Deformable DETR
The content is also available as text: https://github.com/adensur/blog/blob/... This video is part of my "Modern Object Detection: from YOLO to transformers" series: • Modern Object Detection: from YOLO to tran... It talks about Deformable Detr - recent development, originated in 2021, that adds to the foundation of the tricks of the trade that are used in most modern transformer-based object detection models. Useful links: Deformable Convolution paper, 2017: https://arxiv.org/pdf/1703.06211.pdf Deformable Detr paper, 2021: https://arxiv.org/pdf/2010.04159.pdf My previous video about DETR: • Object Detection with Transformers (DETR) 00:00 - Introduction 01:27 - Deformable Convolutions 05:20 - Deformable Convolutions: Offset Prediction 07:50 - Deformable Convolutions: Bilinear Interpolation 12:24 - Deformable Convolutions: Results 14:33 - Deformable Attention 17:06 - Deformable Self-Attention 19:32 - Deformable Cross-Attention 24:27 - MultiScale Deformable Attention 29:04 - Results & Next Up

Reading Deformable DETR source code

DINO - DETR with Improved DeNoising AnchorBoxes for End-to-End Object Detection

Why Does Diffusion Work Better than Auto-Regression?

Обзор архитектуры Detection Transformer (DETR)

Object Detection with Transformers (DETR)

Attention is all you need (Transformer) - Model explanation (including math), Inference and Training

How Attention Mechanism Works in Transformer Architecture

Attention in transformers, step-by-step | Deep Learning Chapter 6

MAMBA and State Space Models explained | SSM explained

OWASP's Top 10 Ways to Attack LLMs: AI Vulnerabilities Exposed

RT DETR - realtime object detection with transformers

Diffusion Models (DDPM & DDIM) - Easily explained!

AlphaFold - The Most Useful Thing AI Has Ever Done

DAB Detr (dynamic anchor boxes)

DN Detr (Denoising Detr for object detection)

LLMs Don't Need More Parameters. They Need Loops.

CoDETR - SOTA object detection with transformers

DETR: End-to-End Object Detection with Transformers (Paper Explained)

Latent Space Visualisation: PCA, t-SNE, UMAP | Deep Learning Animated
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
