arXiv AI
Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 5
Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition
arXiv:2404. 10370v4 Announce Type: replace-cross Abstract: Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference.
arXiv AI
Sep 4
ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition
ScoreMix is a self‑contained synthetic data generation method that improves recognition tasks by mixing class‑conditioned scores along reverse diffusion trajectories, thereby creating hard synthetic samples without external resources. The approach shows that selecting classes far apart in the discriminator’s embedding space yields larger performance gains, up to 3% more improvement than proximity‑based selection. Across eight public face recognition benchmarks, ScoreMix boosts accuracy by up to 7 percentage points, demonstrating robustness and practicality without hyperparameter tuning.
arXiv Machine Learning
Jul 1
T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World
arXiv:2603. 18481v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection remains a critical challenge in open-world learning, where models must adapt to evolving data distributions.
arXiv Machine Learning
Jul 1
Automated Background Swapping for Robustness against Spurious Backgrounds
arXiv:2606. 32018v1 Announce Type: cross Abstract: Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations, i.
arXiv AI
Jun 24
Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios
arXiv:2606. 23758v1 Announce Type: cross Abstract: Domain generalization learns from multiple source domains to generalize to unseen target domains.
Hugging Face Trending Papers
Jul 20
PRiSM: Prototype Regularization for Few-Shot VLMs
Training-free few-shot adaptation methods have gained significant attention recently in the context of Vision-language Models (VLMs). Yet, current benchmarks rely on strong assumptions about the statistics of the adaptation data, e.