A Local Parallel Search Approach for Memory Failure Pattern Identification

Lin, Bing-Yang; Wu, Cheng‐Wen; Lee, Mincent; Lin, Hong‐Ping; Peng, Ching-Nen; Wang, Min-Jer

doi:10.1109/tc.2015.2462820

Cited by 5 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods only get multi receptive fields feature for pixel classification and lead to huge computational costs at the same time. FPN [4] proposed a pyramid hierarchy architecture that has been demonstrated to be beneficial to downstream tasks such as object detection and semantic segmentation. Topformer [14] proposed a lite‐weight semantic module to combine local features and global features.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Lite‐weight semantic segmentation with AG self‐attention

Liu

Gao

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

Due to the large computational and GPUs memory cost of semantic segmentation, some works focus on designing a lite weight model to achieve a good trade‐off between computational cost and accuracy. A common method is to combined CNN and vision transformer. However, these methods ignore the contextual information of multi receptive fields. And existing methods often fail to inject detailed information losses in the downsampling of multi‐scale feature. To fix these issues, we propose AG Self‐Attention, which is Enhanced Atrous Self‐Attention (EASA), and Gate Attention. AG Self‐Attention adds the contextual information of multi receptive fields into the global semantic feature. Specifically, the Enhanced Atrous Self‐Attention uses weight shared atrous convolution with different atrous rates to get the contextual information under the specific different receptive fields. Gate Attention introduces gating mechanism to inject detailed information into the global semantic feature and filter detailed information by producing “fusion” gate and “update” gate. In order to prove our insight. We conduct numerous experiments in common semantic segmentation datasets, consisting of ADE20 K, COCO‐stuff, PASCAL Context, Cityscapes, to show that our method achieves state‐of‐the‐art performance and achieve a good trade‐off between computational cost and accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Existing works mainly focus on designing a lite‐weight backbone to reduce the parameter of the model and the computational cost. Features extracted by the backbone are fed into the FPN [4] or ASPP [5] for segmentation, as shown in Figure 1a,b. The first family of works took the specially designed convolution operation.…”

Section: Introductionmentioning

confidence: 99%

Lite‐weight semantic segmentation with AG self‐attention

Liu

Gao

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Transformers were originally introduced in the context of natural language modelling [VSP*17]. Lin et al [LWL21a] use a vanilla transformer to reconstruct coarsely posed human bodies and hands from images, and a learnable MLP to upsample the meshes to full resolution. In a follow up work [LWL21b], the authors coupled their previous vanilla transformer with graph‐convolutional layers and showed better accuracy in body and hand reconstruction.…”

Section: Related Workmentioning

confidence: 99%

Facial Animation with Disentangled Identity and Motion using Transformers

Chandran

Zoss

Groß

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

We propose a 3D+time framework for modeling dynamic sequences of 3D facial shapes, representing realistic non‐rigid motion during a performance. Our work extends neural 3D morphable models by learning a motion manifold using a transformer architecture. More specifically, we derive a novel transformer‐based autoencoder that can model and synthesize 3D geometry sequences of arbitrary length. This transformer naturally determines frame‐to‐frame correlations required to represent the motion manifold, via the internal self‐attention mechanism. Furthermore, our method disentangles the constant facial identity from the time‐varying facial expressions in a performance, using two separate codes to represent neutral identity and the performance itself within separate latent subspaces. Thus, the model represents identity‐agnostic performances that can be paired with an arbitrary new identity code and fed through our new identity‐modulated performance decoder; the result is a sequence of 3D meshes for the performance with the desired identity and temporal length. We demonstrate how our disentangled motion model has natural applications in performance synthesis, performance retargeting, key‐frame interpolation and completion of missing data, performance denoising and retiming, and other potential applications that include full 3D body modeling.

show abstract