https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/226 2026-07-04T09:39:15Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/212736 Title: MORCU: Margin-based ordinal classification with dynamic regularization for calibration and unimodality Authors: Kim, Daehwan; Chung, Haejun; Jang, Ikbeom Abstract: Confidence calibration is crucial for accurate and reliable ordinal classification, yet it remains largely overlooked, with existing calibration studies rarely addressing the unique challenges posed by ordered class labels. We introduce Margin-based Ordinal Classification with Dynamic Regularization for Calibration and Unimodality (MORCU). It combines dynamic log-barrier regularization to enforce structured probability distributions with our Target-Preserving Margin Penalty (TPMP), a newly introduced approach that refines adjacent non-target logits to promote calibration and unimodality. By adaptively balancing structural constraints and confidence estimation, MORCU mitigates both overconfidence and underconfidence, producing well-calibrated probability distributions aligned with ordinal relationships. Experimental results across diverse benchmark datasets demonstrate consistent calibration gains and competitive ordinal classification performance, making it well-suited for applications requiring both predictive accuracy and trustworthy confidence estimation. The code is publicly available at https://github.com/labhai/MORCU. 2026-11-01T00:00:00Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211397 Title: Bumper-guided representation interpolation for black-box unsupervised domain adaptation Authors: Choi, Jin-Seong; Lee, Jae-Hong; Chang, Joon-Hyuk Abstract: Black-box unsupervised domain adaptation (BUDA) presents a challenging scenario in which only unlabeled target data are available, and access to the source model's parameters is limited. Recent BUDA methods that rely on consistency training struggle with error accumulation caused by fixed source representations. In this paper, we propose a novel framework called bumper-guided representation interpolation (BGRI), which introduces a bumper model that interpolates between the source and target domain representation spaces. Using interpolated representations, the bumper model delivers generalized source information and enables stable and effective knowledge transfer to the target model. Through extensive experiments conducted in real-world scenarios across diverse acoustic and linguistic domains, BGRI consistently outperforms the existing BUDA approaches in terms of adaptation performance and robustness. 2026-10-01T00:00:00Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211349 Title: A dual-branch parallel network for speech enhancement and restoration Authors: Yang, Da-Hee; Kim, Dail; Chang, Joon-Hyuk; Choi, Jeonghwan; Moon, Han-Gil Abstract: We present a novel general speech restoration model, DBP-Net (dual-branch parallel network), designed to effectively handle complex real-world distortions including noise, reverberation, and bandwidth degradation. Unlike prior approaches that rely on a single processing path or separate models for enhancement and restoration, DBP-Net introduces a unified architecture with dual parallel branches-a masking-based branch for distortion suppression and a mapping-based branch for spectrum reconstruction. A key innovation behind DBP-Net lies in the parameter sharing between the two branches and a cross-branch skip fusion, where the output of the masking branch is explicitly fused into the mapping branch. This design enables DBP-Net to simultaneously leverage complementary learning strategies-suppression and generation-within a lightweight framework. Experimental results show that DBP-Net significantly outperforms existing baselines in comprehensive speech restoration tasks while maintaining a compact model size. These findings suggest that DBP-Net offers an effective and scalable solution for unified speech enhancement and restoration in diverse distortion scenarios. 2026-10-01T00:00:00Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211836 Title: Hierarchical mutual distillation for multi-view fusion: Learning from all possible view combinations Authors: Yang, Jiwoong; Chung, Haejun; Jang, Ikbeom Abstract: Multi-view learning often struggles to effectively leverage images captured from diverse angles and locations. Learning methods for unstructured multi-view images remain largely underexplored. We propose a novel Hierarchical Mutual Distillation for Multi-View Fusion (HMDMV) method, which can handle both structured and unstructured multi-view scenarios. It makes predictions utilizing all possible view combinations: single view, partial multi-view, and full multi-view. The method generates predictions for each view combination and then applies hierarchical mutual distillation to enhance inter-view consistency. An uncertainty-based weighting mechanism further refines the fusion process by adjusting the influence of each view combination according to its prediction confidence, reducing the impact of low-confidence views. Extensive experiments on large-scale structured and unstructured datasets demonstrate that HMDMV consistently achieves state-of-the-art classification accuracy. Another unique advantage of HMDMV is that it provides improved flexibility in inference, allowing for more or fewer view counts in inference than those used in training without additional processing. We also provide a light version with reduced training cost by designing an efficient strategy that randomly samples subsets of view combinations during each training iteration. These results highlight HMDMV's robustness in real-world settings where view availability is variable or incomplete. The code is available at https://github.com/labhai/HMDMV. 2026-10-01T00:00:00Z