Search Results for author:
Found 8 papers, 4 papers with code
A Dynamically Weighted Loss Function for Unsupervised Image Segmentation
This work presents an improved version of an unsupervised Convolutional Neural Network (CNN) based algorithm that uses a constant weight factor to balance between the segmentation criteria of feature similarity and spatial continuity, and it requires continuous manual adjustment of parameters depending on the degree of detail in the image and the dataset.
A Contrastive Variational Graph Auto-Encoder for Node Clustering
Thanks to a newly identified term, our lower bound can escape Posterior Collapse and has more flexibility to account for the difference between the inference and generative models.
Graph Attention Network for Camera Relocalization on Dynamic Scenes
We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment.
Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering
We study these issues from two aspects: (1) there is a trade-off between Feature Randomness and Feature Drift when clustering and reconstruction are performed at the same level, and (2) the problem of Feature Drift is more pronounced for GAE models, compared with vanilla auto-encoder models, due to the graph convolutional operation and the graph decoding design.
Ranked #1 on
Node Clustering
on Pubmed
Coarse-to-Fine Object Tracking Using Deep Features and Correlation Filters
Motivated by this observation, and by the fact that discriminative correlation filters(DCFs) may provide a complimentary low-level information, we presenta novel tracking algorithm taking advantage of both approaches.
Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Drift
Clustering using deep autoencoders has been thoroughly investigated in recent years.
Ranked #2 on
Image Clustering
on MNIST-full
Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction
In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities.
Ranked #1 on
Image Clustering
on MNIST-test
Incremental One-Class Models for Data Classification
This research contributes to the field of one-class incremental learning and classification in case of non-stationary environments.
