Justyn Rodrigues
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Justyn Rodrigues has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Krista A. Ehinger
The University of Melbourne
1 shared publication - Oliver Obst
University of New South Wales (UNSW)
1 shared publication - X. Rosalind Wang
Western Sydney University
1 shared publication
Latest Publications
- Open Access
- 21 October 2025
- Published by IOS Press
- p. 1229-1236
Do Explanations Expose Bias? How Saliency Maps Affect Judgements of Biased Face-Recognition Models
Saliency-map explanations are intended to make computer-vision models more transparent, but it is unclear whether they help people recognise biased behaviour. We conducted a controlled on-line study with 40 participants who compared Layer-wise Relevance Propagation maps from convolutional face-recognition models. A fair model was trained on a balanced synthetic dataset; two biased models were trained on data in which either light- or dark-skinned faces appeared only in frontal pose. Each participant completed 32 comparison trials. When the fair model was paired with the dark-skinned-pose-biased model, selections were near chance (52.8% favouring the fair model, binomial p = .36). When the fair model was paired with the light-skinned-pose-biased model, participants chose the biased model significantly more often (58.1%, p = .005). Confidence ratings varied with condition and did not systematically track model fairness. These results indicate that pixel-level attribution alone does not reliably expose training bias and can, in some settings, mislead non-expert users.
- 21 October 2025
- Published by IOS Press
- p. 1229-1236
Open AccessDo Explanations Expose Bias? How Saliency Maps Affect Judgements of Biased Face-Recognition Models
Saliency-map explanations are intended to make computer-vision models more transparent, but it is unclear whether they help people recognise biased behaviour. We conducted a controlled on-line study with 40 participants who compared Layer-wise Relevance Propagation maps from convolutional face-recognition models. A fair model was trained on a balanced synthetic dataset; two biased models were trained on data in which either light- or dark-skinned faces appeared only in frontal pose. Each participant completed 32 comparison trials. When the fair model was paired with the dark-skinned-pose-biased model, selections were near chance (52.8% favouring the fair model, binomial p = .36). When the fair model was paired with the light-skinned-pose-biased model, participants chose the biased model significantly more often (58.1%, p = .005). Confidence ratings varied with condition and did not systematically track model fairness. These results indicate that pixel-level attribution alone does not reliably expose training bias and can, in some settings, mislead non-expert users.