Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Articles about Deep Learning fundamentals and advanced methods, from supervised to self-supervised learning, including Vision Transformers, DINO, CLIP, SAM2, and more; all implemented in PyTorch.
U2SEG is the first unsupervised approach to combine instance, semantic, and panoptic segmentation. It uses MaskCut algorithm from CutLER to create instance segmentation masks and…
U-Net was published in 2015 for spotting microscopic cells in biomedical scans, and since then, it became very popular. It created a massive impact; before…
There are a lot of supervised object detection and instance segmentation models (YOLO, RCNN Family, DETR …). Pipeline is the same for each one; first,…
When we talk about depth in computer vision, we think about stereo cameras, time-of-flight sensors, and LiDAR. These methods don’t work with a single RGB…
“a tiny vision language model that kicks ass and runs anywhere“, that is exactly how the creators of Moondream defined it. They are not wrong,…
SAM3 is just announced, and everybody is talking about it. But what is this hype all about? As you probably know from before, all the…
→ An article explaining Grounding DINO and how to detect objects with text prompts. I have so many articles about closed-set object detection, and most…
→ Step-by-step guide for training DETR(Detection Transformer) object detection models in PyTorch with any dataset. When it comes to object detection, there are popular models…
→ Article explaining DINOv3 and demonstrating how to create similarity maps using cosine similarity formula. Just look around. You probably see a door, window, bookcase,…
→ Article about explaining CLIP and demonstrating image classification using CLIP models. I normally like to write an introduction paragraph about the article, but not…
