We propose spatially-adaptive normalization, a simple but effective layer for synthesizing
photorealistic images given an input semantic layout. Previous methods directly feed the …

Few-shot learning has become essential for producing models that generalize from few
examples. In this work, we identify that metric scaling and metric task conditioning are …

Despite that convolutional neural networks (CNN) have recently demonstrated high-quality
reconstruction for single-image super-resolution (SR), recovering natural and realistic …

We present a simple and general method to train a single neural network executable at
different widths (number of channels in a layer), permitting instant and adaptive accuracy …

We introduce a general-purpose conditioning method for neural networks called FiLM:
Feature-wise Linear Modulation. FiLM layers influence neural network computation via a …

Video object segmentation targets segmenting a specific object throughout a video
sequence when given only an annotated first frame. Recent deep learning based …

Recently, deep residual networks have been successfully applied in many computer vision
and natural language processing tasks, pushing the state-of-the-art performance with …

Synthesizing photo-realistic images from text descriptions is a challenging problem.
Previous studies have shown remarkable progresses on visual quality of the generated …

Person re-identification (Re-ID) aims to match a target person across camera views at
different locations and times. Existing Re-ID studies focus on the short-term cloth-consistent …

Visual question answering requires high-order reasoning about an image, which is a
fundamental capability needed by machine systems to follow complex directives. Recently …