Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding

TL;DR

This paper introduces an enhanced random forest approach for image understanding that incorporates image and patch-level feedback to improve codebook discriminativeness, leading to better performance in scene classification tasks.

Contribution

It proposes a novel feedback scheme that updates the RF codebook using soft class labels from pLSA, combining image and patch-level information for improved discriminative power.

Findings

Improved accuracy on 15-Scene and C-Pascal datasets.

Effective integration of image and patch-level feedback.

Enhanced discriminative capability of the RF codebook.

Abstract

Image understanding is an important research domain in the computer vision due to its wide real-world applications. For an image understanding framework that uses the Bag-of-Words model representation, the visual codebook is an essential part. Random forest (RF) as a tree-structure discriminative codebook has been a popular choice. However, the performance of the RF can be degraded if the local patch labels are poorly assigned. In this paper, we tackle this problem by a novel way to update the RF codebook learning for a more discriminative codebook with the introduction of the soft class labels, estimated from the pLSA model based on a feedback scheme. The feedback scheme is performed on both the image and patch levels respectively, which is in contrast to the state- of-the-art RF codebook learning that focused on either image or patch level only. Experiments on 15-Scene and C-Pascal datasets had shown the effectiveness of the proposed method in image understanding task.