We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image.
#14 best model for Semantic Segmentation on ADE20K val
As a result they are huge in terms of parameters and number of operations; hence slow too.
Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in automatic translation, speech-to-text, scene understanding, ranking user preferences, ad placement, etc.
We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.
#2 best model for Scene Segmentation on SUN-RGBD
Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making.
Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible.
Per-pixel ground-truth depth data is challenging to acquire at scale.
#7 best model for Monocular Depth Estimation on KITTI Eigen split
Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pixels across rows and columns of an image is not fully explored.
SOTA for Lane Detection on TuSimple