DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 노용만 | - |
dc.contributor.author | Shin, Sebin | - |
dc.contributor.author | 신세빈 | - |
dc.date.accessioned | 2024-07-30T19:31:23Z | - |
dc.date.available | 2024-07-30T19:31:23Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096790&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321572 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2024.2,[viii, 82 p. :] | - |
dc.description.abstract | Multispectral pedestrian detection using RGB and thermal sensors (RGBT) has emerged as a promising solution for safety-critical vision applications that require non-stop operations all day/night. However, there are unsolved issues in multispectral pedestrian detection, including the modality bias problem. The imbalanced modality distribution in RGBT datasets provoke modality bias, where models tend to rely on one modality (thermal) over the other (RGB). Therefore, it is necessary to address the modality bias problem in order to learn multimodal relationships robustly in real-world environments. We deal with modality bias problems for multimodal representation through counterfactual approaches that can compensate for modality imbalance in datasets. First, we propose a novel model framework: Causal Mode Multiplexer (CMM) based on counterfactual intervention and guide the model to learn the causality between multimodal inputs and outputs. Different from the symmetrical fusion topology of existing methods, the proposed approach leverages two distinct causal graphs that are tailored to the multimodal data type. Second, we introduce a novel data augmentation framework: Prototypical Cross-modal Balancing (PCB) based on counterfactual image generation. Unlike existing augmentation methods, PCB generates multimodal data considering the modality balance of multimodal data. Each of the proposed methods from the model and data perspective are validated under extensive experiments including comparisons to the state-of-the-art methods, ablation studies, and further qualitative/quantitative results. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 멀티모달▼a모달리티 편향 문제▼a반사실적 개입▼a프로토타입 균형▼a다중 스펙트럼 보행자 검출▼a인과관계 | - |
dc.subject | Multimodal▼aModality bias problems▼aCounterfactual intervention▼aPrototypical balancing▼aMultispectral pedestrian detection▼aCausality | - |
dc.title | Mitigating the modality bias in multispectral pedestrian detection using counterfactual strategies | - |
dc.title.alternative | 반사실적 기법들을 이용한 다중 스펙트럼 보행자 검출의 모달리티 편향 완화 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Ro, Yong Man | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.