Papers Read on AI

Papers Read on AI

By RobNewsTech News
Download on the App Store

Papers Read on AI episodes

  • How Much Can CLIP Benefit Vision-and-Language Tasks?
    We show that CLIP (Contrastive Language-Image Pre-training) significantly outperforms widely-used visual encoders trained with in-domain annotated data, such as BottomUp-TopDown. We achieve competitive or better results on diverse V&L tasks, while establishing new state-of-the-art results on Visual Question Answering, Visual Entailment, and V&L Navigation tasks.
    2021: Sheng Shen, Liunian Harold Li, Hao Tan, M. Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, K. Keutzer
    https://arxiv.org/pdf/2107.06383v1.pdf
    30 min
  • Towards Real-World Blind Face Restoration with Generative Facial Prior

    In this work, we propose GFPGAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via novel channel-split spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real world datasets.

    2021: Xintao Wang, Yu Li, Honglun Zhang, Ying Shan

    https://arxiv.org/pdf/2101.04061v2.pdf

    30 min

About Papers Read on AI

From the publisher's feed

Keeping you up to date with the latest trends and best performing architectures in this fast evolving field in computer science.