StatTexNet: Evaluating the Importance of Statistical Parameters for Pyramid-Based Texture and Peripheral Vision Models

Christian Koevesdi, Vasha DuTell, Anne Harrington, Mark Hamilton, William T. Freeman, Ruth Rosenholtz
Proceedings of The 2nd Gaze Meets ML workshop, PMLR 226:90-106, 2024.

Abstract

Peripheral vision plays an important role in human vision, directing where and when to make saccades. Although human behavior in the periphery is well-predicted by pyramid- based texture models, these approaches rely on hand-picked image statistics that are still insufficient to capture a wide variety of textures. To develop a more principled approach to statistic selection for texture-based models of peripheral vision, we develop a self-supervised machine learning model to determine what set of statistics are most important for repre- senting texture. Our model, which we call StatTexNet, uses contrastive learning to take a large set of statistics and compress them to a smaller set that best represents texture fami- lies. We validate our method using depleted texture images where the constituent statistics are already known. We then use StatTexNet to determine the most and least important statistics for natural (non-depleted) texture images using weight interpretability metrics, finding these to be consistent with previous psychophysical studies. Finally, we demonstrate that textures are most effectively synthesized with the statistics identified as important; we see noticeable deterioration when excluding the most important statistics, but minimal effects when excluding least important. Overall, we develop a machine learning method of selecting statistics that can be used to create better peripheral vision models. With these better models, we can more effectively understand the effects of peripheral vision in human gaze.

Cite this Paper


BibTeX
@InProceedings{pmlr-v226-koevesdi24a, title = {StatTexNet: Evaluating the Importance of Statistical Parameters for Pyramid-Based Texture and Peripheral Vision Models}, author = {Koevesdi, Christian and DuTell, Vasha and Harrington, Anne and Hamilton, Mark and Freeman, William T. and Rosenholtz, Ruth}, booktitle = {Proceedings of The 2nd Gaze Meets ML workshop}, pages = {90--106}, year = {2024}, editor = {Madu Blessing, Amarachi and Wu, Joy and Zanca, Dario and Krupinski, Elizabeth and Kashyap, Satyananda and Karargyris, Alexandros}, volume = {226}, series = {Proceedings of Machine Learning Research}, month = {16 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v226/koevesdi24a/koevesdi24a.pdf}, url = {https://proceedings.mlr.press/v226/koevesdi24a.html}, abstract = {Peripheral vision plays an important role in human vision, directing where and when to make saccades. Although human behavior in the periphery is well-predicted by pyramid- based texture models, these approaches rely on hand-picked image statistics that are still insufficient to capture a wide variety of textures. To develop a more principled approach to statistic selection for texture-based models of peripheral vision, we develop a self-supervised machine learning model to determine what set of statistics are most important for repre- senting texture. Our model, which we call StatTexNet, uses contrastive learning to take a large set of statistics and compress them to a smaller set that best represents texture fami- lies. We validate our method using depleted texture images where the constituent statistics are already known. We then use StatTexNet to determine the most and least important statistics for natural (non-depleted) texture images using weight interpretability metrics, finding these to be consistent with previous psychophysical studies. Finally, we demonstrate that textures are most effectively synthesized with the statistics identified as important; we see noticeable deterioration when excluding the most important statistics, but minimal effects when excluding least important. Overall, we develop a machine learning method of selecting statistics that can be used to create better peripheral vision models. With these better models, we can more effectively understand the effects of peripheral vision in human gaze.} }
Endnote
%0 Conference Paper %T StatTexNet: Evaluating the Importance of Statistical Parameters for Pyramid-Based Texture and Peripheral Vision Models %A Christian Koevesdi %A Vasha DuTell %A Anne Harrington %A Mark Hamilton %A William T. Freeman %A Ruth Rosenholtz %B Proceedings of The 2nd Gaze Meets ML workshop %C Proceedings of Machine Learning Research %D 2024 %E Amarachi Madu Blessing %E Joy Wu %E Dario Zanca %E Elizabeth Krupinski %E Satyananda Kashyap %E Alexandros Karargyris %F pmlr-v226-koevesdi24a %I PMLR %P 90--106 %U https://proceedings.mlr.press/v226/koevesdi24a.html %V 226 %X Peripheral vision plays an important role in human vision, directing where and when to make saccades. Although human behavior in the periphery is well-predicted by pyramid- based texture models, these approaches rely on hand-picked image statistics that are still insufficient to capture a wide variety of textures. To develop a more principled approach to statistic selection for texture-based models of peripheral vision, we develop a self-supervised machine learning model to determine what set of statistics are most important for repre- senting texture. Our model, which we call StatTexNet, uses contrastive learning to take a large set of statistics and compress them to a smaller set that best represents texture fami- lies. We validate our method using depleted texture images where the constituent statistics are already known. We then use StatTexNet to determine the most and least important statistics for natural (non-depleted) texture images using weight interpretability metrics, finding these to be consistent with previous psychophysical studies. Finally, we demonstrate that textures are most effectively synthesized with the statistics identified as important; we see noticeable deterioration when excluding the most important statistics, but minimal effects when excluding least important. Overall, we develop a machine learning method of selecting statistics that can be used to create better peripheral vision models. With these better models, we can more effectively understand the effects of peripheral vision in human gaze.
APA
Koevesdi, C., DuTell, V., Harrington, A., Hamilton, M., Freeman, W.T. & Rosenholtz, R.. (2024). StatTexNet: Evaluating the Importance of Statistical Parameters for Pyramid-Based Texture and Peripheral Vision Models. Proceedings of The 2nd Gaze Meets ML workshop, in Proceedings of Machine Learning Research 226:90-106 Available from https://proceedings.mlr.press/v226/koevesdi24a.html.

Related Material