mlsanityData to 7 Oct 2026

Disentangled representations of microscopy images

arXiv 2506.20649 ↗First posted 25 Jun 2025cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Microscopy image analysis is fundamental for different applications, from diagnosis to synthetic engineering and environmental monitoring. Modern acquisition systems have granted the possibility to acquire an escalating amount of images, requiring a consequent development of a large collection of deep learning-based automatic image analysis methods. Although deep neural networks have demonstrated great performance in this field, interpretability, an essential requirement for microscopy image analysis, remains an open challenge. This work proposes a Disentangled Representation Learning (DRL) methodology to enhance model interpretability for microscopy image classification. Exploiting benchmark datasets from three different microscopic image domains (plankton, yeast vacuoles, and human cells), we show how a DRL framework, based on transferring a representation learnt from synthetic data, can provide a good trade-off between accuracy and interpretability in this domain.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 55 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

24 of 55 references.

References · 24

  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  2. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  3. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  4. 2016Ladder Variational Autoencoderscited by 315
  5. 2018Towards a Definition of Disentangled Representationscited by 294
  6. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  7. 2019On the Fairness of Disentangled Representationscited by 144
  8. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  9. 2022Disentangled Representation Learningcited by 111
  10. 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
  11. 2018Learning Deep Disentangled Embeddings with the F-Statistic Losscited by 101
  12. 2019Are Disentangled Representations Helpful for Abstract Visual Reasoning?cited by 100
12 more
  1. 2020On the Transfer of Disentangled Representations in Realistic Settingscited by 63
  2. 2019Theory and Evaluation Metrics for Learning Disentangled Representationscited by 57
  3. 2021Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning Viewcited by 34
  4. 2023DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Modelscited by 30
  5. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  6. 2016A Survey of Inductive Biases for Factorial Representation-Learningcited by 23
  7. 2021Learning disentangled representations via product manifold projectioncited by 20
  8. 2022A Contrastive Objective for Learning Disentangled Representationscited by 14
  9. 2022An Empirical Study on Disentanglement of Negative-free Contrastive Learningcited by 12
  10. 2023Flow Factorized Representation Learningcited by 11
  11. 2022Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecologycited by 10
  12. 2024Transferring disentangled representations: bridging the gap between synthetic and real imagescited by 1

Built on by

Not cited yet.