supervised 썸네일형 리스트형 DINO : Emerging Properties in Self-Supervised Vision Transformers https://arxiv.org/abs/2104.14294 Emerging Properties in Self-Supervised Vision Transformers In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this architecture works partic arxiv.org CVPR 2021 self-supervised learning이 ViT.. 더보기 ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation [2211.12455] ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation (arxiv.org) 2022.11 arxiv 논문 CAM을 WSSS task에 많이 이용, but segmentation에서 조금 낮은 효율 ⇒ encoder-decoder based segmentation 모델을 변형하 iterative approach 제시 ground-truth segmentation label 주어지지 않음 ⇒ pseudo-segmentation label 생성 Motivation CAM을 WSSS application에 이용하면서 나타나는 2가지 이슈(이 논문에서 중점적으로 발전시킨 부분) classification model 에.. 더보기 이전 1 다음
