arXiv AI
Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 23
Less Is More in the Long Tail: Stage-Adaptive Sample Selection for Annotation-Efficient Dense Prediction
arXiv:2609.25850v1 Announce Type: new Abstract: Deep learning performance generally improves with increasing training data, yet this scaling is fundamentally constrained by annotation cost in large-s...
arXiv AI
Sep 1
MedSegBenchmarker: A Raw-Count-First Framework for Controlled 2D Medical Image Segmentation Benchmarks
arXiv:2608.29677v1 Announce Type: cross Abstract: Despite rapid advances in MIS, fair and reproducible comparisons of segmentation models remain challenging due to heterogeneous datasets, inconsisten...
arXiv Computer Vision
Aug 28
DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT
DALE-CT introduces depth‑aware 2D slice encoders that learn an anatomical world model of chest CT scans without 3D or positional supervision. By sampling self‑supervised views across a physical $z$‑axis slab, the encoder captures how anatomy changes between neighboring slices, enabling it to recover slice ordering and distinguish slices by anatomy alone. The model, trained on a large 287k‑scan corpus, achieves state‑of‑the‑art performance on CT‑RATE and is released with full code and evaluation tools.
arXiv Computer Vision
Sep 22
MTMed3D: A Multi-Task Transformer-Based Model for 3D Medical Imaging
MTMed3D is a multi-task Transformer-based model that jointly performs 3D detection, segmentation, and classification in medical imaging. It uses a shared Transformer encoder to produce multi-scale features, with separate CNN decoders for each task. Evaluated on BraTS 2018 and 2019, it achieves strong results, especially in detection, while reducing computational cost and inference time compared to single-task models.
arXiv AI
Jun 15
How do Self-Supervised Remote Sensing Vision Models Transfer to Downstream Tasks?
arXiv:2606. 13896v1 Announce Type: cross Abstract: Self-supervised geospatial foundation models (GeoFMs) learn transferable representations from remote sensing data, but their downstream behavior is difficult to characterize.
arXiv AI
Jul 1
Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Task-Oriented Review with Practical Design Guidelines
arXiv:2605. 23995v4 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) is increasingly used in medical image analysis to reduce dependence on costly expert annotations by learning transferable representations from unlabeled data.