arXiv Machine Learning

Subdomain-aware representation compression for pretrained image embeddings

The paper explores subdomain-aware dimensionality reduction for pretrained image embeddings, applying techniques such as PCA and LDA to compress representations within specific image subdomains. Results show that this targeted compression reduces space and computational complexity while improving accuracy compared to using full embeddings. Additionally, the study demonstrates that the compressed representations retain transfer learning capabilities across tasks.

arXiv Machine Learning

Aug 31

EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders

EXPOSE is a framework that applies Sparse Autoencoders to Vision Foundation Model embeddings in computational pathology, aiming to separate biological signals from domain‑specific noise. By training a sparse representation of VFM features and using a linear classifier to flag domain‑specific latent dimensions, the method masks these components before downstream relapse prediction, avoiding the need to retrain the backbone model. Experiments on a large prostate cancer dataset demonstrate that removing domain‑specific features improves cross‑domain performance and raises the Domain Robustness Index (DoRI).

By Anja Witte, Maximilian Lennartz, Jan Baumbach, Guido Sauter, Stefan Bonn, Patrick Fuhlert, Marina Zimmermann

rag diffusion

arXiv Machine Learning

Jun 5

Anchor PCA

arXiv:2606. 06233v1 Announce Type: cross Abstract: Principal component analysis (PCA) is one of the most widely used unsupervised dimension reduction techniques.

By Benedikt Seiter, Anya Fries, Julius von K\"ugelgen, Jonas Peters

rag

arXiv Statistics ML

3d ago

Barycentric subspace analysis of network-valued data

arXiv:2507.23559v2 Announce Type: replace-cross Abstract: Certain data are naturally modeled by networks or weighted graphs, be they biological networks or mobility networks. When there is no canonic...

By Elodie Maignant, Xavier Pennec, Alain Trouv\'e, Anna Calissano

rag safety

arXiv Machine Learning

Jun 3

A Robust Optimization Approach to Sparse Principal Component Analysis

arXiv:2606. 03553v1 Announce Type: cross Abstract: While principal component analysis (PCA) is a fundamental tool for dimensionality reduction, its dense representations make it ill-suited for high-dimensional data.

By David V\"avinggren, Francis Bach, Andr\'e M. H. Teixeira, Dave Zachariah, Ant\^onio H. Ribeiro

diffusion efficiency safety

arXiv AI

Jul 16

DIVE: Embedding Compression via Self-Limiting Gradient Updates

arXiv:2605. 20689v2 Announce Type: replace-cross Abstract: High-dimensional language-model embeddings increase storage and search costs, while supervised compressors can overfit when relevance labels are scarce.

By Dongfang Zhao

rag efficiency benchmarks

arXiv Machine Learning

4d ago

Are In-Context Images Worth 10 Dimensions?

arXiv:2609.37659v1 Announce Type: cross Abstract: There has been significant work on understanding the In-Context Learning capabilities of Large Language Models, especially on the induction circuit....

By Adhemar de Senneville, Xavier Bou, J\'er\'emy Anger, Rafael Grompone, Gabriele Facciolo

llms computer-vision

Hugging Face Trending Papers

4d ago

Are In-Context Images Worth 10 Dimensions?

There has been significant work on understanding the In-Context Learning capabilities of Large Language Models, especially on the induction circuit. For a few-shot classification task, the induction c...

llms computer-vision

arXiv Machine Learning

Jun 2

MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment

arXiv:2605. 29987v2 Announce Type: replace Abstract: Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse.

By Dang Nguyen Hong, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham

rag efficiency safety

Towards Data Science

Jul 14

A Gentle Introduction to Autoencoders & Latent Space

Introduction Heavy computation is a well-known problem in various ML algorithms today, especially when generative AI is applied to text, images, and other unstructured data. One of the principal approaches to mitigate this problem is to compress input data into a lower-dimensional representation while preserving the main context.

By Vyacheslav Efimov

diffusion

arXiv AI

Aug 5

Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignment

arXiv:2407. 21311v2 Announce Type: replace-cross Abstract: Unsupervised domain adaptation (UDA) aims to mitigate domain shift, where the distribution of labeled source data differs from that of unlabeled target data.

By Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah

llms computer-vision fine-tuning safety

arXiv Computer Vision

6d ago

VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation

arXiv:2503.10685v3 Announce Type: replace Abstract: Unsupervised Domain Adaptation (UDA) enables strong generalization from a labeled source domain to an unlabeled target domain, often with limited d...

By Brun\'o B. Englert, Gijs Dubbelman

computer-vision fine-tuning benchmarks

arXiv Machine Learning

Aug 10

PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder

arXiv:2601. 19179v2 Announce Type: replace Abstract: Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA).

By Qipeng Zhan, Zhuoping Zhou, Zexuan Wang, Li Shen

diffusion

Related stories