Advanced CNNs for Computer Vision Applications
Chapter 1: Revisiting CNN Foundations and Modern Architectures
Brief Review of CNN Building Blocks
Evolution of CNN Architectures: AlexNet to ResNet
Understanding Residual Connections and Skip Architectures
Inception Modules and Network-in-Network Concepts
DenseNet: Architecture and Connectivity Patterns
EfficientNet: Compound Scaling for Models
Architectural Design Choices and Trade-offs
Implementing Modern Architectures Practice
Chapter 2: Advanced Training and Optimization Techniques
Advanced Optimization Algorithms
Learning Rate Schedules and Cyclical Learning Rates
Regularization Revisited: Advanced Techniques
Batch Normalization Internals and Alternatives
Weight Initialization Strategies for Deep Networks
Gradient Clipping and Gradient Flow Mitigation
Mixed Precision Training Fundamentals
Debugging and Monitoring Deep CNN Training
Hands-on Practical: Implementing Advanced Training Loops
Chapter 3: Object Detection Algorithms
Two-Stage Detectors: R-CNN Family
Region Proposal Networks Explained
Single-Stage Detectors: YOLO Family
Single-Stage Detectors: SSD and RetinaNet
Anchor Boxes: Design and Refinement
Non-Maximum Suppression Variants
Evaluation Metrics for Object Detection
Implementing an Object Detector Practice
Chapter 4: Image Segmentation Techniques
Semantic Segmentation vs. Instance Segmentation
Fully Convolutional Networks for Segmentation
Encoder-Decoder Architectures: U-Net and SegNet
Dilated (Atrous) Convolutions for Segmentation
DeepLab Family: Atrous Spatial Pyramid Pooling
Instance Segmentation Approaches (Mask R-CNN)
Evaluation Metrics for Segmentation
Hands-on Practical: Building a Semantic Segmentation Model
Chapter 5: Attention Mechanisms and Transformers in Vision
Self-Attention Mechanisms in CNNs
Non-local Neural Networks
Introduction to Vision Transformers
ViT Architecture: Patches, Embeddings, Transformer Encoder
Hybrid CNN-Transformer Models
Comparing CNNs and Transformers for Vision Tasks
Implementing Attention Blocks in CNNs Practice
Chapter 6: Advanced Transfer Learning and Domain Adaptation
Revisiting Transfer Learning Strategies
Fine-tuning vs. Feature Extraction: Advanced Considerations
Adapting Models to Different Data Distributions
Domain Generalization Concepts
Few-Shot Learning with CNNs
Self-Supervised Learning Pre-training for Vision
Hands-on Practical: Fine-tuning Models on Specialized Datasets
Chapter 7: Generative Adversarial Networks for Image Synthesis
GAN Fundamentals Revisited
Challenges in Training GANs
Deep Convolutional GANs (DCGANs)
Conditional GANs for Controlled Generation
StyleGAN Architecture and Style-Based Generation
Evaluation Metrics for GANs
Implementing a DCGAN for Image Generation Practice
Chapter 8: Model Compression and Efficient Deep Learning
Motivation for Efficient Models
Network Pruning Techniques
Knowledge Distillation Methods
Quantization: Reducing Model Precision
Designing Efficient Architectures
Neural Architecture Search Overview
Hands-on Practical: Applying Pruning and Quantization
Non-Maximum Suppression Variants
Was this section helpful?
- Soft-NMS -- Improving Object Detection With One Line of Code, Navaneeth Bodla, Bharat Singh, Rama Chellappa, Larry S. Davis, 2017 Proceedings of the IEEE International Conference on Computer Vision (ICCV) DOI: 10.48550/arXiv.1704.04503 - Introduces the Soft-NMS algorithm, which decays scores of overlapping boxes instead of removing them, improving recall in dense scenes.
- Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression, Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, Dongwei Ren, 2020 Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Vol. 34 DOI: 10.48550/arXiv.1911.08287 - Proposes the DIoU and CIoU losses, and introduces DIoU-NMS which incorporates center distance into the suppression criterion.
- YOLACT: Real-time Instance Segmentation, Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee, 2019 Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) DOI: 10.1109/ICCV.2019.00913 - Introduces Matrix NMS, a parallelized NMS method used in the YOLACT instance segmentation model for faster post-processing.