Related papers: Realizing Pixel-Level Semantic Learning in Complex…
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per…
With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…
Assigning meaning to parts of image data is the goal of semantic image segmentation. Machine learning methods, specifically supervised learning is commonly used in a variety of tasks formulated as semantic segmentation. One of the major…
Unsupervised semantic segmentation aims to categorize each pixel in an image into a corresponding class without the use of annotated data. It is a widely researched area as obtaining labeled datasets is expensive. While previous works in…
Semantic segmentation of LiDAR point clouds is an important task in autonomous driving. However, training deep models via conventional supervised methods requires large datasets which are costly to label. It is critical to have…
The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations. However, even the largest public datasets only provide samples with pixel-level annotations for rather limited…
Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudo-labels by…
Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However, the scarcity of detailed annotations remains a major challenge, especially in scenarios…
This work addresses the task of completely weakly supervised class-incremental learning for semantic segmentation to learn segmentation for both base and additional novel classes using only image-level labels. While class-incremental…
Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images. Most previous methods rely on the pixel-level label of support images. In this paper, we focus on a more…
Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment…
This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively…
The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part…
Semantic segmentation is a fundamental task in medical image analysis and autonomous driving and has a problem with the high cost of annotating the labels required in training. To address this problem, semantic segmentation methods based on…
Categorizing driving scenes via visual perception is a key technology for safe driving and the downstream tasks of autonomous vehicles. Traditional methods infer scene category by detecting scene-related objects or using a classifier that…
Nuclei instance segmentation on histopathology images is of great clinical value for disease analysis. Generally, fully-supervised algorithms for this task require pixel-wise manual annotations, which is especially time-consuming and…
Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling…
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…
Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive…
As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs while training neural networks for this purpose, is class…