Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Gaze Meets ML

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

Christian Koevesdi · Vasha DuTell · Anne Harrington · Mark Hamilton · Bill Freeman · Ruth Rosenholtz

Keywords: [ multi-scale pyramid ] [ texture synthesis ] [ statistic selection ] [ contrastive learning ] [ Peripheral vision ]


Abstract:

Peripheral vision plays an important role in human vision, directing where and when tomake 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 stillinsufficient to capture a wide variety of textures. To develop a more principled approach tostatistic selection for texture-based models of peripheral vision, we develop a self-supervisedmachine 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 alarge 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 statisticsare already known. We then use StatTexNet to determine the most and least importantstatistics for natural (non-depleted) texture images using weight interpretability metrics,finding these to be consistent with previous psychophysical studies. Finally, we demonstratethat textures are most effectively synthesized with the statistics identified as important;we see noticeable deterioration when excluding the most important statistics, but minimaleffects when excluding least important. Overall, we develop a machine learning method ofselecting statistics that can be used to create better peripheral vision models. With thesebetter models, we can more effectively understand the effects of peripheral vision in humangaze.

Chat is not available.