Structured Learning of Tree Potentials in CRF for Image Segmentation

Structured Learning of Tree Potentials in CRF for Image Segmentation

We propose a new approach to image segmentation, which exploits the advantages of both conditional random fields (CRFs) and decision trees. In the literature, the potential functions of CRFs are mostly defined as a linear combination of some predefined parametric models, and then, methods, such as structured support vector machines, are applied to learn those linear coefficients. We instead for...

CRF learning with CNN features for image segmentation

Conditional Random Rields (CRF) have been widely applied in image segmentations. While most studies rely on handcrafted features, we here propose to exploit a pre-trained large convolutional neural network (CNN) to generate deep features for CRF learning. The deep CNN is trained on the ImageNet dataset and transferred to image segmentations here for constructing potentials of superpixels. Then ...

Image Segmentation Using Binary Tree Structured Markov Random Fields

Learning Tree-structured Descriptor Quantizers for Image Categorization

Current state-of-the-art image categorization systems rely on bag-of-words representations that model image content as a histogram of quantization indices that code local image appearance. In this context, randomized tree-structured quantizers have been shown to be both computationally efficient and yielding discriminative visual words for a given categorization task. This paper presents a new ...

Learning Tree-Structured Vector Quantization for Image Compression

Kohonen's self-organizing feature map (KSOFM) is an adaptive vector quantization (VQ) scheme for progressive code vector update. However, KSOFM approach belongs to unconstrained vector quantization, which suuers from exponential growth of the codebook. In this paper, a learning tree-structured vector quantization (LTSVQ) is presented for overcoming this drawback, which is based on competitive l...