End-to-End Object Detection with Transformers

DETR still uses CNN for feature extration and then use transformer to capture context of objects (boxes) in images. Compared with previous object detection model, e.g., MaskRCNN, YOLO, it doesn’t need to have anchor and nonmaximal suppression, which is achived by transformer. Besides DETR could be directly applied for panoptic segmentation (joint semantic segmentation and instance segmentation).

Read More

Transformer in Computer Vision

Transformer architecture has achieved state-of-the-art results in many NLP (Natural Language Processing) tasks. Though CNN has been the domiant models for CV tasks, using Transformers for vision tasks became a new research direction for the sake of reducing architecture complexity, and exploring scalability and training efficiency.

Read More

Price Earning Ratio

Most people know price earning ratio (P/E ratio or PE) and use it a way of value whether the stock is over-valued or not.

Read More

MacPorts for Mac

The MacPorts Project is an open-source community initiative to design an easy-to-use system for compiling, installing, and upgrading either command-line, X11 or Aqua based open-source software on the Mac operating system.

Read More