Zobrazeno 1 - 10
of 2 626
pro vyhledávání: '"Han Kai"'
Publikováno v:
Materials & Design, Vol 230, Iss , Pp 111979- (2023)
Gradient nanostructured materials are regarded as a promising class of architectures with tunable mechanical properties, primarily dependent on the optimization of well-controlled fabrication parameters. In this paper, a microvariable-based constitut
Externí odkaz:
https://doaj.org/article/bdb6b2021d374952b8a214789166a00b
Detecting test-time distribution shift has emerged as a key capability for safely deployed machine learning models, with the question being tackled under various guises in recent years. In this paper, we aim to provide a consolidated view of the two
Externí odkaz:
http://arxiv.org/abs/2408.16757
Large multimodal models (LMMs) have exhibited proficiencies across many visual tasks. Although numerous well-known benchmarks exist to evaluate model performance, they increasingly have insufficient headroom. As such, there is a pressing need for a n
Externí odkaz:
http://arxiv.org/abs/2408.11817
Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks, these approach
Externí odkaz:
http://arxiv.org/abs/2408.06798
Generalized Category Discovery (GCD) is a challenging task in which, given a partially labelled dataset, models must categorize all unlabelled instances, regardless of whether they come from labelled categories or from new ones. In this paper, we cha
Externí odkaz:
http://arxiv.org/abs/2408.04591
Histological artifacts pose challenges for both pathologists and Computer-Aided Diagnosis (CAD) systems, leading to errors in analysis. Current approaches for histological artifact restoration, based on Generative Adversarial Networks (GANs) and pixe
Externí odkaz:
http://arxiv.org/abs/2407.20172
We tackle the problem of Continual Category Discovery (CCD), which aims to automatically discover novel categories in a continuous stream of unlabeled data while mitigating the challenge of catastrophic forgetting -- an open problem that persists eve
Externí odkaz:
http://arxiv.org/abs/2407.19001
Point-drag-based image editing methods, like DragDiffusion, have attracted significant attention. However, point-drag-based approaches suffer from computational overhead and misinterpretation of user intentions due to the sparsity of point-based edit
Externí odkaz:
http://arxiv.org/abs/2407.18247
While personalized text-to-image generation has enabled the learning of a single concept from multiple images, a more practical yet challenging scenario involves learning multiple concepts within a single image. However, existing works tackling this
Externí odkaz:
http://arxiv.org/abs/2407.07077
3D modeling has long been an important area in computer vision and computer graphics. Recently, thanks to the breakthroughs in neural representations and generative models, we witnessed a rapid development of 3D modeling. 3D human modeling, lying at
Externí odkaz:
http://arxiv.org/abs/2406.04253