This paper describes Guided Search 6.0 (GS6), a revised model of visual search. When we encounter a scene, we can see something everywhere. However, we cannot recognize more than a few items at a time. Attention is used to select items so that their features can be “bound” into recognizable objects.

In GS6, this guidance comes from five sources of preattentive information: (1) top-down and (2) bottom-up feature guidance, (3) prior history (e.g., priming), (4) reward, and (5) scene syntax and semantics. These sources are combined into a spatial priority map, a dynamic attentional landscape that evolves over the course of search.

所以Guided Policy Search方法将策略搜索方法分成两个相，控制相和监督相。 其中控制相通过 轨迹最优 、传统控制器或 随机最优控制 产生好的数据。 监督相，是利用从控制相产生的好数据进行监督学习。

Guided search (GS) is a model of human visual search performance, specifically of search tasks in which an observer looks for a target object among some number of distracting items. Classically, models have described two mechanisms of search: serial and parallel (Egeth, 1966).

引导搜索模型 [1] 和相似性理论模型以及特征整合理论模型都属于 视觉 搜索的理论模型。 引导搜索模型假设联合特征搜索是系列的而不是随机的，每一时刻注意的探照灯都在运动，指向与平行加工结果指向的可能目标位置，连续的平行加工结果信息更新使随后的系列加工最终找到目标区域。 由Cave和Wolfe [1] 作为特征整合理论模型的修订而提出的，该理论认为，视觉搜索也包括两个阶段：平行加工阶段和系列加工阶段。 由于激活值来自于平行加工阶段，即第二阶段系列加工 …

2024年1月23日 · 我们提出的显示，搜索和告诉Search and Tell（SEAL）框架是一个通用的元架构MLLM。它由VQA LLM和视觉搜索模型组成，通过视觉工作记忆（VWM）进行协作和交互。SEAL框架的图示如图3所示。

Guided Search 2.0 (GS2) is a revision of the model in which virtually all aspects of the model have been made more explicit and/or revised in light of new data. The paper is organized into four parts: Part 1 presents the model and the details of its computer simulation.

This paper describes Guided Search 6.0 (GS6), a revised model of visual search. When we encounter a scene, we can see something everywhere. However, we cannot recognize more than a few items at a time. Attention is used to select items so that their features can be ‘bound’ into recognizable objects.

Accordingly, I have called the present model Guided Search 2.0 (GS2) to denote what I hope is a substantial upgrade ofthe original Guided Search model (GS1). In the first part of the paper, the GS2 model will be described. The details of the simulation and choices that must be made about parameters are also described. Part 1

Guided search is a mechanism that controls and optimizes the deployment of attention during visual search and allows one to pay attention only to highly relevant items. For instance, when searching … Expand