Related papers: Efficient Inference in Fully Connected CRFs with G…

Convolutional neural networks (CNNs) have received increasing attention over the last few years. They were initially conceived for image categorization, i.e., the problem of assigning a semantic label to an entire input image. In this paper…

Conventional change detection methods require a large number of images to learn background models or depend on tedious pixel-level labeling by humans. In this paper, we present a weakly supervised approach that needs only image-level labels…

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…

Superpixel-based Higher-order Conditional random fields (SP-HO-CRFs) are known for their effectiveness in enforcing both short and long spatial contiguity for pixelwise labelling in computer vision. However, their higher-order potentials…

Weakly-supervised segmentation with label-efficient sparse annotations has attracted increasing research attention to reduce the cost of laborious pixel-wise labeling process, while the pairwise affinity modeling techniques play an…

We tackle the panoptic segmentation problem with a conditional random field (CRF) model. Panoptic segmentation involves assigning a semantic label and an instance label to each pixel of a given image. At each pixel, the semantic label and…

We explore the efficiency of the CRF inference module beyond image level semantic segmentation. The key idea is to combine the best of two worlds of semantic co-labeling and exploiting more expressive models. Similar to [Alvarez14] our…

To get more accurate saliency maps, recent methods mainly focus on aggregating multi-level features from fully convolutional network (FCN) and introducing edge information as auxiliary supervision. Though remarkable progress has been…

Current successful approaches for generic (non-semantic) segmentation rely mostly on edge detection and have leveraged the strengths of deep learning mainly by improving the edge detection stage in the algorithmic pipeline. This is in…

Implicit neural representations (INRs) have achieved remarkable successes in learning expressive yet compact signal representations. However, they are not naturally amenable to predictive tasks such as segmentation, where they must learn…

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs)…

While the literature has been fairly dense in the areas of scene understanding and semantic labeling there have been few works that make use of motion cues to embellish semantic performance and vice versa. In this paper, we address the…

Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of…

Image classification is a challenging problem for computer in reality. Large numbers of methods can achieve satisfying performances with sufficient labeled images. However, labeled images are still highly limited for certain image…

This paper proposes a new deep convolutional neural network (DCNN) architecture that learns pixel embeddings, such that pairwise distances between the embeddings can be used to infer whether or not the pixels lie on the same region. That…

Semi-Markov Conditional Random Fields (semi-CRFs) assign labels to segments of a sequence rather than to individual positions, enabling exact inference over segment-level features and principled uncertainty estimates at their boundaries.…

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…

In this paper we propose an improved mean-field inference algorithm for the fully connected paired CRFs model. The improved method Message Passing operation is changed from the original linear convolution to the present graph attention…

Machine learning methods on graphs have proven useful in many applications due to their ability to handle generally structured data. The framework of Gaussian Markov Random Fields (GMRFs) provides a principled way to define Gaussian models…

Classification of remotely sensed images into land cover or land use is highly dependent on geographical information at least at two levels. First, land cover classes are observed in a spatially smooth domain separated by sharp region…