LAUSR

Learning local descriptors with multi-level feature aggregation and spatial context pyramid

Sign Up to like & get
recommendations!
0 Published in 2021 at "Neurocomputing"

DOI: 10.1016/j.neucom.2021.07.030

Abstract: Abstract Despite that efforts have shifted to learning local descriptors with convolutional neural network (CNN) from hand-crafted realm, the inherent feature hierarchy within CNN has been rarely explored. To increase both the invariant and discriminative… read more here.

Keywords: local descriptors; feature; learning local; level feature ... See more keywords

Learning Local and Global Priors for JPEG Image Artifacts Removal

Sign Up to like & get
recommendations!
1 Published in 2020 at "IEEE Signal Processing Letters"

DOI: 10.1109/lsp.2020.3039932

Abstract: Lossy compression will inevitably introduce image artifacts in the decoded image and degrade the image quality. In recent years, convolutional neural network (CNN) has been exploited for removing compression artifacts with great success. However, most… read more here.

Keywords: global prior; image artifacts; local global; learning local ... See more keywords

Deep Spike Learning With Local Classifiers

Sign Up to like & get
recommendations!
2 Published in 2022 at "IEEE Transactions on Cybernetics"

DOI: 10.1109/tcyb.2022.3188015

Abstract: Backpropagation has been successfully generalized to optimize deep spiking neural networks (SNNs), where, nevertheless, gradients need to be propagated back through all layers, resulting in a massive consumption of computing resources and an obstacle to… read more here.

Keywords: learning local; spike learning; deep spike; local learning ... See more keywords

SharpFormer: Learning Local Feature Preserving Global Representations for Image Deblurring

Sign Up to like & get
recommendations!
2 Published in 2023 at "IEEE Transactions on Image Processing"

DOI: 10.1109/tip.2023.3251029

Abstract: The goal of dynamic scene deblurring is to remove the motion blur presented in a given image. To recover the details from the severe blurs, conventional convolutional neural networks (CNNs) based methods typically increase the… read more here.

Keywords: information; image deblurring; learning local; local feature ... See more keywords

Learning Local Metrics and Influential Regions for Classification

Sign Up to like & get
recommendations!
0 Published in 2020 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"

DOI: 10.1109/tpami.2019.2914899

Abstract: The performance of distance-based classifiers heavily depends on the underlying distance metric, so it is valuable to learn a suitable metric from the data. To address the problem of multimodality, it is desirable to learn… read more here.

Keywords: metrics influential; distance; local metrics; influential regions ... See more keywords