Learn and apply the state-of-the-art approaches for computer vision.
Segmentation Models
Understanding the state-of-the-art segmentation techniques and tools in computer vision.
Computer Vision
Miniseries / Collections
Camoufladge Object Detection
Understanding the state-of-the-art approaches for camoufladge object detection.
Medical Image Landmark Detection
Understanding the state-of-the-art approaches for the detection of landmakrs in medical images.
Standalone Posts
Building a Masked Autoencoder (MAE) from Scratch in PyTorch
Learn how masked autoencoder (MAE) works and implemented in PyTorch
ViTDet: Plain Vision Transformer Backbones for Object Detection
ViTDet demonstrates that plain, non-hierarchical Vision Transformers can compete with hierarchical backbones for object detection through simple adaptations.
The Image is a Sequence: Dissecting the Vision Transformer (ViT)
An in-depth look at ‘An Image is Worth 16x16 Words,’ the paper that introduced the pure Vision Transformer, its architecture, novelty, limitations, and how modern models like Swin Transformer evolved from it.
Swin Transformer: Shifting Windows to Build Hierarchical Vision Models
This post provides a minimal PyTorch implementation of Swin Transformer for a simple image classification.