This repository catalogs a year-long learning journey focused on computer vision and deep learning. Each day covers a specific paper or model architecture, including object detection frameworks (EfficientDet, YOLO, DETR), segmentation networks (UNet, SegNet, DeconvNet), transformer architectures (ViT, DeiT), and visualization techniques. The posts reference top ML/CV venues like CVPR, ICCV, ECCV, and ICLR.