arXiv AI
Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 16
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
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 AI
Jun 8
SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
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 Machine Learning
Jul 13
Robustifying Vision-Language Models via Test-Time Prompt Adaptation
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.
arXiv Machine Learning
Aug 27
Sample Margin-Aware Recalibration of Temperature Scaling
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.
Hugging Face Trending Papers
Jun 21
Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation
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 Machine Learning
Aug 12
Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration
arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.