The Highest-Trending Research Papers From CVPR 2020


CVPR 2020 is yet another big AI conference that takes place 100% virtually this year. But regardless of the format, the conference still showcases the most interesting cutting-edge research ideas in computer vision and image generation.
Here we’ve picked up the research papers that started trending within the AI research community months before their actual presentation at CVPR 2020. These papers cover the efficiency of object detectors, novel techniques for converting RGB-D images into 3D photography, and autoencoders that go beyond the capabilities of generative adversarial networks (GANs) with respect to image generation and manipulation.
Subscribe to our AI Research mailing list at the bottom of this article to be alerted when we release new summaries.
If you’d like to skip around, here are the papers we featured:

EfficientDet: Scalable and Efficient Object Detection
3D Photography using Context-aware Layered Depth Inpainting
Adversarial Latent Autoencoders

 
Cutting-Edge Research Papers From CVPR 2020
 

1. EfficientDet: Scalable and Efficient Object Detection , by Mingxing Tan, Ruoming Pang, Quoc V. Le

 
Original Abstract 
Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multi-scale feature fusion; Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and EfficientNet backbones, we have developed a new family of object detectors, called EfficientDet, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single-model and single-scale, our EfficientDet-D7 achieves state-of-the-art 52.2 AP on COCO test-dev with 52M parameters and 325B FLOPs, being 4×–9× smaller and using 13×–42× fewer FLOPs than previous detectors. Code is available on GitHub .
 
Our Summary 
The large size of object detection models deters their deployment in real-world applications such as self-driving cars and robotics. To address this problem, the Google Research team introduces two optimizations, namely (1) a weighted bi-directional feature pyramid network (BiFPN) for efficient multi-scale feature fusion and (2) a novel compound scaling method. By combining these optimizations with the EfficientNet backbones, the authors develop a family of object detectors, called EfficientDet . The experiments demonstrate that these object detectors consistently achieve higher accuracy with far...

Top