredrik Larsson, Johan Wiklund, Niclas Wadströmer, Jörgen Ahlberg · 14 de agosto de 2026

  We propose a novel method for iterative learning of point correspondences between image sequences. Points moving on surfaces in 3D space are projected into two images. Given a point in either view, the considered problem is to determine the corresponding location in the other view. The geometry and …