arXiv Machine Learning October 16, 2026 By Arjun Dadhwal, Brian Summa

Topology-Inspired Fine-Tuning for Wind-Field Super-Resolution

Read the original on arXiv Machine Learning →

The paper introduces topology‑inspired fine‑tuning for wind‑field super‑resolution, adding auxiliary losses based on persistence diagrams and merge‑tree distances to a pretrained CNN. A comprehensive study of 16 fine‑tuning setups shows that gradient supervision improves bottleneck persistence‑diagram metrics, while fixed‑pair supervision yields the most consistent gains in both persistence‑diagram and merge‑tree distances. The combined objective reduces key topological distances by up to 31% and improves PSNR by 1.30 dB compared to the original CNN.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 7

Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures

arXiv:2404. 06294v2 Announce Type: replace-cross Abstract: Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to the standard of its High-Resolution (HR) counterpart.

By Arkaprabha Basu, Kushal Bose, Sankha Subhra Mullick, Anish Chakrabarty, Swagatam Das

diffusion benchmarks safety

arXiv Machine Learning

3d ago

ExGrad: Beyond Suppression - Explicit Clean-Gradient Subtraction in Adversarial Training

arXiv:2610.30018v1 Announce Type: new Abstract: Adversarial training derives updates from surrogate losses, but source-loss descent does not directly characterize an update's effect on adversarial ma...

By Zhiyuan Ye, Xiangyu Zhou, Ji Qi, Hao Zhang, Yi Zhou

safety

arXiv AI

Oct 5

The Effective Depth Paradox: Topology and Trainability in Deep CNNs

arXiv:2602. 13298v4 Announce Type: replace-cross Abstract: This paper presents a controlled comparative study of convolutional neural network (CNN) topology and image classification performance across the architectural families VGG, ResNet, and GoogLeNet, evaluated on CIFAR-10 under a unified training protocol.

By Manfred M. Fischer, Joshua Pitts

llms computer-vision

arXiv AI

Jul 3

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

arXiv:2607. 01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation.

By Tasnim Shahriar

arXiv Machine Learning

Jul 10

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

arXiv:2603. 12478v2 Announce Type: replace-cross Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven.

By Rujie Wu, Haozhe Zhao, Hai Ci, Yizhou Wang

fine-tuning multimodal benchmarks

arXiv AI

Jul 1

A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization

arXiv:2505. 03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.

By Tasnim Shahriar

fine-tuning benchmarks

One email a morning, machine-written

Related stories

Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures

ExGrad: Beyond Suppression - Explicit Clean-Gradient Subtraction in Adversarial Training

The Effective Depth Paradox: Topology and Trainability in Deep CNNs

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization