전체 글 썸네일형 리스트형 양자컴퓨터 원리 기록용 https://www.youtube.com/shorts/_RaXna92WQE FACT CHECK · QUANTUM COMPUTING 양자컴퓨터는"동시에 다 계산해서" 빠른 게 아니다 중첩은 시작일 뿐입니다. 진짜 핵심은 오답을 지우고 정답만 키우는 간섭이고, 그걸 가장 깔끔하게 보여주는 게 그로버 알고리즘입니다. 유튜브 쇼츠 하나가 알고리즘에 떴습니다. 호수 위에 배를 띄워놓고 보물선을 찾는 비유로 양자 알고리즘을 설명하는 영상인데, 결론부터 말하면 설명이 정확합니다. 대중매체가 흔히 저지르는 오해를 정확히 짚고, 그로버 알고리즘의 작동 원리를 비유로 .. 더보기 Real-Time Object Detection Meets DINOv3 https://intellindust-ai-lab.github.io/projects/DEIMv2/ DEIMv2Real-Time Object Detection Meets DINOv3intellindust-ai-lab.github.io Real-Time Object Detection Meets DINOv3Shihua Huang¹⋆, Yongjie Hou¹²⋆, Longfei Liu¹⋆, Xuanlong Yu¹, Xi Shen¹†¹ Intellindust AI Lab; ² 샤먼대학교(Xiamen University)⋆ 공동 1저자(Equal Contribution);† 교신 저자(Corresponding Author)프로젝트 페이지: https://intellindust-ai-lab.github.io/proj.. 더보기 Object Detection Model Leaderboard https://leaderboard.roboflow.com/ Computer Vision Model Leaderboard | Object Detection BenchmarksCompare object detection models like YOLO, RT-DETR, and D-FINE on COCO 2017 dataset. Filter by architecture, parameters, license, and performance metrics like mAP and F1 score.leaderboard.roboflow.com 더보기 Mamba YOLO: A Simple Baseline for Object Detection with State Space Model https://arxiv.org/abs/2406.05835 Mamba YOLO: A Simple Baseline for Object Detection with State Space ModelDriven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly extending the marxiv.org Mamba YOLO: 상태 공간 모델(State.. 더보기 YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection https://arxiv.org/abs/2512.23273 YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time DetectionExisting Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to all inputs, misallarxiv.org YOLO-Mas.. 더보기 LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection https://arxiv.org/abs/2406.03459 LW-DETR: A Transformer Replacement to YOLO for Real-Time DetectionIn this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advarxiv.org LW-DETR: 실시간 객체 검출을 위한 YOLO 대체 Tr.. 더보기 RF-DETR: Neural Architecture Search for Real-Time Detection Transformers https://arxiv.org/abs/2511.09554 RF-DETR: Neural Architecture Search for Real-Time Detection TransformersOpen-vocabulary detectors achieve impressive performance on COCO, but often fail to generalize to real-world datasets with out-of-distribution classes not typically found in their pre-training. Rather than simply fine-tuning a heavy-weight vision-languagearxiv.org RF-DETR: 실시간 탐지 트랜스포머를 위한 신경.. 더보기 D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement https://arxiv.org/abs/2410.13842 D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution RefinementWe introduce D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Glarxiv.org D-FINE: DETR에서 회귀(.. 더보기 이전 1 2 3 4 ··· 75 다음