Modern CV Models
Use YOLO, SAM, ViT, and other modern CV architectures.
0%
Confidence · no data yet
After this skill you can…
- Run YOLO for real-time object detection
- Use SAM for zero-shot segmentation
- Fine-tune ViT on custom datasets
Prerequisites
Watch (10 videos)
YOLO V2 | Object Detection Series | Part 2
→ Understand the improvements in YOLO V2→ Use batch normalization in object detection models
TensorFlow: Advanced Techniques Specialization
→ Build advanced computer vision models→ Optimize training for computer vision tasks→ Create generative deep learning models
DeepSeek V3.2 Speciale Testing – Can It Handle Complex Tasks Without Tools?
→ Generate code for games→ Create 3D rendering prototypes
What is Segment Anything 3 (SAM3)? Live Q&A with Meta's Engineers Behind the Model
→ Use SAM 3 for object detection, segmentation, and tracking→ Fine-tune SAM 3 on custom data
RF-DETR Segmentation. Benchmarks, Inference, Training | Live Coding + Q&A (Jan 29th)
→ Train RF-DETR Segmentation models→ Compare model architectures
Artem Sevastopolsky and Dmitrii Pozdeev - DenseMarks Learning Canonical Embeddings for Human Heads
→ Use DenseMarks for downstream tasks→ Apply multi-task learning for facial landmarks and head segmentation→ Enforce spatial continuity with latent cube features
Is YOLO26 Faster Than YOLO11? Full Comparison & Results
→ Use ONNX export for faster CPU inference→ Optimize computer vision models for real-time detection
Mask R-CNN - Explained!
→ Implement Mask R-CNN for object detection and segmentation→ Understand the architecture and training of Mask R-CNN
Mistral OCR 3 Deep Dive: Document AI Done Right
→ Train VLMs→ Integrate OCR with VLMs→ Develop Document AI systems
PyTorch Day India 2026 Exploring Tile based Programming Abstractions for KLA’s Image Processing Work
→ Deploy computer vision models→ Tune kernel performance
DeepCamp AI