Few-shot & Meta-Learning

• Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning Tutorial

• Prototypical Networks for Few-shot Learning

• A Closer Look at Few-shot Classification

• Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

• PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

• Few-Shot Segmentation via Cycle-Consistent Transformer

• Hypercorrelation Squeeze for Few-Shot Segmentation -- Recording

Distribution Shift

• Wild-Time: A Benchmark of in-the-wild Distribution Shift Over Time -- Recording

• Spawrious: A benchmark for fine control of spurious correlation biases

Transformers and ViTs

• Introduction to Transformers from here

• An Image is Worth 16X16 Words

• End-to-End Object Detection with Transformers

• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

• Masked-attention Mask Transformer for Universal Image Segmentation

Generative Modelling:

• Diffusion Models Intro

Classical Computer Vision Study Group:

• Feature Detection - Part I

• Feature Detection - Part II

• Optical Flow

• Projective Geometry - Part I

• Projective Geometry - Part II

Others:

• YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss

• Spectral Metric for Dataset Complexity Assessment