Out of Distribution Generalization via Interventional Style Transfer in
Single-Cell Microscopy
- URL: http://arxiv.org/abs/2306.11890v1
- Date: Thu, 15 Jun 2023 20:08:16 GMT
- Title: Out of Distribution Generalization via Interventional Style Transfer in
Single-Cell Microscopy
- Authors: Wolfgang M. Pernice, Michael Doron, Alex Quach, Aditya Pratapa, Sultan
Kenjeyev, Nicholas De Veaux, Michio Hirano, Juan C. Caicedo
- Abstract summary: Real-world deployment of computer vision systems requires causal representations that are invariant to contextual nuisances.
We propose tests to assess the extent to which models learn causal representations across increasingly challenging levels of OOD-generalization.
We show that despite seemingly strong performance, as assessed by other established metrics, both naive and contemporary baselines designed to ward against confounding, collapse on these tests.
- Score: 1.7778546320705952
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Real-world deployment of computer vision systems, including in the discovery
processes of biomedical research, requires causal representations that are
invariant to contextual nuisances and generalize to new data. Leveraging the
internal replicate structure of two novel single-cell fluorescent microscopy
datasets, we propose generally applicable tests to assess the extent to which
models learn causal representations across increasingly challenging levels of
OOD-generalization. We show that despite seemingly strong performance, as
assessed by other established metrics, both naive and contemporary baselines
designed to ward against confounding, collapse on these tests. We introduce a
new method, Interventional Style Transfer (IST), that substantially improves
OOD generalization by generating interventional training distributions in which
spurious correlations between biological causes and nuisances are mitigated. We
publish our code and datasets.
Related papers
- Learning Divergence Fields for Shift-Robust Graph Representations [73.11818515795761]
In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging problem with interdependent data.
We derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains.
arXiv Detail & Related papers (2024-06-07T14:29:21Z) - Utilizing Weak-to-Strong Consistency for Semi-Supervised Glomeruli Segmentation [0.803784679671919]
We present a semi-supervised learning approach for glomeruli segmentation based on the weak-to-strong consistency framework validated on multiple real-world datasets.
Our experimental results on 3 independent datasets indicate superior performance of our approach as compared with existing supervised baseline models.
arXiv Detail & Related papers (2024-05-30T10:19:21Z) - Rethinking Model Prototyping through the MedMNIST+ Dataset Collection [0.11999555634662634]
This work presents a benchmark for the MedMNIST+ database to diversify the evaluation landscape.
We conduct a thorough analysis of common convolutional neural networks (CNNs) and Transformer-based architectures, for medical image classification.
Our findings suggest that computationally efficient training schemes and modern foundation models hold promise in bridging the gap between expensive end-to-end training and more resource-refined approaches.
arXiv Detail & Related papers (2024-04-24T10:19:25Z) - Seeing Unseen: Discover Novel Biomedical Concepts via
Geometry-Constrained Probabilistic Modeling [53.7117640028211]
We present a geometry-constrained probabilistic modeling treatment to resolve the identified issues.
We incorporate a suite of critical geometric properties to impose proper constraints on the layout of constructed embedding space.
A spectral graph-theoretic method is devised to estimate the number of potential novel classes.
arXiv Detail & Related papers (2024-03-02T00:56:05Z) - Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image.
In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting.
Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
arXiv Detail & Related papers (2023-11-27T13:14:06Z) - A Comprehensive Augmentation Framework for Anomaly Detection [1.90365714903665]
This paper analyzes crucial traits of simulated anomalies that contribute to the training of reconstructive networks.
We integrate this framework with a reconstruction-based approach and concurrently propose a split training strategy.
arXiv Detail & Related papers (2023-08-29T07:00:35Z) - Causal Balancing for Domain Generalization [95.97046583437145]
We propose a balanced mini-batch sampling strategy to reduce the domain-specific spurious correlations in observed training distributions.
We provide an identifiability guarantee of the source of spuriousness and show that our proposed approach provably samples from a balanced, spurious-free distribution.
arXiv Detail & Related papers (2022-06-10T17:59:11Z) - Learning Neural Causal Models with Active Interventions [83.44636110899742]
We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process.
Our method significantly reduces the required number of interactions compared with random intervention targeting.
We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
arXiv Detail & Related papers (2021-09-06T13:10:37Z) - Cohort Bias Adaptation in Aggregated Datasets for Lesion Segmentation [0.8466401378239363]
We propose a generalized affine conditioning framework to learn and account for cohort biases across multi-source datasets.
We show that our cohort bias adaptation method improves performance of the network on pooled datasets.
arXiv Detail & Related papers (2021-08-02T08:32:57Z) - An Empirical Framework for Domain Generalization in Clinical Settings [14.363133217553715]
We benchmark the performance of eight domain generalization methods on multi-site clinical time series and medical imaging data.
We find that current domain generalization methods do not achieve significant gains in out-of-distribution performance over empirical risk minimization.
arXiv Detail & Related papers (2021-03-20T11:48:57Z) - Adversarial Sample Enhanced Domain Adaptation: A Case Study on
Predictive Modeling with Electronic Health Records [57.75125067744978]
We propose a data augmentation method to facilitate domain adaptation.
adversarially generated samples are used during domain adaptation.
Results confirm the effectiveness of our method and the generality on different tasks.
arXiv Detail & Related papers (2021-01-13T03:20:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.