人与机器之间的行为差异在视觉处理的早期就会出现
Thomas Klein1,2,3, Wieland Brendel1,4,5,6, Felix A Wichmann2,7
1Max-Planck-Institute for Intelligent Systems, Tübingen, Germany.
Journal of vision
|February 17, 2026
概括
深度神经网络 (DNN) 显示的错误模式不同于人类,即使是简短的图像呈现. 这表明早期视觉处理的根本差异,而不仅仅是以后的认知偏见.
科学领域:
- 计算神经科学是一种计算神经科学.
- 认知科学是一种认知科学.
- 计算机视觉 计算机视觉 计算机视觉
背景情况:
- 深度神经网络 (DNN) 擅长预测灵长类动物视觉皮层中的神经活动.
- 然而,心理物理研究揭示了在图像识别任务中,DNN和人类观察者之间的行为差异.
- 错误一致性 (EC) 突出了DNN和人类对图像难度的不同看法.
研究的目的:
- 调查DNN和人类之间的错误一致性 (EC) 差异是否来自后期视觉处理.
- 测试早期视觉表现相似的假设,以后的认知因素驱动行为分歧.
- 为了确定呈现时间是否会影响EC中观察到的差异.
主要方法:
- 系统变化刺激呈现时间 (8.3到267毫秒) 对于背面掩饰的自然图像.
- 测量人类在加快八倍识别任务上的表现.
- 在不同呈现时间段中,对人类性能和DNN之间的错误一致性 (EC) 的量化.
主要成果:
- 错误一致性 (EC) 没有随着呈现时间的缩短而增加,仍然低于先前确定的0.4.4的值.
- 这些发现与EC差异归因于后期处理或观察者特定因素的假设相矛盾.
- 与DNN相比,人类的表现显示出系统的差异,即使在非常短的展示时间内也是如此.
结论:
- 持续的低误差一致性 (EC) 表明DNN和人类视觉系统之间的差异不是由于后期的认知影响.
- 这些结果表明DNN与人类视觉系统早期阶段之间的基本处理差异.
- DNN可能不是当前理解的早期人类视觉处理的准确计算模型.
相关概念视频
01:20Parallel Processing
791
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
791
01:26Visual System
1.9K
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
1.9K