Feature Correlation
56 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Feature Correlation
Most implemented papers
Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
SHI-Labs/Cross-Scale-Non-Local-Attention
•
•
CVPR 2020
By combining the new CS-NL prior with local and in-scale non-local priors in a powerful recurrent fusion cell, we can find more cross-scale feature correlations within a single low-resolution (LR) image.
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
PruneTruong/GLU-Net
•
•
NeurIPS 2020
We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer.
Deep Graph Clustering via Dual Correlation Reduction
yueliu1999/awesome-deep-graph-clustering
•
•
To address this issue, we propose a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner.
Correlation Verification for Image Retrieval
Geometric verification is considered a de facto solution for the re-ranking task in image retrieval.
Tabular Data Contrastive Learning via Class-Conditioned and Feature-Correlation Based Augmentation
layer6ai-labs/tabular-class-conditioned-ssl
•
•
Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space.
Non-Local Recurrent Network for Image Restoration
Ding-Liu/NLRN
•
•
NeurIPS 2018
The main contributions of this work are: (1) Unlike existing methods that measure self-similarity in an isolated manner, the proposed non-local module can be flexibly integrated into existing deep networks for end-to-end training to capture deep feature correlation between each location and its neighborhood.
Removing the Feature Correlation Effect of Multiplicative Noise
Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks.
Second-Order Attention Network for Single Image Super-Resolution
daitao/SAN
•
•
CVPR 2019
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance.
Zero-Shot Out-of-Distribution Detection with Feature Correlations
zeroshot-ood/ood-detection
•
•
We find that characterizing activity patterns by feature correlations and identifying anomalies in pairwise feature correlation values can yield high OOD detection rates.
Correlating Edge, Pose with Parsing
Compared with the existing practice of feature concatenation, we find that uncovering the correlation among the three factors is a superior way of leveraging the pivotal contextual cues provided by edges and poses.
