Author name cluster

Sumyeong Ahn

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

TMLR Journal 2025 Journal Article

FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning

Seongyoon Kim
Minchan Jeong
Sungnyun Kim
Sungwoo Cho
Sumyeong Ahn
Se-Young Yun

Federated Learning (FL) has emerged as a pivotal framework for the development of effective global models (global FL) or personalized models (personalized FL) across clients with heterogeneous, non-iid data distribution. A key challenge in FL is client drift, where data heterogeneity impedes the aggregation of scattered knowledge. Recent studies have tackled the client drift issue by identifying significant divergence in the last linear (classifier) layer. To mitigate this divergence, strategies such as freezing the classifier weights and aligning the feature extractor accordingly have proven effective. Although the local alignment between classifier and feature extractor has been studied as a crucial factor in FL, we observe that it may lead the model to overemphasize the observed classes and underestimate the unobserved classes within each client. Therefore, our goals are twofold: (1) improving local alignment and (2) maintaining the representation of unseen class samples, ensuring that the solution seamlessly incorporates knowledge from individual clients, thus enhancing performance in both global and personalized FL. To achieve this, we introduce a novel algorithm named FedDr+, which empowers local model alignment using dot-regression loss. FedDr+ freezes the classifier as a simplex ETF to align the features and improves aggregated global models by employing a feature distillation mechanism to retain information about unseen/missing classes. Our empirical results demonstrate that FedDr+ not only outperforms methods with a frozen classifier but also surpasses other state-of-the-art approaches, ensuring robust performance across diverse data distributions.

PDF Details

TMLR Journal 2025 Journal Article

VSCoDe: Visual-Augmentation Selection for Contrastive Decoding

Sihyeon Kim
Boryeong Cho
Sangmin Bae
Sumyeong Ahn
Se-Young Yun

Despite the impressive performance of recent Large Vision-Language Models (LVLMs), these models often produce inaccurate responses. To address this issue, previous studies have aimed to reduce hallucinations by using contrastive decoding (CD) with modified images, such as cropping objects related to query or adding noise, thereby contrasting with the original image. However, these methods have several limitations. First, employing fixed visual augmentation, such as adding noise, is a simple approach but too rigid to contrast on various queries. Conversely, using semantics in queries or images by leveraging external models can adaptively generate contrastive images, but it entails significant additional costs. To address these shortcomings, we explore using pre-defined visual augmentations to enable flexible adaptation to each query without relying on external models. We observe that each query achieves different contrasts through different visual augmentations. Based on this, we propose a novel method called VSCoDe, Visual-Augmentation Selection for Contrastive Decoding, which adaptively selects augmentations using a proposed distance metric to identify those with higher contrast. Our empirical evaluations demonstrate that VSCoDe outperforms previous methods and enhances the quality of various vision-language tasks without additional training or reliance on external models.

PDF Details

IJCAI Conference 2024 Conference Paper

Fine-tuning Pre-trained Models for Robustness under Noisy Labels

Sumyeong Ahn
Sihyeon Kim
Jongwoo Ko
Se-Young Yun

The presence of noisy labels in a training dataset can significantly impact the performance of machine learning models. In response to this issue, researchers have focused on identifying clean samples and reducing the influence of noisy labels. Recent works in this field have achieved notable success in terms of generalizability, albeit at the expense of extensive computing resources. Therefore, reducing computational costs remains a crucial challenge. Concurrently, in other research areas, there has been a focus on developing fine-tuning techniques to efficiently achieve high generalization performance. Despite their proven efficiently achievable generalization capabilities, these techniques have seen limited exploration from a label noise point of view. In this research, we aim to find an effective approach to fine-tune pre-trained models for noisy labeled datasets. To achieve this goal, we empirically investigate the characteristics of pre-trained models on noisy labels and propose an algorithm, named TURN. We present the results of extensive testing and demonstrate both efficient and improved denoising performance on various benchmarks, surpassing previous methods.

PDF Details DOI

ICLR Conference 2023 Conference Paper

CUDA: Curriculum of Data Augmentation for Long-tailed Recognition

Sumyeong Ahn
Jongwoo Ko
Se-Young Yun

Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets. To mitigate this problem, many approaches have aimed to balance among given classes by re-weighting or re-sampling training samples. These re-balancing methods increase the impact of minority classes and reduce the influence of majority classes on the output of models. However, the extracted representations may be of poor quality owing to the limited number of minority samples. To handle this restriction, several methods have been developed that increase the representations of minority samples by leveraging the features of the majority samples. Despite extensive recent studies, no deep analysis has been conducted on determination of classes to be augmented and strength of augmentation has been conducted. In this study, we first investigate the correlation between the degree of augmentation and class-wise performance, and find that the proper degree of augmentation must be allocated for each class to mitigate class imbalance problems. Motivated by this finding, we propose a simple and efficient novel curriculum, which is designed to find the appropriate per-class strength of data augmentation, called CUDA: CUrriculum of Data Augmentation for long-tailed recognition. CUDA can simply be integrated into existing long-tailed recognition methods. We present the results of experiments showing that CUDA effectively achieves better generalization performance compared to the state-of-the-art method on various imbalanced datasets such as CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018.

Details

AAAI Conference 2023 Conference Paper

Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels

Sumyeong Ahn
Se-Young Yun

Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved generalization performance by underestimating easy-to-learn samples (i.e., bias-aligned samples) and highlighting difficult-to-learn samples (i.e., bias-conflicting samples). However, these techniques may fail owing to noisy labels, because the trained model recognizes noisy labels as difficult-to-learn and thus highlights them. In this study, we find that earlier approaches that used the provided labels to quantify difficulty could be affected by the small proportion of noisy labels. Furthermore, we find that running denoising algorithms before debiasing is ineffective because denoising algorithms reduce the impact of difficult-to-learn samples, including valuable bias-conflicting samples. Therefore, we propose an approach called denoising after entropy-based debiasing, i.e., DENEB, which has three main stages. (1) The prejudice model is trained by emphasizing (bias-aligned, clean) samples, which are selected using a Gaussian Mixture Model. (2) Using the per-sample entropy from the output of the prejudice model, the sampling probability of each sample that is proportional to the entropy is computed. (3) The final model is trained using existing denoising algorithms with the mini-batches constructed by following the computed sampling probability. Compared to existing debiasing and denoising algorithms, our method achieves better debiasing performance on multiple benchmarks.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Mitigating Dataset Bias by Using Per-Sample Gradient

Sumyeong Ahn
Seongyoon Kim
Se-Young Yun

The performance of deep neural networks is strongly influenced by the training dataset setup. In particular, when attributes with a strong correlation with the target attribute are present, the trained model can provide unintended prejudgments and show significant inference errors (i.e., the dataset bias problem). Various methods have been proposed to mitigate dataset bias, and their emphasis is on weakly correlated samples, called bias-conflicting samples. These methods are based on explicit bias labels provided by humans. However, such methods require human costs. Recently, several studies have sought to reduce human intervention by utilizing the output space values of neural networks, such as feature space, logits, loss, or accuracy. However, these output space values may be insufficient for the model to understand the bias attributes well. In this study, we propose a debiasing algorithm leveraging gradient called Per-sample Gradient-based Debiasing (PGD). PGD is comprised of three steps: (1) training a model on uniform batch sampling, (2) setting the importance of each sample in proportion to the norm of the sample gradient, and (3) training the model using importance-batch sampling, whose probability is obtained in step (2). Compared with existing baselines for various datasets, the proposed method showed state-of-the-art accuracy for the classification task. Furthermore, we describe theoretical understandings of how PGD can mitigate dataset bias.

Details