paper-with-me

Papers

ACLS: Adaptive and Conditional Label Smoothing for Network Calibration

2023-08-23 · ICCV 2023 1 · Hyekang Park, Jongyoun Noh, Youngmin Oh, Donghyeon Baek, Bumsub Ham

We address the problem of network calibration adjusting miscalibrated confidences of deep neural networks. Many approaches to network calibration adopt a regularization-based method that exploits a regularization term to smooth the miscalibrated confidences. Although these approaches have shown the effectiveness on calibrating the networks, there is still a lack of understanding on the underlying principles of regularization in terms of network calibration. We present in this paper an in-depth analysis of existing regularization-based methods, providing a better understanding on how they affect to network calibration. Specifically, we have observed that 1) the regularization-based methods can be interpreted as variants of label smoothing, and 2) they do not always behave desirably. Based on the analysis, we introduce a novel loss function, dubbed ACLS, that unifies the merits of existing regularization methods, while avoiding the limitations. We show extensive experimental results for image classification and semantic segmentation on standard benchmarks, including CIFAR10, Tiny-ImageNet, ImageNet, and PASCAL VOC, demonstrating the effectiveness of our loss function.

📄 PDF Abstract BibTeX arXiv:2308.11911

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationSemantic Segmentation

Similar Papers 제목 키워드 기반

Learning Better Structured Representations Using Low-rank Adaptive Label Smoothing

2021-01-01 · ICLR 2021 1 · Asish Ghoshal, Xilun Chen, Sonal Gupta, Luke Zettlemoyer 외

Training with soft targets instead of hard targets has been shown to improve performance and calibration of deep neural networks. Label smoothing is popular way of computing soft targets, where one-hot encoding of a clas…

Generalization BoundsMachine TranslationSemantic ParsingStructured Prediction+2

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

2026-06-26 · Thiru Thillai Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge arxiv

Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods. This manifests itself as either overconfident incorrect predic…

Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation

2022-10-22 · Dongkyu Lee, Ka Chun Cheung, Nevin L. Zhang

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked d…

Knowledge DistillationText Generation

Adaptive Label Smoothing with Self-Knowledge

2021-09-29 · Dongkyu Lee, Ka Chun Cheung, Nevin Zhang

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked d…

Knowledge DistillationMachine Translation

CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning

2025-07-30 · Jinsoo Bae, Seoung Bum Kim, Hyungrok Do arxiv

Semi-supervised learning (SSL) uses unlabeled data to improve the performance of machine learning models when labeled data is scarce. However, its real-world applications often face the label distribution mismatch proble…