← Back to all news
arXiv Machine Learning By Yunus Serhat B{\i}\c{c}ak\c{c}{\i}

Vision Transformer Ensembles for Panoramic Street Segmentation

Read the original on arXiv Machine Learning →

The paper presents a two‑stage approach to street‑panorama semantic segmentation using Vision Transformer ensembles. In the first stage, nine pretrained models are compared under equal compute budgets, and the best two are trained with three random seeds, achieving 60.95% mIoU on validation and 57.08% on the hidden test leaderboard. The second stage explores augmentations, larger inputs, and additional architectures, culminating in an ensemble of four models that scores 64.53% mIoU on validation and 61.54% mIoU (71.93% F1) on the hidden test leaderboard, while the study documents all runs, costs, and releases the code and models.

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
3d ago

PairCLIP-SWA: Similarity-Guided Balancing and Stochastic Weight Averaging for Generalized Deepfake Image Detection with OpenCLIP

PairCLIP‑SWA is a single‑backbone deepfake detector that fine‑tunes an OpenCLIP ViT‑L/14 visual tower using a class‑balanced corpus created by CLIP‑similarity‑guided subsampling and then applies stochastic weight averaging over the fine‑tuning trajectory. Trained on the IEEE SP Cup 2025 (DF‑Wild‑Cup) benchmark, the weight‑averaged model achieves 97.04 % accuracy, 98.64 % AU‑ROC and a 4.07 % equal error rate—outperforming the best published three‑backbone ensemble. The study shows that averaging stabilizes validation performance, prevents misranking on disjoint test sets, and that CLIP pre‑training, rather than ensembling, is the key driver of accuracy.

By Md. Nakib, Sudipto Sarkar, A. J. A. Jubayer Talukder, Mohammad Ariful Haque
fine-tuningbenchmarks
More like this →
arXiv Machine Learning
Oct 12

Shortcut Learning in Geospatial Foundation Model Embeddings for Cross-Disaster Damage Assessment

The study investigates shortcut learning in geospatial foundation model embeddings for cross-disaster damage assessment. By holding out entire disasters during evaluation, the authors demonstrate a significant drop in mean balanced accuracy across multiple datasets, revealing that models rely on event or scene characteristics rather than transferable evidence. They further show that simple feature-level transformations, such as supervised contrastive learning or PCA, can improve generalization to unseen disasters.

By Ali Shibli, Andrea Nascetti, Yifang Ban
rag
More like this →