Swin Transformer: Hierarchical Vision Transformer using Shifted Windows — HN submission

Sun, 09 Apr 2023 16:12:18 GMT

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

48 points; 19 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows — mentioned by mrintellectual

Wed, 13 Apr 2022 18:33:22 GMT

> ViT models are outperforming CNNs in terms of computational efficiency and accuracy, achieving highly competitive performance in tasks like image classification, object detection, and semantic image segmentation. Since then, this has been show to be untrue. Using more modern training techniques along with depthwise convolutions (https://arxiv.org/abs/2201.03545) results in equal if not better performance on vision tasks. Improved training methodologies have also been shown to boost the accuracy of ResNet50 - an 6-year-old pure convolutional architecture - on ImageNet-1k by over 5%…

Paper and discussion history. A mention is not an endorsement.

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows · HackerPapers discussions

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows — HN submission

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows — mentioned by mrintellectual