Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Liu, Wenze"'
We introduce a new paradigm for AutoRegressive (AR) image generation, termed Set AutoRegressive Modeling (SAR). SAR generalizes the conventional AR to the next-set setting, i.e., splitting the sequence into arbitrary sets containing multiple tokens,
Externí odkaz:
http://arxiv.org/abs/2410.10511
The labelling difficulty has been a longstanding problem in deep image matting. To escape from fine labels, this work explores using rough annotations such as trimaps coarsely indicating the foreground/background as supervision. We present that the c
Externí odkaz:
http://arxiv.org/abs/2408.10539
The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image
Externí odkaz:
http://arxiv.org/abs/2407.13500
Category-Agnostic Pose Estimation (CAPE) aims to localize keypoints on an object of any category given few exemplars in an in-context manner. Prior arts involve sophisticated designs, e.g., sundry modules for similarity calculation and a two-stage fr
Externí odkaz:
http://arxiv.org/abs/2407.13483
Autor:
Zhuo, Le, Du, Ruoyi, Xiao, Han, Li, Yangguang, Liu, Dongyang, Huang, Rongjie, Liu, Wenze, Zhao, Lirui, Wang, Fu-Yun, Ma, Zhanyu, Luo, Xu, Wang, Zehan, Zhang, Kaipeng, Zhu, Xiangyang, Liu, Si, Yue, Xiangyu, Liu, Dingning, Ouyang, Wanli, Liu, Ziwei, Qiao, Yu, Li, Hongsheng, Gao, Peng
Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabili
Externí odkaz:
http://arxiv.org/abs/2406.18583
Publikováno v:
电力工程技术, Vol 43, Iss 5, Pp 100-111 (2024)
With the development of new power systems, the protection and control tasks of distribution networks have become increasingly complex. When intelligent terminals are employed to handle these tasks, the requirements for balancing resource supply and d
Externí odkaz:
https://doaj.org/article/e5a1121d83ed435ba49c0e8b6140138e
We present DySample, an ultra-lightweight and effective dynamic upsampler. While impressive performance gains have been witnessed from recent kernel-based dynamic upsamplers such as CARAFE, FADE, and SAPA, they introduce much workload, mostly due to
Externí odkaz:
http://arxiv.org/abs/2308.15085
Conditional spatial queries are recently introduced into DEtection TRansformer (DETR) to accelerate convergence. In DAB-DETR, such queries are modulated by the so-called conditional linear projection at each decoder stage, aiming to search for positi
Externí odkaz:
http://arxiv.org/abs/2307.08353
We introduce the notion of point affiliation into feature upsampling. By abstracting a feature map into non-overlapped semantic clusters formed by points of identical semantic meaning, feature upsampling can be viewed as point affiliation -- designat
Externí odkaz:
http://arxiv.org/abs/2307.08198
We introduce point affiliation into feature upsampling, a notion that describes the affiliation of each upsampled point to a semantic cluster formed by local decoder feature points with semantic similarity. By rethinking point affiliation, we present
Externí odkaz:
http://arxiv.org/abs/2209.12866