Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models

• URL: http://arxiv.org/abs/2410.02681v1
• Date: Thu, 3 Oct 2024 17:06:21 GMT
• Title: Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
• Authors: Shuoyuan Wang, Yixuan Li, Hongxin Wei,
• Abstract summary: Confidence calibration is critical for the safe deployment of machine learning models in the real world. Existing prompt tuning methods usually lead to a trade-off of calibration between base and new classes. We introduce Dynamic Outlier Regularization to ensure the confidence calibration on both base and new classes after fine-tuning.
• Score: 22.501089777956654
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Confidence calibration is critical for the safe deployment of machine learning models in the real world. However, such issue in vision-language models like CLIP, particularly after fine-tuning, has not been fully addressed. In this work, we demonstrate that existing prompt tuning methods usually lead to a trade-off of calibration between base and new classes: the cross-entropy loss in CoOp causes overconfidence in new classes by increasing textual label divergence, whereas the regularization of KgCoOp maintains the confidence level but results in underconfidence in base classes due to the improved accuracy. Inspired by the observations, we introduce Dynamic Outlier Regularization (DOR) to ensure the confidence calibration on both base and new classes after fine-tuning. In particular, we propose to minimize the feature deviation of novel textual labels (instead of base classes) sampled from a large vocabulary. In effect, DOR prevents the increase in textual divergence for new labels while easing restrictions on base classes. Extensive experiments demonstrate that DOR can enhance the calibration performance of current fine-tuning methods on base and new classes.

Related papers

• Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning [19.87230756515995]
  Class-incremental learning is critical for numerous real-world applications, such as smart home devices. Fine-tuning the model on novel classes often leads to the phenomenon of catastrophic forgetting. We propose a simple yet effective mechanism to address this challenge by controlling the trade-off between novel and base class accuracy.
  arXiv  Detail & Related papers  (2025-01-27T12:31:50Z)
• Improved Feature Generating Framework for Transductive Zero-shot Learning [31.656888766677664]
  Feature Generative Adversarial Networks have emerged as powerful generative models in producing high-quality representations of unseen classes. This paper delves into the pivotal influence of unseen class priors within the framework of Zero-shot Learning (TZSL) We introduce our Improved Feature Generation Framework, termed I-VAEGAN, which incorporates two novel components: Pseudo-conditional Feature Adversarial (PFA) learning and Variational Embedding Regression (VER)
  arXiv  Detail & Related papers  (2024-12-24T08:42:16Z)
• Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration [60.95748658638956]
  This paper introduces the Multi-Label Confidence task, aiming to provide well-calibrated confidence scores in multi-label scenarios. Existing single-label calibration methods fail to account for category correlations, which are crucial for addressing semantic confusion. We propose the Dynamic Correlation Learning and Regularization algorithm, which leverages multi-grained semantic correlations to better model semantic confusion.
  arXiv  Detail & Related papers  (2024-07-09T13:26:21Z)
• Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation [56.1776710527814]
  Weakly Incremental Learning for Semantic (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-level labels. A prevailing way to solve WILSS is the generation of seed areas for each new class, serving as a form of pixel-level supervision. We propose an innovative, tendency-driven relationship of mutual exclusivity, meticulously tailored to govern the behavior of the seed areas.
  arXiv  Detail & Related papers  (2024-04-18T08:23:24Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• A Study on the Calibration of In-context Learning [27.533223818505682]
  We study in-context learning (ICL), a prevalent method for adapting static language models through tailored prompts. We observe that, with an increasing number of ICL examples, models initially exhibit increased miscalibration before achieving better calibration. We explore recalibration techniques and find that a scaling-binning calibrator can reduce calibration errors consistently.
  arXiv  Detail & Related papers  (2023-12-07T03:37:39Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• Calibration-Aware Bayesian Learning [37.82259435084825]
  This paper proposes an integrated framework, referred to as calibration-aware Bayesian neural networks (CA-BNNs) It applies both data-dependent or data-independent regularizers while optimizing over a variational distribution as in Bayesian learning. Numerical results validate the advantages of the proposed approach in terms of expected calibration error (ECE) and reliability diagrams.
  arXiv  Detail & Related papers  (2023-05-12T14:19:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.