Related papers: WebSeg: Learning Semantic Segmentation from Web Se…
We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive…
We introduce a purely feed-forward architecture for semantic segmentation. We map small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions of increasing extent. These regions are…
Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature…
Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is…
For best performance, today's semantic segmentation methods use large and carefully labeled datasets, requiring expensive annotation budgets. In this work, we show that coarse annotation is a low-cost but highly effective alternative for…
Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse…
Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…
This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL benefits from fast and low-cost data collection, noises in…
Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely challenging due to correlation…
Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base…
Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in annotation time and in the annotators' expertise. Existing…
Learning from web data has attracted lots of research interest in recent years. However, crawled web images usually have two types of noises, label noise and background noise, which induce extra difficulties in utilizing them effectively.…
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…
This paper proposes a novel weakly-supervised semantic segmentation method using image-level label only. The class-specific activation maps from the well-trained classifiers are used as cues to train a segmentation network. The well-known…
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…
Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation…
Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance…
Modern incremental learning for semantic segmentation methods usually learn new categories based on dense annotations. Although achieve promising results, pixel-by-pixel labeling is costly and time-consuming. Weakly incremental learning for…
The performance of deep networks for semantic image segmentation largely depends on the availability of large-scale training images which are labelled at the pixel level. Typically, such pixel-level image labellings are obtained manually by…
We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neural architecture search (NAS), FasterSeg is discovered from a…