Unsupervised knowledge distillation from a pretrained language model to *itself*, by alternating between its bi- and cross-encoder forms.

Siamese U-Net model with a pre-trained ResNet34 architecture as an encoder for data efficient Change Detection

Siamese U-Net

Deep Active Learning in Remote Sensing for data efficient Change Detection

Trans-Encoder

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

The **Local Relation Network** (**LR-Net**) is a network built with local relation layers which represent a feature image extractor. This feature extractor adaptively determines aggregation weights based on the compositional relationship of local pixel pairs.

Source	Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com

Viet-Anh on Software

What is: Trans-Encoder?

Viet-Anh on Software