Zobrazeno 1 - 10
of 1 257
pro vyhledávání: '"Lee, Minjae"'
Pillar-based 3D object detection has gained traction in self-driving technology due to its speed and accuracy facilitated by the artificial densification of pillars for GPU-friendly processing. However, dense pillar processing fundamentally wastes co
Externí odkaz:
http://arxiv.org/abs/2408.13798
Autor:
Seo, Minhyuk, Koh, Hyunseo, Jeung, Wonje, Lee, Minjae, Kim, San, Lee, Hankook, Cho, Sungjun, Choi, Sungik, Kim, Hyunwoo, Choi, Jonghyun
Online continual learning suffers from an underfitted solution due to insufficient training for prompt model update (e.g., single-epoch training). To address the challenge, we propose an efficient online continual learning method using the neural col
Externí odkaz:
http://arxiv.org/abs/2404.01628
Autor:
Seo, Minhyuk, Cho, Seongwon, Lee, Minjae, Misra, Diganta, Choi, Hyeonbeom, Kim, Seon Joo, Choi, Jonghyun
Requiring extensive human supervision is often impractical for continual learning due to its cost, leading to the emergence of 'name-only continual learning' that only provides the name of new concepts (e.g., classes) without providing supervised sam
Externí odkaz:
http://arxiv.org/abs/2403.10853
Autor:
Heo, Hee-Soo, Nam, KiHyun, Lee, Bong-Jin, Kwon, Youngki, Lee, Minjae, Kim, You Jin, Chung, Joon Son
In the field of speaker verification, session or channel variability poses a significant challenge. While many contemporary methods aim to disentangle session information from speaker embeddings, we introduce a novel approach using an additional embe
Externí odkaz:
http://arxiv.org/abs/2309.14741
Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to mitigating the h
Externí odkaz:
http://arxiv.org/abs/2307.09254
Knowledge tracing plays a pivotal role in intelligent tutoring systems. This task aims to predict the probability of students answering correctly to specific questions. To do so, knowledge tracing systems should trace the knowledge state of the stude
Externí odkaz:
http://arxiv.org/abs/2306.06841
Autor:
Jung, Jee-weon, Seo, Soonshin, Heo, Hee-Soo, Kim, Geonmin, Kim, You Jin, Kwon, Young-ki, Lee, Minjae, Lee, Bong-Jin
The task of speaker change detection (SCD), which detects points where speakers change in an input, is essential for several applications. Several studies solved the SCD task using audio inputs only and have shown limited performance. Recently, multi
Externí odkaz:
http://arxiv.org/abs/2306.00680
Autor:
Lee, Minjae, Park, Seongmin, Kim, Hyungmin, Yoon, Minyong, Lee, Janghwan, Choi, Jun Won, Kim, Nam Sung, Kang, Mingu, Choi, Jungwook
3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting stringent resource and latency requirements. PointPillars, a widely adopted bird's-eye view (BEV)
Externí odkaz:
http://arxiv.org/abs/2305.07522
With the advent of Neural Radiance Field (NeRF), representing 3D scenes through multiple observations has shown remarkable improvements in performance. Since this cutting-edge technique is able to obtain high-resolution renderings by interpolating de
Externí odkaz:
http://arxiv.org/abs/2303.06335
Global place recognition and 3D relocalization are one of the most important components in the loop closing detection for 3D LiDAR Simultaneous Localization and Mapping (SLAM). In order to find the accurate global 6-DoF transform by feature matching
Externí odkaz:
http://arxiv.org/abs/2303.06308