REVIEW 5 cited by
Deep Transparent Prediction through Latent Representation Analysis
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The paper presents a novel deep learning approach, which extracts latent information from trained Deep Neural Networks (DNNs) and derives concise representations that are analyzed in an effective, unified way for prediction purposes. It is well known that DNNs are capable of analyzing complex data; however, they lack transparency in their decision making, in the sense that it is not straightforward to justify their prediction, or to visualize the features on which the decision was based. Moreover, they generally require large amounts of data in order to learn and become able to adapt to different environments. This makes their use difficult in healthcare, where trust and personalization are key issues. Transparency combined with high prediction accuracy are the targeted goals of the proposed approach. It includes both supervised DNN training and unsupervised learning of latent variables extracted from the trained DNNs. Domain Adaptation from multiple sources is also presented as an extension, where the extracted latent variable representations are used to generate predictions in other, non-annotated, environments. Successful application is illustrated through a large experimental study in various fields: prediction of Parkinson's disease from MRI and DaTScans; prediction of COVID-19 and pneumonia from CT scans and X-rays; optical character verification in retail food packaging.
Forward citations
Cited by 5 Pith papers
-
DVD: A Comprehensive Dataset for Advancing Violence Detection in Real-World Scenarios
The authors propose a new frame-level annotated violence detection dataset, DVD, with 500 videos and rich metadata, but it is not yet available and lacks validation experiments.
-
Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization
Input-space standardization via lung cropping and density-based slice sampling reduces inter-source feature variance by 75% and improves COVID-19 CT classification F1 by roughly 24 points across architectures.
-
Multi-Source COVID-19 Detection via Variance Risk Extrapolation
A challenge entry combining VREx and Mixup in a two-stage training pipeline reports 0.96 macro F1 on a four-hospital COVID-19 CT validation set, but without baselines or statistical validation.
-
Multi Source COVID-19 Detection via Kernel-Density-based Slice Sampling
EfficientNet-B7 with SSFL and KDS slice sampling achieves 94.68 F1 on a multi-source COVID-19 CT validation set, outperforming Swin Transformer-Base's 93.34, though the evaluation has class-imbalance and no-ablation issues.
-
Advancing Lung Disease Diagnosis in 3D CT Scans
A 3D ResNeSt50 model with slice removal and weighted cross-entropy achieves a Macro F1 of 0.80 on the Fair Disease Diagnosis Challenge validation set.
Discussion (0). Sign in to comment.