Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks.
#53 best model for Image Classification on ImageNet
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
#8 best model for Semantic Segmentation on Cityscapes val
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN).
#18 best model for Image Super-Resolution on Set5 - 4x upscaling
This means that the super-resolution (SR) operation is performed in HR space.
In this work, we revisit the global average pooling layer proposed in , and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.
#2 best model for Weakly-Supervised Object Localization on Tiny ImageNet
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images.