Chaim Baskin
Deep Learning Researcher
We present a novel confidence refinement scheme that enhances pseudo-lab...
Traditional methods for learning with the presence of noisy labels have
...
It has been recently discovered that adversarially trained classifiers
e...
Deep neural networks are known to be susceptible to adversarial perturba...
Autonomous scene exposure and exploration, especially in localization or...
Strategic classification studies learning in settings where users can mo...
Quantized neural networks are well known for reducing latency, power
con...
Binary Neural Networks (BNNs) are an extremely promising method to reduc...
Equivariance to permutations and rigid motions is an important inductive...
Graph isomorphism testing is usually approached via the comparison of gr...
Despite their growing popularity, graph neural networks (GNNs) still hav...
The referring video object segmentation task (RVOS) involves segmentatio...
The success of learning with noisy labels (LNL) methods relies heavily o...
We consider the problem of supervised classification, such that the feat...
Graph neural networks (GNNs) have shown broad applicability in a variety...
Unsupervised learning has always been appealing to machine learning
rese...
Convolutional Neural Networks (CNNs) have become common in many fields
i...
Even though deep learning have shown unmatched performance on various ta...
Deep neural networks are known to be vulnerable to inputs with malicious...
Neural network quantization enables the deployment of large models on
re...
Convolutional neural networks (CNNs) have become the dominant neural net...
Convolutional neural networks (CNNs) achieve state-of-the-art accuracy i...
Recently, deep learning has become a de facto standard in machine learni...
Beauty is in the eye of the beholder. This maxim, emphasizing the
subjec...
Convolutional Neural Networks (CNN) has become more popular choice for
v...
Convolutional Neural Networks (CNN) are very popular in many fields incl...
We present a novel method for training a neural network amenable to infe...
We present a novel method for training deep neural network amenable to
i...
Deep neural networks (DNNs) are used by different applications that are
...