Summaries on paper contributions

Annotated Papers and Summaries for EN4583 - Advances in Machine Vision at the University of Moratuwa, Sri Lanka [Restricted for access tentatively]

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

• Generative Adversarial Nets

• ADAM: A Method for Stochastic Optimization

• FaceNet: A Unified Embedding for Face Recognition and Clustering

• Deep Residual Learning for Image Recognition

• U-Net: Convolutional Networks for Biomedical Image Segmentation

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

• You Only Look Once: Unified, Real-Time Object Detection

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

• Attention is all you need

• A simple framework for contrastive learning of visual representations

• Learning transferable visual models from natural language supervision

• Masked autoencoders are scalable vision learners

• Image-to-image translation with conditional adversarial networks

• BERT: Pre-training of deep bidirectional transformers for language understanding

• Mask R-CNN

• Learning to compare: Relation network for few-shot learning

• An image is worth 16x16 words: Transformers for image recognition at scale

• Restormer: Efficient transformer for high-resolution image restoration

• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

• Nerf: Representing scenes as neural radiance fields for view synthesis

• High-resolution image synthesis with latent diffusion models

• Singan: Learning a generative model from a single natural image

• VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

• Generating natural adversarial examples

• Point-GNN: Graph neural network for 3D object detection in a point cloud [Slides]

• Language models are few-shot learners