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.
Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks.
#78 best model for Image Classification on ImageNet
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN).
#10 best model for Image Super-Resolution on Urban100 - 2x upscaling
This means that the super-resolution (SR) operation is performed in HR space.
A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation.
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.