视觉生成AI的交叉分析:稳定扩散的情况
Petra Jääskeläinen1, Nickhil Kumar Sharma2,3, Helen Pallett2
1Division of Media Technology and Interaction Design, Department of Human-Centered Technology, EECS, KTH Royal Institute of Technology, Stockholm, Sweden.
概括
像稳定扩散这样的视觉生成人工智能 (vGenAI) 工具通过反映社会权力结构来延续有害的偏见,包括种族主义和性别歧视. 这项研究要求对vGenAI的开发和部署采取社会正义的方法.
科学领域:
- 计算机科学
- 社会学
- 媒体研究
背景情况:
- 视觉生成人工智能 (vGenAI) 工具正在迅速被采用,用于创建现实的图像.
- 这些技术可以反映和延续社会偏见和权力结构.
- 稳定扩散 (SD) 是一个突出的开源vGenAI工具,需要进行批判性检查.
研究的目的:
- 批判性地分析稳定扩散 (SD) 产生的图像中的美学和潜在的动力系统.
- 调查SD如何延续种族主义,性别歧视和殖民主义等社会不平等.
- 为vGenAI发展提出以社会正义为导向的方法.
主要方法:
- 对180个SD生成图像进行视觉和交叉分析.
- 在女权主义的科学和技术研究,视觉媒体研究和批判理论的基础上.
- 检查美学,机构背景和电力系统的交叉点.
主要成果:
- SD的形象延续了性别歧视,种族主义,异性规范,
- 产生的图像通常会默认为白色,有能力的,男性的表现.
- 发现了以欧洲和北美为中心的文化代表的趋势.
结论:
- 像SD这样的vGenAI工具在文化或美学上并不中立.
- 通过这些技术不断重现有害和暴力的图像.
- 需要一个以社会正义为导向的补偿性方法来解决vGenAI的伤害.
相关概念视频
Diffusion
4.9K
Diffusion is a type of passive transport. In passive transport, a substance tends to move from an area of high concentration to an area of low concentration until the concentration is equal across the space. For example, take the diffusion of substances through the air. When someone opens a perfume bottle in a room filled with people, the perfume is at its highest concentration in the bottle and is at its lowest at the edges of the room. The perfume vapor will diffuse, or spread away, from the...
4.9K
Multi-input and Multi-variable systems
149
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
In the absence...
149
Convolution: Math, Graphics, and Discrete Signals
396
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
396
Modeling and Similitude
328
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
328
Genetic Drift
40.6K
Natural selection—probably the most well-known evolutionary mechanism—increases the prevalence of traits that enhance survival and reproduction. However, evolution does not merely propagate favorable traits, nor does it always benefit populations.
40.6K
Forced Transdifferentiation
2.0K
Transdifferentiation, also known as lineage reprogramming, was first discovered by Selman and Kafatos in 1974 in silkmoths. They observed that the moths’ cuticle-producing cells transformed into salt-producing cells. Many such cases of natural transdifferentiation occur in organisms. In humans, pancreatic alpha cells can become beta cells. In newts, the loss of the eye’s lens causes the pigmented epithelial cells to transdifferentiate into the lens cells.
Artificial...
Artificial...
2.0K


