← Back to all news
arXiv Machine Learning By Jinyi Niu, Ziyi Song, Weining Shen

Sex Estimation from Footwear Outsole Impressions Using CNN Transfer Learning and Interpretable Image Statistics

Read the original on arXiv Machine Learning →

The study evaluates binary sex estimation from footwear outsole impressions using convolutional neural network (CNN) transfer learning compared to traditional feature-based classification. Fine‑tuned CNNs outperform classifiers that rely solely on handcrafted, geometric, and metadata descriptors, while frozen‑feature approaches provide a less computationally intensive alternative. Exploratory analysis links low‑dimensional CNN representations to measurable image properties such as frequency threshold ratio, contrast, and wavelet summaries, indicating that CNNs capture additional discriminative information.

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.

Related stories

arXiv AI
Sep 3

Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics

The paper presents lightweight architectures for detecting GAN-generated synthetic faces, comparing a compact Swin Transformer, pre‑trained Swin‑Tiny and Swin‑Small models, and a hybrid EfficientNet‑B0 + Swin Transformer. Using the 140K Real and Fake Faces dataset, the hybrid model achieved 99% accuracy and 99.44% recall on 5,000 test images, outperforming both pure Swin variants and a CNN‑only baseline. The study demonstrates that combining hierarchical CNN features with shifted‑window self‑attention yields an efficient, computationally lightweight detection method.

By Sejuti Basu, Ashima Sood, Vijay Kumar, Sahil Sharma
llmsdiffusioncomputer-vision
More like this →