A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented, which breaks down the complex problem of scene understanding by rapidly selecting conspicuous locations to be analyzed in detail.
Five important trends have emerged from recent work on computational models of focal visual attention that emphasize the bottom-up, image-based control of attentional deployment, providing a framework for a computational and neurobiological understanding of visual attention.
It is found that the models designed specifically for salient object detection generally work better than models in closely related areas, which provides a precise definition and suggests an appropriate treatment of this problem that distinguishes it from other problems.
IEEE Transactions on Pattern Analysis and Machine…
2013
TLDR
A taxonomy of nearly 65 models of attention provides a critical comparison of approaches, their capabilities, and shortcomings, and addresses several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing meaningful performance measures.
This work studies KD from a new perspective: rather than compressing models, students are trained parameterized identically to their teachers, and shows significant advantages from transferring knowledge between DenseNets and ResNets in either direction.
This study allows one to assess the state-of-the-art visual saliency modeling, helps to organizing this rapidly growing field, and sets a unified comparison framework for gauging future efforts, similar to the PASCAL VOC challenge in the object recognition and detection domains.
A general-purpose usefulness of the algorithm is suggested in improving compression ratios of unconstrained video, based on a nonlinear integration of low-level visual cues, mimicking processing in primate occipital, and posterior parietal cortex.