Interpretable Self-Supervised Learning
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification
Announce Type: replace-cross Abstract: X-ray computed tomography (XCT) is widely used for non-destructive testing of Nomex honeycomb structures in aerospace manufacturing, but industrial inspection still relies heavily on manual interpretation and supervised models trained on limited labeled data. This work introduces NL-MambaXCT, a Mamba-based framework that combines self-supervised masked image modelling with a Nested Learning (NL) formulation for automated, label-efficient defect...
Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\"om Approximation
Announce Type: replace Abstract: Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific explanations. We introduce KREPES, a unified framework to analytically interpret the learned representations of SSL objectives, including SimCLR, BYOL, and VICReg. By bridging empirical neural tangent kernel approximations of neural networks with the Representer Theorem for kernels, we...
Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\"om Approximation
arXiv:2509.24467v3 Announce Type: replace Abstract: Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necessitating domain-specific explanations. We introduce KREPES, a unified framework to analytically interpret the learned representations of SSL objectives, including SimCLR, BYOL, and VICReg. By bridging empirical neural tangent kernel approximations of neural networks with the Representer Theorem...
STEP: Learning STructured Embeddings for Progressive Time Series
arXiv:2605.31061v1 Announce Type: new Abstract: We present a novel method for learning interpretable representations of progressive time series, that is, data capturing irreversible state transitions such as degradation or task completion. Our approach uses a self-supervised contrastive objective to learn a low-dimensional latent space whose geometry is itself the interpretation: each observation becomes a point on a manifold anchored between two fixed orthogonal prototype vectors, and a...
Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models
Announce Type: new Abstract: Earth Observation (EO) has fundamentally transformed the monitoring of environmental processes and human activities up to planetary scale. Recent advances in self-supervised learning have given rise to Earth Observation Foundation Models (EOFMs), which leverage petabyte-scale unlabeled EO data to learn transferable representations across a wide range of downstream geospatial tasks. Despite these advances, current EOFMs remain largely confined to raster...
Integrating gene regulatory priors into Transformer attention with scTransformer for interpretable scRNA-seq analysis
Announce Type: cross Abstract: Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supervised learning on millions of cells. However, most existing approaches treat genes as independent features, and largely ignore prior biological knowledge, which limits interpretability and robustness. In this paper, we explore whether explicitly incorporating gene regulatory information can improve both model...
VISReg: Variance-Invariance-Sketching Regularization for JEPA training
Announce Type: new Abstract: Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regularization into variance and covariance objectives, offering flexibility and interpretability. However, covariance captures only second-order statistics -- encouraging decorrelation but failing to enforce the full distributional shape needed for stable training.
MAD: Mapping-Aware World Models for Agile Quadrotor Flight
Announce Type: new Abstract: Agile quadrotor flight in cluttered scenes requires more than a reactive mapping from a depth image to a control command: the vehicle must remember which regions have been observed, infer nearby occupied space, and act under partial visibility and tight latency. In this paper, we present Mapping-Aware Dreamer (MAD), a geometry-aware world model for vision-based quadrotor flight. Instead of using raw-image reconstruction as the main self-supervised objective, MAD...
A Foundation Model for the Cancer Genome
Cancer is a disease of the genome, in which somatic mutations and copy-number alterations determine tumour identity, clinical behaviour, and response to therapy. Consortium-scale sequencing has profiled hundreds of thousands of tumours, yet clinical interpretation still proceeds one alteration at a time against hand-curated knowledgebases, often ignoring co-occurring alterations and the genome-wide copy-number pattern. Self-supervised foundation models pretrained on unlabelled corpora have...
A Foundation Model for Wearable Movement Data in Mental Health Research
arXiv:2411.15240v5 Announce Type: replace Abstract: Wearable movement data is collected by nearly all commercially available smartwatches and is a valuable resource for mental health research, reflecting fine-grained temporal behavioral trends. Despite its promise, the development of foundation models for health wearable modeling remains limited when compared to clinical image and text analysis. We designed transformers with patch embeddings and used self-supervised masked autoencoder...