Measuring uncertainty in human visual segmentation

Abstract

Segmenting visual stimuli into distinct groups of features and visual objects is central to visual function. Classical psychophysical methods have helped uncover many rules of human perceptual segmentation, and recent progress in machine learning has produced successful algorithms. Yet, the computational logic of human segmentation remains unclear, partially because we lack well-controlled paradigms to measure perceptual segmentation maps and compare models quantitatively. Here we propose a new, integrated approach: given an image, we measure multiple pixel-based same–different judgments and perform model–based reconstruction of the underlying segmentation map. The reconstruction is robust to several experimental manipulations and captures the variability of individual participants. We demonstrate the validity of the approach on human segmentation of natural images and composite textures. We show that image uncertainty affects measured human variability, and it influences how participants weigh different visual features. Because any putative segmentation algorithm can be inserted to perform the reconstruction, our paradigm affords quantitative tests of theories of perception as well as new benchmarks for segmentation algorithms.

Scaling Painting Style Transfer

“…formulated style transfer as an optimization problem minimizing the distances between Gram matrices of VGG features [GEB16]. Other global statistics have been proven effective for style transfer and texture synthesis such as deep correlations [SC17; GGL22], Bures metric [VDKC20], spatial mean of features [LZW16; DDD*21], feature histograms [RWB17], or even the full feature distributions [HVCB21]. Specific cost function corrections have also been proposed for photorealistic style transfer [LPSB17].…”

“…NST is performed by optimizing a functional aiming at a compromise between fidelity to VGG19 features of the content image while reproducing the Gram matrices statistics of the style image. Other global statistics have been proven effective for style transfer and texture synthesis [LZW16; SC17; LPSB17; VDKC20; RWB17; HVCB21; DDD*21; GGL22] and it has been shown that a coarse‐to‐fine multiscale approach allows one to reproduce different levels of style detail for images of moderate to high‐resolution (HR) [GEB*17; Sne17; GGL22]. The two major drawbacks of such optimization‐based NST are the computation time and the limited resolution of images because of large GPU memory requirements.…”