.png){kind=icon}
Return
Multi-view and multi-augmentation for self-supervised visual representation learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-023-05163-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the real world, the appearance of identical objects depends on factors as varied as resolution, angle, illumination conditions, and viewing perspectives. This suggests that the data augmentation pipeline could benefit downstream tasks by exploring the overall data appearance in a self-supervised framework. Previous work on self-supervised learning that yields outstanding performance relies heavily on data augmentation such as cropping and color distortion. However, most methods use a static data augmentation pipeline, limiting the amount of feature exploration. To generate representations that encompass scale-invariant, explicit information about various semantic features and are invariant to nuisance factors such as relative object location, brightness, and color distortion, we propose the Multi-View, Multi-Augmentation (MVMA) framework. MVMA consists of multiple augmentation pipelines, with each pipeline comprising an assortment of augmentation policies. By refining the baseline self-supervised framework to investigate a broader range of image appearances through modified loss objective functions, MVMA enhances the exploration of image features through diverse data augmentation techniques. Transferring the resultant representation learning using convolutional networks (ConvNets) to downstream tasks yields significant improvements compared to the state-of-the-art DINO across a wide range of vision tasks and classification tasks: +4.1% and +8.8% top-1 on the ImageNet dataset with linear evaluation and k-NN classifier, respectively. Moreover, MVMA achieves a significant improvement of +5% AP(50) and +7% AP(50)(m) on COCO object detection and segmentation.
Keywords:
Multi-augmentation
SSL augmentation pipelines
Data augmentation policies
Nuisance factors
Scale-invariant representation learning
Metric learning
Journal
IF:
3.5
Papers:
7.6K
Citations:
1.7W
Organization
Cited Papers
ShareSaveShareSaveThermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons.png)
Indoor Air
OAAI
Indoor AirIF0
OAAIShareSaveShareSaveShareSaveShareSaveShareSave
View more