deadlock
发表于 2025-3-28 16:23:07
http://reply.papertrans.cn/24/2343/234261/234261_41.png
Cleave
发表于 2025-3-28 19:03:25
http://reply.papertrans.cn/24/2343/234261/234261_42.png
胶水
发表于 2025-3-28 22:57:44
,SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud, registration, in conditions without initial transformation hints. Experiments have demonstrated that our line-based registration method is highly competitive to state-of-the-art point-based approaches. Our code is available at ..
podiatrist
发表于 2025-3-29 03:56:24
http://reply.papertrans.cn/24/2343/234261/234261_44.png
cancellous-bone
发表于 2025-3-29 10:50:14
,HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors,e assistant is an additional detection head with the architecture homogeneous to the teacher head attached to the student backbone. Thus, a hetero-KD is transformed into a homo-KD, allowing efficient knowledge transfer from the teacher to the student. Moreover, we extend HEAD into a Teacher-Free HEA
愤愤不平
发表于 2025-3-29 13:50:27
,Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection,
财主
发表于 2025-3-29 18:58:18
Introductory Concepts and Problems,ore specifically, we apply two rigid transformations to each object observation in parallel, and feed them into DPDN respectively to yield dual sets of predictions; on top of the parallel learning, an inter-consistency term is employed to keep cross consistency between dual predictions for improving
cataract
发表于 2025-3-29 20:34:51
The Economics of Self-Destructive Choicesbetween proposals and ground-truth (GT). Benefiting from these strategies, P2BNet is able to produce high-quality instance-level bags for object detection. P2BNet improves the mean average precision (AP) by more than 50% relative to the previous best PSOD method on the MS COCO dataset. It also demon
摇摆
发表于 2025-3-30 03:40:15
http://reply.papertrans.cn/24/2343/234261/234261_49.png
formula
发表于 2025-3-30 06:41:04
http://reply.papertrans.cn/24/2343/234261/234261_50.png