Zobrazeno 1 - 10
of 1 902
pro vyhledávání: '"Lu, Guangming"'
Few-shot semantic segmentation (FSS) has achieved great success on segmenting objects of novel classes, supported by only a few annotated samples. However, existing FSS methods often underperform in the presence of domain shifts, especially when enco
Externí odkaz:
http://arxiv.org/abs/2404.10322
Autor:
Scott, John J R, Lu, Guangming, Rodriguez, Brian J., MacLaren, Ian, Salje, Ekhard K. H., Arredondo, Miryam
The elastic interaction between kinks (and antikinks) within domain walls plays a pivotal role in shaping the domain structure, and their dynamics. In bulk materials, kinks interact as elastic monopoles, dependent on the distance between walls, and t
Externí odkaz:
http://arxiv.org/abs/2401.16048
Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency. To mitigate this inefficiency, we present Bi-directional Tuning for lossless Accelerat
Externí odkaz:
http://arxiv.org/abs/2401.12522
Autor:
Pei, Wenjie, Xu, Weina, Wu, Zongze, Li, Weichao, Wang, Jinfan, Lu, Guangming, Wang, Xiangrong
The crux of graph classification lies in the effective representation learning for the entire graph. Typical graph neural networks focus on modeling the local dependencies when aggregating features of neighboring nodes, and obtain the representation
Externí odkaz:
http://arxiv.org/abs/2401.00755
Autor:
Chen, Hao, Du, Lun, Lu, Yuxuan, Fu, Qiang, Chen, Xu, Han, Shi, Kang, Yanbin, Lu, Guangming, Li, Zi
Online recruitment platforms typically employ Person-Job Fit models in the core service that automatically match suitable job seekers with appropriate job positions. While existing works leverage historical or contextual information, they often disre
Externí odkaz:
http://arxiv.org/abs/2401.00010
As a prominent parameter-efficient fine-tuning technique in NLP, prompt tuning is being explored its potential in computer vision. Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which represents an
Externí odkaz:
http://arxiv.org/abs/2312.10376
3D single object tracking remains a challenging problem due to the sparsity and incompleteness of the point clouds. Existing algorithms attempt to address the challenges in two strategies. The first strategy is to learn dense geometric features based
Externí odkaz:
http://arxiv.org/abs/2312.10608
D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
Adapting large pre-trained image models to few-shot action recognition has proven to be an effective and efficient strategy for learning robust feature extractors, which is essential for few-shot learning. Typical fine-tuning based adaptation paradig
Externí odkaz:
http://arxiv.org/abs/2312.01431
Accurately labeling biomedical data presents a challenge. Traditional semi-supervised learning methods often under-utilize available unlabeled data. To address this, we propose a novel reliability-based training data cleaning method employing inducti
Externí odkaz:
http://arxiv.org/abs/2309.07332
Effective image restoration with large-size corruptions, such as blind image inpainting, entails precise detection of corruption region masks which remains extremely challenging due to diverse shapes and patterns of corruptions. In this work, we pres
Externí odkaz:
http://arxiv.org/abs/2308.14061