Related papers: AlignSeg: Feature-Aligned Segmentation Networks

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Integrating high-level context information with low-level details is of central importance in semantic segmentation. Towards this end, most existing segmentation models apply bilinear up-sampling and convolutions to feature maps of…

Semantic segmentation is a fundamental task in computer vision that involves dense pixel-wise classification for scene understanding. Despite significant progress, achieving high accuracy while maintaining real-time performance remains a…

Semantic segmentation is applied extensively in autonomous driving and intelligent transportation with methods that highly demand spatial and semantic information. Here, an STDC-MA network is proposed to meet these demands. First, the…

Scene parsing from images is a fundamental yet challenging problem in visual content understanding. In this dense prediction task, the parsing model assigns every pixel to a categorical label, which requires the contextual information of…

Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…

Medical image segmentation plays an important role in clinical decision making, treatment planning, and disease tracking. However, it still faces two major challenges. On the one hand, there is often a ``soft boundary'' between foreground…

Semantic segmentation is a fundamental task in multimedia processing, which can be used for analyzing, understanding, editing contents of images and videos, among others. To accelerate the analysis of multimedia data, existing segmentation…

The growing popularity of robotic minimally invasive surgeries has made deep learning-based surgical training a key area of research. A thorough understanding of the surgical scene components is crucial, which semantic segmentation models…

State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are structurally different.…

Aggregating information from features across different layers is an essential operation for dense prediction models. Despite its limited expressiveness, feature concatenation dominates the choice of aggregation operations. In this paper, we…

Co-occurrent visual pattern makes aggregating contextual information a common paradigm to enhance the pixel representation for semantic image segmentation. The existing approaches focus on modeling the context from the perspective of the…

Semantic segmentation is challenging as it requires both object-level information and pixel-level accuracy. Recently, FCN-based systems gained great improvement in this area. Unlike classification networks, combining features of different…

Foreground segmentation is an essential task in the field of image understanding. Under unsupervised conditions, different images and instances always have variable expressions, which make it difficult to achieve stable segmentation…

Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, we present the concept of class center which extracts 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…

Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling…

Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition,…

This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextual information within individual images. Though impressive,…

A serious issue that harms the performance of zero-shot visual recognition is named objective misalignment, i.e., the learning objective prioritizes improving the recognition accuracy of seen classes rather than unseen classes, while the…