paper-with-me

홈 › Papers

MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition

2025-02-28 · Ryosuke Kawamura, Hideaki Hayashi, Noriko Takemura, Hajime Nagahara

Dynamic facial expression recognition (DFER) is an important task in the field of computer vision. To apply automatic DFER in practice, it is necessary to accurately recognize ambiguous facial expressions, which often appear in data in the wild. In this paper, we propose MIDAS, a data augmentation method for DFER, which augments ambiguous facial expression data with soft labels consisting of probabilities for multiple emotion classes. In MIDAS, the training data are augmented by convexly combining pairs of video frames and their corresponding emotion class labels, which can also be regarded as an extension of mixup to soft-labeled video data. This simple extension is remarkably effective in DFER with ambiguous facial expression data. To evaluate MIDAS, we conducted experiments on the DFEW dataset. The results demonstrate that the model trained on the data augmented by MIDAS outperforms the existing state-of-the-art method trained on the original dataset.

📄 PDF Abstract BibTeX arXiv:2503.00202

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDynamic Facial Expression RecognitionFacial Expression Recognition

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

Similar Papers 제목 키워드 기반

Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation

2025-06-25 · Ryosuke Kawamura, Hideaki Hayashi, Shunsuke Otake, Noriko Takemura 외

Dynamic facial expression recognition (DFER) is a task that estimates emotions from facial expression video sequences. For practical applications, accurately recognizing ambiguous facial expressions -- frequently encount…

Data AugmentationDynamic Facial Expression RecognitionFacial Expression Recognition

Learning from Ambiguous Data with Hard Labels

2025-01-03 · Zeke Xie, Zheng He, Nan Lu, Lichen Bai 외

Real-world data often contains intrinsic ambiguity that the common single-hard-label annotation paradigm ignores. Standard training using ambiguous data with these hard labels may produce overly confident models and thus…

CPU

SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing

2025-09-14 · Qiuhao Liu, Ling Li, Yao Lu, Qi Xuan 외 arxiv

Deep neural networks tend to memorize noisy labels, severely degrading their generalization performance. Although Mixup has demonstrated effectiveness in improving generalization and robustness, existing Mixup-based meth…

Learning with noisy labels

Multi-Granularity Detector for Vulnerability Fixes

2023-05-23 · Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang, Ratnadira Widyasari 외

With the increasing reliance on Open Source Software, users are exposed to third-party library vulnerabilities. Software Composition Analysis (SCA) tools have been created to alert users of such vulnerabilities. SCA requ…

MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning

2025-09-30 · Seong-Hyeon Hwang, Soyoung Choi, Steven Euijong Whang arxiv

Multimodal models often over-rely on dominant modalities, failing to achieve optimal performance. While prior work focuses on modifying training objectives or optimization procedures, data-centric solutions remain undere…

Data Augmentation