arXiv AI
A Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures
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 25
Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks?
The paper introduces SphereTrust, a method that uses frozen self‑supervised hyperspherical features to evaluate and rank candidate masks produced by foundation segmenters like SAM. By measuring angular contrast, foreground coverage, and image‑frame contact, SphereTrust can select high‑quality masks in 0.55 s per image and outperforms existing baselines on multiple segmentation tasks. The selected masks are then used as priors to train student models, improving performance on several benchmark datasets.
arXiv Machine Learning
Jul 14
Vertical Fusion: Condensing Internal Representations for Robust ViT Classification
arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.
arXiv AI
2d 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.
arXiv AI
Sep 30
Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...
arXiv Machine Learning
Aug 11
ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.
arXiv Machine Learning
Oct 2
When a Flatness Proxy Is Not a Function: Robustness Certificates and Training Interventions
arXiv:2609.38540v1 Announce Type: new Abstract: A valid curvature upper bound need not justify either a robustness certificate or an intervention on an intrinsic predictor property. We demonstrate th...