Random Forest with Learned Representations for Semantic Segmentation
This work addresses the need for efficient semantic segmentation in applications like hand-object interaction, though it appears incremental by extending random forests with learned representations.
The paper tackles the problem of semantic segmentation by proposing a random forest framework that learns flexible filters for feature representation, achieving real-time performance with limited computational and memory resources.
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.