State of AI Report 2021 (Benaich and Hogarth) (includes Computer Vision)

State of AI Report 2021 (Benaich and Hogarth) (includes Computer Vision)

State of AI Report 2021

The State of AI Report analyses the most interesting developments in AI … Now in its fourth year, the State of AI Report 2021 is reviewed by AI practioners in industry and research, and features invited contributions from a range of well-known and up-and-coming companies and research groups.
State of AI https://www.stateof.ai

State of AI Google slides (188 pages) https://docs.google.com/presentation/d/1bwJDRC777rAf00Drthi9yT2c9b0MabWO5ZlksfvFzx8

State of AI Report 2021 (Benaich and Hogarth)

Section 1: Research

Some computer vision headlines are below. The 188 page report covers many other areas of AI and also has sections on talent and industry.

1. Self-supervision is taking over computer vision

2. Researchers compare a self-supervised ViT (SSViT) to fully supervised ViTs and convnets .. find that SSViTs learn more powerful representations.

3. Transformers take over other major AI applications, e.g. audio and 3D point clouds

4. Transformers extend into efficient self-attention-based architectures

5. MLPs and CNNs make a comeback .. When trained properly, they are competitive with transformers on several NLP and computer vision tasks.

6. Remarkable progress in Novel View Synthesis .. Neural Radiance Fields (NeRF) already achieves SOTA results on view synthesis.

7. Less is more: watching a few clips is enough .. to caption a video .. ClipBERT .. outperforms existing methods that exploit full-length videos.

8. GANs have .. new adversary: diffusion models .. outperforms .. in image generation, audio synthesis, shape generation and music generation.

9. medical image representations .. ConVIRT .. pre-trains .. image-text pairs .. without .. supervision .. outperforms all ImageNet .. 10% .. data.

10. Using CLIP’s .. representations for zero-shot object detection .. create a learning model (VLiD) that surpasses supervised models on zero-shot

11. Computer vision unlocks accurate and fast disease assessment using digital biomarkers for drug discovery

Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website

LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b

Photo by Andrew Stutesman on Unsplash

--

--

AI News Clips by Morris Lee: News to help your R&D

A computer vision consultant in artificial intelligence and related hitech technologies 37+ years. Am innovator with 66+ patents and ready to help a firm's R&D.