Related papers: Learning Pixel-level Semantic Affinity with Image-…
This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application. Prior neural networks, such as ResNet, tend…
Semantic segmentation has made much progress with increasingly powerful pixel-wise classifiers and incorporating structural priors via Conditional Random Fields (CRF) or Generative Adversarial Networks (GAN). We propose a simpler…
Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic…
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at…
Semantic image segmentation is a principal problem in computer vision, where the aim is to correctly classify each individual pixel of an image into a semantic label. Its widespread use in many areas, including medical imaging and…
We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories. It exploits localization cues that emerge from training classification-tasked…
Semantic segmentation necessitates approaches that learn high-level characteristics while dealing with enormous amounts of data. Convolutional neural networks (CNNs) can learn unique and adaptive features to achieve this aim. However, due…
Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the…
Recently developed deep learning models are able to learn to segment scenes into component objects without supervision. This opens many new and exciting avenues of research, allowing agents to take objects (or entities) as inputs, rather…
Deep Convolutional Neural Networks have proven effective in solving the task of semantic segmentation. However, their efficiency heavily relies on the pixel-level annotations that are expensive to get and often require domain expertise,…
This work investigates the use of deep fully convolutional neural networks (DFCNN) for pixel-wise scene labeling of Earth Observation images. Especially, we train a variant of the SegNet architecture on remote sensing data over an urban…
Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…
Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data where labels are readily available sounds promising,…
Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connections between the two tasks, which is not the most efficient…
Unsupervised localization and segmentation are long-standing computer vision challenges that involve decomposing an image into semantically-meaningful segments without any labeled data. These tasks are particularly interesting in an…
Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address…
Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output…
Semantic segmentation is pixel-wise classification which retains critical spatial information. The "feature map reuse" has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later…
Recently, significant improvement has been made on semantic object segmentation due to the development of deep convolutional neural networks (DCNNs). Training such a DCNN usually relies on a large number of images with pixel-level…