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 particularly well, we make the following observations: first, self-supervised ViT features contain explicit information about the semantic segmentation of an image, which does not emerge as clearly with supervised ViTs, nor with convnets. Second, these features are also excellent k-NN classifiers, reaching 78.3% top-1 on ImageNet with a small ViT. Our study also underlines the importance of momentum encoder, multi-crop training, and the use of small patches with ViTs. We implement our findings into a simple self-supervised method, called DINO, which we interpret as a form of self-distillation with no labels. We show the synergy between DINO and ViTs by achieving 80.1% top-1 on ImageNet in linear evaluation with ViT-Base.
Code (32)
Tasks
Copy DetectionImage ClassificationImage RetrievalLinear evaluationSelf-Supervised Image ClassificationSelf-Supervised LearningSemantic SegmentationSingle-object discoveryVideo Object DetectionVideo Object SegmentationVisual Place RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINO
This work conducts the first analysis on the robustness against adversarial attacks on self-supervised Vision Transformers trained using DINO. First, we evaluate whether features learned through self-supervision are more…
Adversarial RobustnessUnderstanding The Robustness in Vision Transformers
Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic u…
Domain GeneralizationImage Classificationobject-detectionObject Detection+1Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?
Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? As a by-product of p…
Image ClassificationImage RetrievalMetric LearningObject Discovery+3HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throug…
Transfer LearningSelf-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals
Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between p…
Autonomous Drivingmotion prediction