CVPR 2020

Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection

CVPR 2020 tensorflow/models

In this paper we propose a method that leverages temporal context from the unlabeled frames of a novel camera to improve performance at that camera.

VIDEO OBJECT DETECTION VIDEO UNDERSTANDING

MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

CVPR 2020 tensorflow/models

We propose Mnasfpn, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models.

OBJECT DETECTION

PointRend: Image Segmentation as Rendering

CVPR 2020 facebookresearch/detectron2

We present a new method for efficient high-quality image segmentation of objects and scenes.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

Distilling Effective Supervision from Severe Label Noise

CVPR 2020 google-research/google-research

For instance, on CIFAR100 with a $40\%$ uniform noise ratio and only 10 trusted labeled data per class, our method achieves $80. 2{\pm}0. 3\%$ classification accuracy, where the error rate is only $1. 4\%$ higher than a neural network trained without label noise.

IMAGE CLASSIFICATION

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

CVPR 2020 open-mmlab/mmdetection

In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them.

OBJECT DETECTION

Analyzing and Improving the Image Quality of StyleGAN

CVPR 2020 NVlabs/stylegan2

Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

IMAGE GENERATION

Adversarial Examples Improve Image Recognition

CVPR 2020 rwightman/pytorch-image-models

We show that AdvProp improves a wide range of models on various image recognition tasks and performs better when the models are bigger.

#12 best model for Image Classification on ImageNet (using extra training data)

IMAGE CLASSIFICATION

Designing Network Design Spaces

CVPR 2020 rwightman/pytorch-image-models

In this work, we present a new network design paradigm.

#64 best model for Image Classification on ImageNet (using extra training data)

IMAGE CLASSIFICATION

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

CVPR 2020 tensorflow/tpu

We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.

INSTANCE SEGMENTATION NEURAL ARCHITECTURE SEARCH REAL-TIME OBJECT DETECTION