arXiv:2609.17386v1 Announce Type: new Abstract: Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance....
arXiv:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.
arXiv:2607. 09450v1 Announce Type: cross Abstract: Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations.
The paper introduces SMART, a lightweight recalibration technique that adjusts logits based on the margin between the top two logits, called the logit gap. It uses a soft-binned Expected Calibration Error objective to balance bias and variance, enabling stable updates even with limited calibration data. Experiments across various datasets and architectures show SMART achieves state‑of‑the‑art calibration with fewer parameters than existing methods.
Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupted inputs also destabilize online updates. We study robust test-time adaptation (RTTA) in the adversarial-stream setting, which remains comparatively underexplored relative to standard TTA, and propose SAFER (Stochastic Augmentation Framework for Enhanced Robustness), a training-free reliability-guided augmentation wrapper for RTTA.
arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.
Optimizable Model Averaging (OMA) is a black‑box method that assigns nonnegative weights to each candidate model’s predictive probabilities, keeping all model parameters frozen. By minimizing regularized predictive entropy, OMA learns a single scalar coefficient per model to average outputs from heterogeneous architectures. The authors show that appropriate regularization reduces expected calibration error and improves the trade‑off between performance and calibration compared to simple output averaging.
The paper introduces MAGIC, a method for improving test-time robustness of large vision‑language models by mitigating language bias. MAGIC evaluates decision margins to selectively activate textual and visual perturbation branches, integrates logits from multiple perturbed views, and restores the most informative corrupted views for ambiguous samples. It also uses a calibration dataset to prune ineffective branches, reducing inference cost while enhancing performance on benchmark datasets.
arXiv:2607. 08347v1 Announce Type: cross Abstract: Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled.
The paper introduces EUA‑Cal, a calibration method that preserves the early‑training uncertainty of deep neural networks. By regularizing predictions and feature prototypes based on the early model, EUA‑Cal mitigates overconfidence while maintaining accuracy. Experiments on image classification and multiple‑choice question answering across eight models show EUA‑Cal outperforms existing calibration techniques.
The paper introduces Local Adaptive Probability Estimation (LAPE), a post‑hoc residual calibration framework that refines global calibrator outputs using non‑parametric local evidence from neighboring samples in feature space. LAPE serves as a plug‑and‑play module that leverages feature‑space geometry and reuses calibration data, improving calibration quality for various baselines. The authors also extend the approach to multi‑view inputs with Cascade Feature Augmentation Fusion (CFAF) and demonstrate its effectiveness through extensive experiments.