Cell biology is fundamentally limited in its ability to collect complete data on cellular
phenotypes and the wide range of responses to perturbation. Areas such as computer vision …

Variational autoencoders (VAEs) are deep latent space generative models that have been
immensely successful in multiple exciting applications in biomedical informatics such as …

We present a generative framework for generalized zero-shot learning where the training
and test classes are not necessarily disjoint. Built upon a variational autoencoder based …

Responses generated by neural conversational models tend to lack informativeness and
diversity. We present Adversarial Information Maximization (AIM), an adversarial learning …

Zero shot learning in Image Classification refers to the setting where images from some
novel classes are absent in the training data but other information such as natural language …

We introduce a simple yet effective episode-based training framework for zero-shot learning
(ZSL), where the learning system requires to recognize unseen classes given only the …

We address the problem of generalized zero-shot semantic segmentation (GZS3) predicting
pixel-wise semantic labels for seen and unseen classes. Most GZS3 methods adopt a …

Zero-shot learning (ZSL) is a challenging task due to the lack of unseen class data during
training. Existing works attempt to establish a map** between the visual and class spaces …

Compound fault diagnosis of bearings has always been a challenge, due to the occurrence
of various faults with randomness and complexity. Existing deep learning-based methods …

Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image
database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should …