Related papers: Efficient Learning of Sparse Conditional Random Fi…

Complex textual information extraction tasks are often posed as sequence labeling or \emph{shallow parsing}, where fields are extracted using local labels made consistent through probabilistic inference in a graphical model with constrained…

Most NeRF-based models are designed for learning the entire scene, and complex scenes can lead to longer learning times and poorer rendering effects. This paper utilizes scene semantic priors to make improvements in fast training, allowing…

There are two major approaches for sequence labeling. One is the probabilistic gradient-based methods such as conditional random fields (CRF) and neural networks (e.g., RNN), which have high accuracy but drawbacks: slow training, and no…

Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities…

We consider learning a sparse pairwise Markov Random Field (MRF) with continuous-valued variables from i.i.d samples. We adapt the algorithm of Vuffray et al. (2019) to this setting and provide finite-sample analysis revealing sample…

Deep convolutional networks have achieved the state-of-the-art for semantic image segmentation tasks. However, training these networks requires access to densely labeled images, which are known to be very expensive to obtain. On the other…

Modern high-dimensional methods often adopt the "bet on sparsity" principle, while in supervised multivariate learning statisticians may face "dense" problems with a large number of nonzero coefficients. This paper proposes a novel…

Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or…

Dense conditional random fields (CRF) with Gaussian pairwise potentials have emerged as a popular framework for several computer vision applications such as stereo correspondence and semantic segmentation. By modeling long-range…

A key recent advance in face recognition models a test face image as a sparse linear combination of a set of training face images. The resulting sparse representations have been shown to possess robustness against a variety of distortions…

Recent works on deep conditional random fields (CRF) have set new records on many vision tasks involving structured predictions. Here we propose a fully-connected deep continuous CRF model for both discrete and continuous labelling…

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…

The redundant features existing in high dimensional datasets always affect the performance of learning and mining algorithms. How to detect and remove them is an important research topic in machine learning and data mining research. In this…

Towards a safe and comfortable driving, road scene segmentation is a rudimentary problem in camera-based advance driver assistance systems (ADAS). Despite of the great achievement of Convolutional Neural Networks (CNN) for semantic…

Modern semantic segmentation methods devote much effect to adjusting image feature representations to improve the segmentation performance in various ways, such as architecture design, attention mechnism, etc. However, almost all those…

Feature selection is one of the most decisive tools in understanding data and machine learning models. Among other methods, sparsity induced by $L^{1}$ penalty is one of the simplest and best studied approaches to this problem. Although…

Fully connected pairwise Conditional Random Fields (Full-CRF) with Gaussian edge weights can achieve superior results compared to sparsely connected CRFs. However, traditional methods for Full-CRFs are too expensive. Previous work develops…

Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT) methods aim at significantly reducing the computational and…

Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This paper studies semantic…

In this paper we proposed an ordered patch based method using Conditional Random Field (CRF) in order to encode local properties and their spatial relationship in images to address texture classification, face recognition, and scene…