Example: confidence
Search results with tag "Adversar"
Generative Adversarial Nets - NIPS
papers.nips.ccGenerative adversarial networks has been sometimes confused with the related concept of “adversar-ial examples” [28]. Adversarial examples are examples found by using gradient-based optimization directly on the input to a classification network, in order to find examples that are similar to the data yet misclassified.
CCNet: Criss-Cross Attention for Semantic Segmentation
openaccess.thecvf.comMRF, for semantic segmentation. AAF [19] used adversar-ial learning to capture and match the semantic relations be-tween neighboring pixels in the label space. BiSeNet [35] was designed for real-time semantic segmentation. Contextual information aggregation In addition, some works aggregate the contextual information to augment the ...