Example: confidence
Search results with tag "For unsupervised"
Richer Convolutional Features for Edge Detection
openaccess.thecvf.comfied framework that can be potentially generalized to other vision tasks. By carefully designing a universal strategy to ... for the extraction of visually significant edges and bound-aries. [39,53] presented zero-crossing theory based algo- ... proposed a complex model for unsupervised learn-ing of edge detection, but the performance is ...
Momentum Contrast for Unsupervised Visual Representation ...
openaccess.thecvf.comUnsupervised representation learning is highly success-ful in natural language processing, e.g., as shown by GPT [50, 51] and BERT [12]. But supervised pre-training is still dominant in computer vision, where unsupervised meth-ods generally lag behind. The reason may stem from dif-ferences in their respective signal spaces. Language tasks