Related papers: A Projected Gradient Descent Method for CRF Infere…
We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation. This reduction allows to train feed-forward non-recurrent deep instance segmentation systems in an end-to-end fashion using…
Structural learning, a method to estimate the parameters for discrete energy minimization, has been proven to be effective in solving computer vision problems, especially in 3D scene parsing. As the complexity of the models increases,…
The problem of inferring object shape from a single 2D image is underconstrained. Prior knowledge about what objects are plausible can help, but even given such prior knowledge there may still be uncertainty about the shapes of occluded…
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…
We develop a new framework for learning variational autoencoders and other deep generative models that balances generative and discriminative goals. Our framework optimizes model parameters to maximize a variational lower bound on the…
Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical…
We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation…
Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years. Current state-of-the-art object detection methods mostly adhere to the framework of regions with convolutional…
3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have advanced novel-view synthesis. Recent methods extend multi-view 2D segmentation to 3D, enabling instance/semantic segmentation for better scene understanding. A key…
Deep learning based methods have seen a massive rise in popularity for hyperspectral image classification over the past few years. However, the success of deep learning is attributed greatly to numerous labeled samples. It is still very…
Semantic segmentation is an important task in computer vision that is often tackled with convolutional neural networks (CNNs). A CNN learns to produce pixel-level predictions through training on pairs of images and their corresponding…
We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation…
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…
Object Pose Estimation is a crucial component in robotic grasping and augmented reality. Learning based approaches typically require training data from a highly accurate CAD model or labeled training data acquired using a complex setup. We…
Deep learning approaches to generic (non-semantic) segmentation have so far been indirect and relied on edge detection. This is in contrast to semantic segmentation, where DNNs are applied directly. We propose an alternative approach called…
Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks. However, the local label dependencies and inefficient Viterbi decoding have always been a problem to be solved. In this work, we introduce…
This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield…
Combining CNN with CRF for modeling dependencies between pixel labels is a popular research direction. This task is far from trivial, especially if end-to-end training is desired. In this paper, we propose a novel simple approach to CNN+CRF…
Deep convolutional neural networks (CNNs) are the backbone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can significantly enhance…
Weakly supervised semantic segmentation has been a subject of increased interest due to the scarcity of fully annotated images. We introduce a new approach for solving weakly supervised semantic segmentation with deep Convolutional Neural…