Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
In this work we introduce a fully-connected graph structure in the Deep Gaussian Conditional Random Field (G-CRF) model. For this we express the pairwise interactions between pixels as the inner-products of low-dimensional embeddings, delivered by a new subnetwork of a deep architecture. We efficiently minimize the resulting energy by solving the resulting low-rank linear system with conjugate gradients, and derive an analytic expression for the gradient of our embeddings which allows us to train them end-to-end with backpropagation. We demonstrate the merit of our approach by achieving state of the art results on three challenging Computer Vision benchmarks, namely semantic segmentation, human parts segmentation, and saliency estimation. Our implementation is fully GPU based, built on top of the Caffe library, and will be made publicly available.
Code (0)
등록된 구현이 없습니다.
Tasks
GPUSaliency PredictionSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Pivotal CLTs for Pseudolikelihood via Conditional Centering in Dependent Random Fields
In this paper, we study fluctuations of conditionally centered statistics of the form $$N^{-1/2}\sum_{i=1}^N c_i(g(σ_i)-\mathbb{E}_N[g(σ_i)|σ_j,j\neq i])$$ where $(σ_1,\ldots ,σ_N)$ are sampled from a dependent random fi…
Deep Spatio-Temporal Random Fields for Efficient Video Segmentation
In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a dens…
Instance SegmentationSemantic SegmentationStructured PredictionVideo Segmentation+2Image Restoration Using Conditional Random Fields and Scale Mixtures of Gaussians
This paper proposes a general framework for internal patch-based image restoration based on Conditional Random Fields (CRF). Unlike related models based on Markov Random Fields (MRF), our approach explicitly formulates t…
DenoisingImage DenoisingImage RestorationRegularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond
We introduce regularized Frank-Wolfe, a general and effective algorithm for inference and learning of dense conditional random fields (CRFs). The algorithm optimizes a nonconvex continuous relaxation of the CRF inference…
Semantic SegmentationEfficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level models often feature dense pairwise connectivity, pi…
Image SegmentationSegmentationSemantic Segmentation