Related papers: PatchRefineNet: Improving Binary Segmentation by I…

Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory. The boundaries of predicted instance masks are usually imprecise due to the low spatial resolution of feature maps and the imbalance…

We present a lightweight post-processing method to refine the semantic segmentation results of point cloud sequences. Most existing methods usually segment frame by frame and encounter the inherent ambiguity of the problem: based on a…

Detection of curvilinear structures in images has long been of interest. One of the most challenging aspects of this problem is inferring the graph representation of the curvilinear network. Most existing delineation approaches first…

How to effectively approximate real-valued parameters with binary codes plays a central role in neural network binarization. In this work, we reveal an important fact that binarizing different layers has a widely-varied effect on the…

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…

While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them…

Binary neural networks leverage $\mathrm{Sign}$ function to binarize weights and activations, which require gradient estimators to overcome its non-differentiability and will inevitably bring gradient errors during backpropagation. Although…

The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of training samples has to be manually labeled on…

A major challenge in image segmentation is classifying object boundaries. Recent efforts propose to refine the segmentation result with boundary masks. However, models are still prone to misclassifying boundary pixels even when they…

Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new…

Salient segmentation aims to segment out attention-grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and…

Change detection, as a research hotspot in the field of remote sensing, has witnessed continuous development and progress. However, the discrimination of boundary details remains a significant bottleneck due to the complexity of surrounding…

Small object detection in aerial images suffers from severe information degradation during feature extraction due to limited pixel representations, where shallow spatial details fail to align effectively with semantic information, leading…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

Despite the superior performance of Deep Learning (DL) on numerous segmentation tasks, the DL-based approaches are notoriously overconfident about their prediction with highly polarized label probability. This is often not desirable for…

Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation…

Binarization is a powerful compression technique for neural networks, significantly reducing FLOPs, but often results in a significant drop in model performance. To address this issue, partial binarization techniques have been developed,…

In High-definition (HD) maps, lane elements constitute the majority of components and demand stringent localization requirements to ensure safe vehicle navigation. Vision lane detection with LiDAR position assignment is a prevalent method…

To reduce memory footprint and run-time latency, techniques such as neural network pruning and binarization have been explored separately. However, it is unclear how to combine the best of the two worlds to get extremely small and efficient…

Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by extreme viewpoint variations.…