# Random Forest with Learned Representations for Semantic Segmentation

## TL;DR

This paper introduces a novel random forest framework that learns flexible feature representations by optimizing weights, shapes, and sparsities, enabling real-time semantic segmentation with limited resources.

## Contribution

It proposes an unconstrained feature representation learning method within a random forest framework for improved semantic segmentation.

## Key findings

- Achieves real-time segmentation performance.
- Effective on hand-object interaction and semantic datasets.
- Uses limited computational and memory resources.

## Abstract

In this work, we present a random forest framework that learns the weights, shapes, and sparsities of feature representations for real-time semantic segmentation. Typical filters (kernels) have predetermined shapes and sparsities and learn only weights. A few feature extraction methods fix weights and learn only shapes and sparsities. These predetermined constraints restrict learning and extracting optimal features. To overcome this limitation, we propose an unconstrained representation that is able to extract optimal features by learning weights, shapes, and sparsities. We, then, present the random forest framework that learns the flexible filters using an iterative optimization algorithm and segments input images using the learned representations. We demonstrate the effectiveness of the proposed method using a hand segmentation dataset for hand-object interaction and using two semantic segmentation datasets. The results show that the proposed method achieves real-time semantic segmentation using limited computational and memory resources.