Our extension: telling the model where to look
AFT never says where the saliency should go. We added a training term that does. It measures the share of the saliency map that falls inside the object's outline, and the Energy Pointing Game loss is one minus that share.
The term needs object outlines, so we train on COCO. It takes the gradient of a gradient, so each step runs 1.27 times as long. Applied from the start, training doesn't converge. As a 2,000-step stage on top of a finished AFT model it works, and its weight becomes a dial.
Grad-ECLIP, a saliency method the loss never sees, improves at every step too, which points to a change in the encoder itself. On skin-lesion images the Simple Gradient pointing game rises from 0.428 with AFT to 0.820 at ws = 0.6. In theory the term shifts the model's sensitivity from the background to the object, and a background-only attack agrees. Plain AFT reacts 1.25 to 1.29 times more to background pixels than to object pixels. The new term brings that ratio down to 0.68 at the highest weight, though part of that drop may come from the COCO training itself.
Deletion and insertion tests, and a test of whether the map follows the prompt, don't improve consistently with the weight. The clearest gain is in foreground alignment.