Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics
This work addresses the problem of making web images accessible to BLV users by highlighting flaws in existing evaluation metrics, which is incremental but crucial for guiding AI systems toward better accessibility.
The paper argues that current referenceless metrics for evaluating image descriptions fail to align with the needs of blind and low vision (BLV) users because they ignore context, which is highly valued by BLV users, and presents a study with BLV participants showing this inadequacy, along with a contextual version of CLIPScore as a proof-of-concept.
Few images on the Web receive alt-text descriptions that would make them accessible to blind and low vision (BLV) users. Image-based NLG systems have progressed to the point where they can begin to address this persistent societal problem, but these systems will not be fully successful unless we evaluate them on metrics that guide their development correctly. Here, we argue against current referenceless metrics -- those that don't rely on human-generated ground-truth descriptions -- on the grounds that they do not align with the needs of BLV users. The fundamental shortcoming of these metrics is that they do not take context into account, whereas contextual information is highly valued by BLV users. To substantiate these claims, we present a study with BLV participants who rated descriptions along a variety of dimensions. An in-depth analysis reveals that the lack of context-awareness makes current referenceless metrics inadequate for advancing image accessibility. As a proof-of-concept, we provide a contextual version of the referenceless metric CLIPScore which begins to address the disconnect to the BLV data. An accessible HTML version of this paper is available at https://elisakreiss.github.io/contextual-description-evaluation/paper/reflessmetrics.html