VisAlign: Dataset for Measuring the Degree of Alignment between AI and Humans in Visual Perception

by   Jiyoung Lee, et al.

AI alignment refers to models acting towards human-intended goals, preferences, or ethical principles. Given that most large-scale deep learning models act as black boxes and cannot be manually controlled, analyzing the similarity between models and humans can be a proxy measure for ensuring AI safety. In this paper, we focus on the models' visual perception alignment with humans, further referred to as AI-human visual alignment. Specifically, we propose a new dataset for measuring AI-human visual alignment in terms of image classification, a fundamental task in machine perception. In order to evaluate AI-human visual alignment, a dataset should encompass samples with various scenarios that may arise in the real world and have gold human perception labels. Our dataset consists of three groups of samples, namely Must-Act (i.e., Must-Classify), Must-Abstain, and Uncertain, based on the quantity and clarity of visual information in an image and further divided into eight categories. All samples have a gold human perception label; even Uncertain (severely blurry) sample labels were obtained via crowd-sourcing. The validity of our dataset is verified by sampling theory, statistical theories related to survey design, and experts in the related fields. Using our dataset, we analyze the visual alignment and reliability of five popular visual perception models and seven abstention methods. Our code and data is available at <>.


Human Uncertainty in Concept-Based AI Systems

Placing a human in the loop may abate the risks of deploying AI systems ...

CNNs and Transformers Perceive Hybrid Images Similar to Humans

Hybrid images is a technique to generate images with two interpretations...

AI Alignment Dialogues: An Interactive Approach to AI Alignment in Support Agents

AI alignment is about ensuring AI systems only pursue goals and activiti...

Exploring Alignment of Representations with Human Perception

We argue that a valuable perspective on when a model learns good represe...

Making a Bird AI Expert Work for You and Me

As powerful as fine-grained visual classification (FGVC) is, responding ...

StructChart: Perception, Structuring, Reasoning for Visual Chart Understanding

Charts are common in literature across different scientific fields, conv...

Measuring uncertainty in human visual segmentation

Segmenting visual stimuli into distinct groups of features and visual ob...

Please sign up or login with your details

Forgot password? Click here to reset