Neural and computational mechanisms underlying robust object recognition

鲁棒物体识别背后的神经和计算机制

• 批准号: 10682285
• 负责人: FRANK TONG
• 金额: $ 41.15万
• 依托单位: VANDERBILT UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-01 至 2027-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10682285
• 关键词: Animals; Architecture; Automobile Driving; Behavioral; Brain; Brain Diseases; Brain Injuries; Brain Neoplasms; Classification; Computer Vision Systems; Craniocerebral Trauma; Data; Development; Disease; Evaluation; Eye; Face; Functional Magnetic Resonance Imaging; Future; Goals; Human; Image; Inherited; Knowledge; Learning; Macaca; Mediating; Medical Imaging; Methods; Modeling; Nature; Neural Network Simulation; Neurodevelopmental Disorder; Neurons; Noise; Perceptual learning; Performance; Persons; Positioning Attribute; Protocols documentation; Psychophysics; Recurrence; Regimen; Research; Resolution; Role; Sampling; Shapes; Stimulus; Stroke; Training; Vision; Vision Disorders; Visual; Visual Cortex; Visual Pathways; Visual System; Work; base; cognitive neuroscience; computational neuroscience; deep neural network; design; experience; experimental study; flexibility; human model; image processing; improved; inferotemporal cortex; nervous system disorder; neural; neural network architecture; object recognition; predictive modeling; response; visual neuroscience; visual stimulus; Animals; Architecture; Automobile Driving; Behavioral; Brain; Brain Diseases; Brain Injuries; Brain Neoplasms; Classification; Computer Vision Systems; Craniocerebral Trauma; Data; Development; Disease; Evaluation; Eye; Face; Functional Magnetic Resonance Imaging; Future; Goals; Human; Image; Inherited; Knowledge; Learning; Macaca; Mediating; Medical Imaging; Methods; Modeling; Nature; Neural Network Simulation; Neurodevelopmental Disorder; Neurons; Noise; Perceptual learning; Performance; Persons; Positioning Attribute; Protocols documentation; Psychophysics; Recurrence; Regimen; Research; Resolution; Role; Sampling; Shapes; Stimulus; Stroke; Training; Vision; Vision Disorders; Visual; Visual Cortex; Visual Pathways; Visual System; Work; base; cognitive neuroscience; computational neuroscience; deep neural network; design; experience; experimental study; flexibility; human model; image processing; improved; inferotemporal cortex; nervous system disorder; neural; neural network architecture; object recognition; predictive modeling; response; visual neuroscience; visual stimulus

Deep neural networks (DNNs) for object classification have been argued to provide the most promising state- of-the-art models of the visual system, accompanied by claims that they have attained or even surpassed human-level performance. However, mounting evidence has revealed that DNNs fail catastrophically when faced with more noisy or degraded viewing conditions. By contrast, the human visual system is far more robust. To better understand and model human vision, one must determine whether the brittle nature of DNN performance arises from flaws in their architectural design, imperfections in their learning protocols, or inadequate sampling of relevant training experiences. This project will investigate the neurocomputational bases of robust object recognition, focusing on challenge conditions of visual noise and blur, to develop new DNN models that can provide a better account of human behavioral and neural responses to object images that will vary from clear to severely degraded. Both feedforward and recurrent DNN architectures will be evaluated, and the critical sets of training experiences needed for DNNs to attain robustness will be determined. In Aim 1, we will evaluate what types of DNNs can adequately predict human behavioral and neural responses to objects embedded in noise on an image-by-image basis. Correspondences between fMRI responses at multiple levels of the human visual pathway will be compared with layer-wise DNN representations to evaluate the goodness of fit for DNN model predictions. In Aim 2, we will determine what types of DNNs can better account for human behavioral and neural responses to blurry object images. We will further explore how training with blurry images modifies the visual representations learned by DNNs, leading to greater robustness to other types of image degradation and greater sensitivity to shape information. In Aim 3, we will investigate whether perceptual training with noisy or blurry objects can allow humans to acquire even greater robustness. We will then determine whether human improvements in behavioral and neural performance can be effectively modeled by DNNs that undergo comparable regimens in visual training. As a whole, this project will lead to the development of powerful new DNN models that provide a better account of human behavioral and neural responses across a wide range of challenging viewing conditions. By developing a better neurocomputational model of the intact human visual system, we will be better positioned to eventually develop models of central visual disorders, which can arise from neurodevelopmental or neurological disorders, stroke, head injury, brain tumors or other diseases. The advancement of more robust, human-like DNNs is also highly relevant to AI applications in computer vision and medical image processing.

已经有人说，用于对象分类的深神经网络（DNN）提供了最有希望的状态 - 视觉系统的艺术模型，伴随着他们已经达到甚至超过的声称 人类水平的表现。但是，越来越多的证据表明，当DNN在 面对更多嘈杂或退化的观看条件。相比之下，人类的视觉系统要多得多 强壮的。为了更好地理解和建模人类的视野，必须确定DNN的脆性是否 性能来自其建筑设计中的缺陷，学习协议中的瑕疵或 相关培训经验的采样不足。该项目将研究神经计算 强大的物体识别基础，专注于视觉噪音和模糊的挑战条件，以发展新的 DNN模型可以更好地说明人类行为和神经对象的反应 这将从清晰到严重的退化。前馈和经常性DNN架构将是 经过评估，DNN达到鲁棒性所需的关键培训经验将是 决定。在AIM 1中，我们将评估哪些类型的DNN可以充分预测人类的行为和 对物体的神经反应以逐图嵌入在噪声中的对象。 fMRI之间的对应关系 将人类视觉途径的多个级别的响应与层的DNN进行比较 评估DNN模型预测拟合优度的表示。在AIM 2中，我们将确定什么 DNN的类型可以更好地说明人类行为和神经对模糊对象图像的反应。我们将 进一步探索模糊图像训练如何修改DNN学到的视觉表示，导致 对其他类型的图像降解和对塑造信息的敏感性更大的鲁棒性。在AIM 3中， 我们将调查具有嘈杂或模糊的对象的感知训练是否可以使人类甚至可以获取 更大的鲁棒性。然后，我们将确定人类在行为和神经方面的改善 性能可以通过在视觉训练中经过可比方案的DNN有效地建模。作为 整体，该项目将导致强大的新DNN模型的发展，以更好地说明 人类的行为和神经反应在广泛的挑战性观察条件下。通过发展 完整的人类视觉系统的更好的神经计算模型，我们将更好地确定最终 开发中央视觉疾病的模型，这可能是由神经发育或神经系统引起的 疾病，中风，头部受伤，脑肿瘤或其他疾病。更坚固，人类的进步 DNNS也与计算机视觉和医疗图像处理中的AI应用高度相关。