The human visual system processes images with varied degrees of resolution, with the fovea, a small portion of the retina, capturing the highest acuity region, which gradually declines toward the field of view's periphery. However, the majority of existing object localization methods rely on images acquired by image sensors with space-invariant resolution, ignoring biological attention mechanisms. As a region of interest pooling, this study employs a fixation prediction model that emulates human objective-guided attention of searching for a given class in an image. The foveated pictures at each fixation point are then classified to determine whether the target is present or absent in the scene. Throughout this two-stage pipeline method, we investigate the varying results obtained by utilizing high-level or panoptic features and provide a ground-truth label function for fixation sequences that is smoother, considering in a better way the spatial structure of the problem. Finally, we present a novel dual task model capable of performing fixation prediction and detection simultaneously, allowing knowledge transfer between the two tasks. We conclude that, due to the complementary nature of both tasks, the training process benefited from the sharing of knowledge, resulting in an improvement in performance when compared to the previous approach's baseline scores.

翻译：人类视觉系统以不同分辨率处理图像，其中视网膜的一小部分——中央凹——捕获最高敏锐度的区域，而这一敏锐度向视野外围逐渐递减。然而，现有的大多数目标定位方法依赖于具有空间不变分辨率的图像传感器获取的图像，忽略了生物注意力机制。本研究采用一种模拟人类目标导向注意力的注视预测模型作为感兴趣区域池化方法，用于在图像中搜索特定类别。随后，对每个注视点的中央凹图像进行分类，以判断场景中是否存在目标。通过这一两阶段流程方法，我们探究了利用高层特征或全景特征所获得的不同结果，并提供了一种更平滑的注视序列真实标签函数，该函数能更好地考虑问题的空间结构。最后，我们提出了一种新颖的双任务模型，能够同时执行注视预测与目标检测，从而实现两个任务之间的知识迁移。我们得出结论，由于这两个任务具有互补性，训练过程受益于知识共享，与先前方法的基线分数相比，性能得到了提升。