Adaptive Nonparametric Image Parsing

TL;DR

This paper introduces an adaptive nonparametric method for image parsing that dynamically determines the optimal number of neighbors for each test image, improving pixel annotation accuracy through local retrieval and contextual smoothing.

Contribution

It proposes a novel adaptive approach to nonparametric image parsing that automatically selects the best k for each test image, enhancing label prediction accuracy.

Findings

Outperforms state-of-the-art nonparametric methods on challenging datasets.

Adaptive k selection improves pixel label accuracy.

Contextual smoothing further refines parsing results.

Abstract

In this paper, we present an adaptive nonparametric solution to the image parsing task, namely annotating each image pixel with its corresponding category label. For a given test image, first, a locality-aware retrieval set is extracted from the training data based on super-pixel matching similarities, which are augmented with feature extraction for better differentiation of local super-pixels. Then, the category of each super-pixel is initialized by the majority vote of the $k$-nearest-neighbor super-pixels in the retrieval set. Instead of fixing $k$ as in traditional non-parametric approaches, here we propose a novel adaptive nonparametric approach which determines the sample-specific k for each test image. In particular, $k$ is adaptively set to be the number of the fewest nearest super-pixels which the images in the retrieval set can use to get the best category prediction. Finally, the initial super-pixel labels are further refined by contextual smoothing. Extensive experiments on challenging datasets demonstrate the superiority of the new solution over other state-of-the-art nonparametric solutions.