Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03,vehicleID),imageclassification(ImageNet,UB200,Oxford-Pet,Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements.

A Rh s s is the attention matrix, where rowirepresents the attention coefficients of each tokenintheinput with respect tothetokeni.

It has been observed that visual classification models often rely mostly on spurious cues such as the image background, which hurts their robustness to distribution changes. To alleviate this shortcoming, we propose to monitor the model's relevancy signal and direct the model to base its prediction on the foregroundobject.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/