Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding
This work addresses a specific bottleneck in image understanding for computer vision applications, but it is incremental as it builds on existing RF and pLSA methods.
The paper tackled the problem of degraded Random Forest performance due to poorly assigned local patch labels by introducing a novel feedback scheme that updates the RF codebook learning with soft class labels from a pLSA model, achieving effectiveness in image understanding tasks on 15-Scene and C-Pascal datasets.
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.