We present a simple, highly modularized network architecture for image classification. Our
network is constructed by repeating a building block that aggregates a set of transformations …

Contrastive learning is a self-supervised representation learning method that achieves
milestone performance in various classification tasks. However, due to its unsupervised …

Disentanglement learning is crucial for obtaining disentangled representations and
controllable generation. Current disentanglement methods face several inherent limitations …

Data in vision domain often exhibit highly-skewed class distribution, ie, most data belong to
a few majority classes, while the minority classes only contain a scarce amount of instances …

Convolutional neural networks provide visual features that perform remarkably well in many
computer vision applications. However, training these networks requires significant amounts …

We present a novel framework for iterative visual reasoning. Our framework goes beyond
current recognition systems that lack the capability to reason beyond stack of convolutions …

Distinguishing subtle differences in attributes is valuable, yet learning to make visual
comparisons remains nontrivial. Not only is the number of possible comparisons quadratic in …

When labeled data is scarce for a specific target task, transfer learning often offers an
effective solution by utilizing data from a related source task. However, when transferring …

ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its
basic operations include group, channel-wise convolution and channel shuffling. However …

We study the problem of building models that disentangle independent factors of variation.
Such models could be used to encode features that can efficiently be used for classification …