6 papers
FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity
Ganghyeon Lee, Inha Lee, Junhee Lee +3
Although recent robot perception research emphasizes training on data from diverse environments to improve generalization, most existing methods still rely on centralized learning,…
Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
SeungBum Ha, Saerom Park, Sung Whan Yoon
Machine unlearning (MU) aims to expunge a designated forget set from a trained model without costly retraining, yet the existing techniques overlook two critical blind spots: "over…
A Flat Minima Perspective on Understanding Augmentations and Model Robustness
Weebum Yoo, Sung Whan Yoon
Model robustness indicates a model's capability to generalize well on unforeseen distributional shifts, including data corruptions and adversarial attacks. Data augmentation is one…
Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation
SeungBum Ha, Taehwan Lee, Jiyoun Lim +1
Federated learning (FL) enables decentralized training while preserving data privacy, yet existing FL benchmarks address relatively simple classification tasks, where each sample i…
Understanding Flatness in Generative Models: Its Role and Benefits
Taehwan Lee, Kyeongkook Seo, Jaejun Yoo +1
Flat minima, known to enhance generalization and robustness in supervised learning, remain largely unexplored in generative models. In this work, we systematically investigate the…
RiSi: Spectro-temporal RAN-agnostic Modulation Identification for OFDMA Signals
Daulet Kurmantayev, Dohyun Kwun, Hyoil Kim +1
RAN-agnostic communications can identify intrinsic features of the unknown signal without any prior knowledge, with which incompatible RANs in the same unlicensed band could achiev…