MSB-VQA:克服多个来源的偏见,以获得强大的视觉问题答案
Jingliang Gu1, Xingjie Zhuang1, Zhixin Li1
1Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, 541004, China; Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, 541004, China.
概括
本研究介绍了MSB-VQA,这是一种减少视觉问题答案 (VQA) 模型偏差的新方法. 它有效地减轻了多式联运快捷方式和分布偏差,改善了对具有挑战性的数据集的模型性能.
科学领域:
- 人工智能的人工智能
- 计算机视觉 计算机视觉
- 自然语言处理自然语言处理.
背景情况:
- 许多视觉问题答案 (VQA) 模型表现出偏见,阻碍了他们与多式联络信息推理的能力.
- 现有的偏差缓解技术往往只关注语言偏差,并产生不满意的结果.
- 在标准VQA数据集上表现出色的模型在偏差敏感的VQA-CP数据集上失败.
研究的目的:
- 提出一种新的方法,MSB-VQA,全面针对VQA模型中的各种偏差来源.
- 通过解决多式联网捷径和分布偏差,增强VQA模型的稳定性和推理能力.
- 在不依赖于数据平衡或增量的情况下,实现显著的偏差减少.
主要方法:
- 使用生成对抗网络和知识蒸开发了一个偏差检测器,以模拟偏差形成并消除多式联网捷径偏差.
- 实施了带有自适应角边际损失和监督对比损失的共弦值分类器,以对抗来自不均样本分布的分布偏差.
- 来自共因分类器和基本模型的融合预测,以平衡分布式 (ID) 和分布式 (OOD) 之外的数据集的性能.
主要成果:
- 拟议的MSB-VQA方法在VQA-CPv2,VQAv2和VQA-CE数据集的偏差减少方面显著优于现有的方法.
- 证明有效地减轻多式联运捷径和分配偏差.
- 在不使用数据平衡或增强技术的情况下实现了卓越的性能.
结论:
- 在开发公正和强大的VQA模型方面,MSB-VQA提供了显著的进步.
- 该方法有效地解决了复杂的偏见,从而提高了各种VQA基准的性能.
- 这种方法为未来研究可靠的多式联络人工智能提供了有希望的方向.
相关概念视频
01:31Confirmation Biases
7.2K
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
7.2K
01:12Hindsight Biases
3.9K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now?
3.9K
01:25The Anchoring-and-Adjustment Heuristic
7.4K
In order to make good decisions, we use our knowledge and our reasoning. Often, this knowledge and reasoning is sound and solid. However, sometimes, we are swayed by biases or by others manipulating a situation. For example, let’s say you and three friends wanted to rent a house and had a combined target budget of $1,600. The realtor shows you only very run-down houses for $1,600 and then shows you a very nice house for $2,000. Might you ask each person to pay more in rent to get the...
7.4K
01:25Strategies for Assessing and Addressing Confounding
155
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
155
02:13The Representativeness Heuristic
16.2K
The representative heuristic describes a biased way of thinking, in which you unintentionally stereotype someone or something. For example, you may assume that your professors spend their free time reading books and engaging in intellectual conversation, because the idea of them spending their time playing volleyball or visiting an amusement park does not fit in with your stereotypes of professors.
16.2K
01:22Multi-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