Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration

TL;DR

This paper introduces DCLR, a novel method for multi-label confidence calibration that models semantic correlations to improve the reliability of confidence scores in complex visual recognition tasks.

Contribution

It proposes the DCLR algorithm that leverages dynamic semantic correlations for adaptive regularization in multi-label confidence calibration, addressing limitations of existing single-label methods.

Findings

DCLR outperforms existing calibration methods on multi-label benchmarks.

The approach effectively models semantic correlations to improve confidence reliability.

Extensive experiments validate the superiority of DCLR in multi-label recognition models.

Abstract

Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confidence scores that necessitate calibration. While current confidence calibration techniques primarily address single-label scenarios, there is a lack of focus on more practical and generalizable multi-label contexts. This paper introduces the Multi-Label Confidence Calibration (MLCC) task, aiming to provide well-calibrated confidence scores in multi-label scenarios. Unlike single-label images, multi-label images contain multiple objects, leading to semantic confusion and further unreliability in confidence scores. Existing single-label calibration methods, based on label smoothing, fail to account for category correlations, which are crucial for addressing semantic confusion, thereby yielding sub-optimal performance. To overcome these limitations, we propose the Dynamic Correlation Learning and Regularization (DCLR) algorithm, which leverages multi-grained semantic correlations to better model semantic confusion for adaptive regularization. DCLR learns dynamic instance-level and prototype-level similarities specific to each category, using these to measure semantic correlations across different categories. With this understanding, we construct adaptive label vectors that assign higher values to categories with strong correlations, thereby facilitating more effective regularization. We establish an evaluation benchmark, re-implementing several advanced confidence calibration algorithms and applying them to leading multi-label recognition (MLR) models for fair comparison. Through extensive experiments, we demonstrate the superior performance of DCLR over existing methods in providing reliable confidence scores in multi-label scenarios.