# 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).

# Time of Flight vs. FMCW LiDAR

AEye.ai shared comparison of time of flight (ToF) and Frequency Modulated Continuous Wave (FMCW). I had worked in ToF when I was in Samsung (2014~2016) and am very interested in learning more of it.

# Get Option Data from Yahoo with Pandas

This notebook shows how to read the option chain data from Yahoo finance with Pandas. Especially we will use pandas.read_html.

I will create a new reading note series based on Must-read AI Papers from Crossminds.ai.

# 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.