1. Core Vision Tasks

• Image classification
• Object detection (bounding boxes)
• Image segmentation (semantic, instance, panoptic segmentation)
• Image retrieval (metric learning, nearest-neighbor search
• Image description (captioning)
• Image description with visual grounding (phrase grounding)
• Image generation

2. Performance Evaluation

• Classification (Accuracy, Top-k accuracy)
• Detection
• Intersection over Union (IoU)
• Precision, recall
• F1 score
• Average Precision (AP), mAP
• Segmentation
• Mean IoU
• Pixel accuracy
• Retrieval
• Recall@K
• Captioning & grounding
• BLEU, CIDEr, METEOR
• Grounding accuracy (IoU ≥ threshold)

3. Feature Representation

• Hand-crafted features
• Edge detectors (Sobel, Canny), SIFT, HOG
• Learned features
• CNN feature maps
• Patch embeddings
• Multimodal embeddings (vision-language)

4. Models and Architectures

• Fully Connected Networks (FCN)
• Convolutional Neural Networks (CNN)
• AlexNet, VGG, ResNet
• Vision Transformers (ViT)
• Patch tokenization
• Self-attention
• Contrastive Models (CLIP)
• Large Language Models (LLM)
• Token prediction
• Prompting and conditioning
• Vision-Language Models (VLM)
• LLaVA, Qwen-VL
• Cross-attention vs unified token spaces
• Grounded Vision Models
• Grounding DINO
• Open-vocabulary detection

5. Training Paradigms

• Supervised learning
• Self-supervised learning
• Masked image modeling (MAE)
• Weakly supervised learning
• Zero-shot and few-shot learning

6. Loss Functions

• Cross-entropy loss
• Contrastive loss (InfoNCE)
• Focal loss
• IoU-based losses
• Metric learning losses (Triplet loss, Cosine similarity loss)
• Generative losses (Diffusion loss, adversarial loss (GANs))

7. Explainability and Interpretability

• Saliency maps
• Heatmpas (CAM, Grad-CAM, LeGrad)
• Attention visualization
• LogitLens for VLMs

 

Sources:

Stanford CS 231. Deep Learning for CV and Video Lectures

Computer Vision Lectures by Svetlana Lazebnik

Understanding Deep Learning book

and notebooks

Vision-Language Models