Search Results for author:
Found 13 papers, 3 papers with code
WERank: Towards Rank Degradation Prevention for Self-Supervised Learning Using Weight Regularization
A common phenomena confining the representation quality in Self-Supervised Learning (SSL) is dimensional collapse (also known as rank degeneration), where the learned representations are mapped to a low dimensional subspace of the representation space.
Scalable Graph Self-Supervised Learning
Our experiments demonstrate that the cost associated with the loss computation can be reduced via node or dimension sampling without lowering the downstream performance.
ExGRG: Explicitly-Generated Relation Graph for Self-Supervised Representation Learning
Self-supervised Learning (SSL) has emerged as a powerful technique in pre-training deep learning models without relying on expensive annotated labels, instead leveraging embedded signals in unlabeled data.
Todyformer: Towards Holistic Dynamic Graph Transformers with Structure-Aware Tokenization
Furthermore, we illustrate the underlying aspects of the proposed model in effectively capturing extensive temporal dependencies in dynamic graphs.
DyG2Vec: Efficient Representation Learning for Dynamic Graphs
Temporal graph neural networks have shown promising results in learning inductive representations by automatically extracting temporal patterns.
Ranked #1 on
Dynamic Link Prediction
on Social Evolution
ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI
To address these limitations, we propose ROOD-MRI: a platform for benchmarking the Robustness of DNNs to Out-Of-Distribution (OOD) data, corruptions, and artifacts in MRI.
Video action recognition for lane-change classification and prediction of surrounding vehicles
Up to four different two-stream-based approaches, that have been successfully applied to address human action recognition, are adapted here by stacking visual cues from forward-looking video cameras to recognize and anticipate lane-changes of target vehicles.
Contextual Interference Reduction by Selective Fine-Tuning of Neural Networks
We study the role of the context on interfering with a disentangled foreground target object representation in this work.
Two-Stream Networks for Lane-Change Prediction of Surrounding Vehicles
Different sizes of the regions around the vehicles are analyzed, evaluating the importance of the interaction between vehicles and the context information in the performance.
Compact Neural Representation Using Attentive Network Pruning
Network parameter reduction methods have been introduced to systematically deal with the computational and memory complexity of deep networks.
Selective Segmentation Networks Using Top-Down Attention
Convolutional neural networks model the transformation of the input sensory data at the bottom of a network hierarchy to the semantic information at the top of the visual hierarchy.
Priming Neural Networks
This process has been shown to be an effect of top-down signaling in the visual system triggered by the said cue.
STNet: Selective Tuning of Convolutional Networks for Object Localization
Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks.
