Gan-supervised dense visual alignment
Abstract We propose GAN-Supervised Learning, a framework for learning discriminative
models and their GAN-generated training data jointly end-to-end. We apply our framework to …
models and their GAN-generated training data jointly end-to-end. We apply our framework to …
Unsupervised part-based disentangling of object shape and appearance
Large intra-class variation is the result of changes in multiple object characteristics. Images,
however, only show the superposition of different variable factors such as appearance or …
however, only show the superposition of different variable factors such as appearance or …
Mixnmatch: Multifactor disentanglement and encoding for conditional image generation
We present MixNMatch, a conditional generative model that learns to disentangle and
encode background, object pose, shape, and texture from real images with minimal …
encode background, object pose, shape, and texture from real images with minimal …
Robot target recognition using deep federated learning
B Xue, Y He, F Jing, Y Ren, L Jiao… - International Journal of …, 2021 - Wiley Online Library
Robot target recognition is a critical and fundamental machine vision task. In this paper,
InVision, a robot target recognition approach is proposed using deep federated learning …
InVision, a robot target recognition approach is proposed using deep federated learning …
Infogan-cr and modelcentrality: Self-supervised model training and selection for disentangling gans
Disentangled generative models map a latent code vector to a target space, while enforcing
that a subset of the learned latent codes are interpretable and associated with distinct …
that a subset of the learned latent codes are interpretable and associated with distinct …
Contrastive learning for diverse disentangled foreground generation
We introduce a new method for diverse foreground generation with explicit control over
various factors. Existing image inpainting based foreground generation methods often …
various factors. Existing image inpainting based foreground generation methods often …
Explicit disentanglement of appearance and perspective in generative models
Disentangled representation learning finds compact, independent and easy-to-interpret
factors of the data. Learning such has been shown to require an inductive bias, which we …
factors of the data. Learning such has been shown to require an inductive bias, which we …
Mutual information maximization on disentangled representations for differential morph detection
S Soleymani, A Dabouei… - Proceedings of the …, 2021 - openaccess.thecvf.com
In this paper, we present a novel differential morph detection framework, utilizing landmark
and appearance disentanglement. In our framework, the face image is represented in the …
and appearance disentanglement. In our framework, the face image is represented in the …
A tale of two latent flows: learning latent space normalizing flow with short-run langevin flow for approximate inference
We study a normalizing flow in the latent space of a top-down generator model, in which the
normalizing flow model plays the role of the informative prior model of the generator. We …
normalizing flow model plays the role of the informative prior model of the generator. We …
Learning dynamic generator model by alternating back-propagation through time
This paper studies the dynamic generator model for spatialtemporal processes such as
dynamic textures and action sequences in video data. In this model, each time frame of the …
dynamic textures and action sequences in video data. In this model, each time frame of the …