Very Deep Convolutional Networks for Large-Scale Image Recognition

4 Sep 2014facebookresearch/detectron

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting.

Deep Residual Learning for Image Recognition

CVPR 2016 facebookresearch/detectron

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.

IMAGE CLASSIFICATION OBJECT DETECTION

Group Normalization

ECCV 2018 facebookresearch/detectron

GN can outperform its BN-based counterparts for object detection and segmentation in COCO, and for video classification in Kinetics, showing that GN can effectively replace the powerful BN in a variety of tasks.

OBJECT DETECTION VIDEO CLASSIFICATION

Detecting and Recognizing Human-Object Interactions

CVPR 2018 facebookresearch/detectron

Our hypothesis is that the appearance of a person -- their pose, clothing, action -- is a powerful cue for localizing the objects they are interacting with.

HUMAN-OBJECT INTERACTION DETECTION

Feature Pyramid Networks for Object Detection

CVPR 2017 facebookresearch/detectron

Feature pyramids are a basic component in recognition systems for detecting objects at different scales.

#17 best model for Object Detection on COCO

OBJECT DETECTION

Aggregated Residual Transformations for Deep Neural Networks

CVPR 2017 facebookresearch/detectron

Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set.

IMAGE CLASSIFICATION

Data Distillation: Towards Omni-Supervised Learning

CVPR 2018 facebookresearch/detectron

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data.

KEYPOINT DETECTION OBJECT DETECTION

R-FCN: Object Detection via Region-based Fully Convolutional Networks

NeurIPS 2016 facebookresearch/detectron

In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.

REAL-TIME OBJECT DETECTION

Fast R-CNN

ICCV 2015 facebookresearch/detectron

Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks.

OBJECT DETECTION

Learning to Segment Every Thing

CVPR 2018 facebookresearch/detectron

Most methods for object instance segmentation require all training examples to be labeled with segmentation masks.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION