CVPR 2018

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

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

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

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

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

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

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

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

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

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