CVPR 2018

MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

CVPR 2018 tensorflow/models

We present MorphNet, an approach to automate the design of neural network structures.

NEURAL ARCHITECTURE SEARCH

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

CVPR 2018 tensorflow/models

In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth.

IMAGE RETRIEVAL

The iNaturalist Species Classification and Detection Dataset

CVPR 2018 tensorflow/models

Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories.

IMAGE CLASSIFICATION

AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions

CVPR 2018 tensorflow/models

The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1. 58M action labels with multiple labels per person occurring frequently.

TEMPORAL ACTION LOCALIZATION VIDEO UNDERSTANDING

Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints

CVPR 2018 tensorflow/models

We present a novel approach for unsupervised learning of depth and ego-motion from monocular video.

DEPTH AND CAMERA MOTION

Learning Transferable Architectures for Scalable Image Recognition

CVPR 2018 tensorflow/models

In our experiments, we search for the best convolutional layer (or "cell") on the CIFAR-10 dataset and then apply this cell to the ImageNet dataset by stacking together more copies of this cell, each with their own parameters to design a convolutional architecture, named "NASNet architecture".

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH

MobileNetV2: Inverted Residuals and Linear Bottlenecks

CVPR 2018 tensorflow/models

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.

IMAGE CLASSIFICATION OBJECT DETECTION SEMANTIC SEGMENTATION

DensePose: Dense Human Pose Estimation In The Wild

CVPR 2018 facebookresearch/detectron

In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation.

POSE ESTIMATION

Non-local Neural Networks

CVPR 2018 facebookresearch/detectron

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.

INSTANCE SEGMENTATION KEYPOINT DETECTION OBJECT DETECTION VIDEO CLASSIFICATION

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