Related papers: Weakly Supervised Instance Segmentation using Clas…
Deep convolutional networks have achieved the state-of-the-art for semantic image segmentation tasks. However, training these networks requires access to densely labeled images, which are known to be very expensive to obtain. On the other…
Current instance segmentation methods rely heavily on pixel-level annotated images. The huge cost to obtain such fully-annotated images restricts the dataset scale and limits the performance. In this paper, we formally address…
Weakly supervised instance segmentation has gained popularity because it reduces high annotation cost of pixel-level masks required for model training. Recent approaches for weakly supervised instance segmentation detect and segment objects…
Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discriminative parts of the object which are small and sparse. We…
Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To…
Class Activation Mapping (CAM) methods are widely applied in weakly supervised learning tasks due to their ability to highlight object regions. However, conventional CAM methods highlight only the most discriminative regions of the target.…
Instance-level image classification tasks have traditionally relied on single-instance labels to train models, e.g., few-shot learning and transfer learning. However, set-level coarse-grained labels that capture relationships among…
As an essential indicator for cancer progression and treatment response, tumor size is often measured following the response evaluation criteria in solid tumors (RECIST) guideline in CT slices. By marking each lesion with its longest axis…
This work addresses weakly-supervised image semantic segmentation based on image-level class labels. One common approach to this task is to propagate the activation scores of Class Activation Maps (CAMs) using a random-walk mechanism in…
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in…
With the increase in the number of image data and the lack of corresponding labels, weakly supervised learning has drawn a lot of attention recently in computer vision tasks, especially in the fine-grained semantic segmentation problem. To…
Lesion segmentation in medical imaging serves as an effective tool for assessing tumor sizes and monitoring changes in growth. However, not only is manual lesion segmentation time-consuming, but it is also expensive and requires expert…
We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels which specify the object classes present in the image. Our method uses deep convolutional neural networks (CNNs) and…
Universal models for medical image segmentation, such as interactive and in-context learning (ICL) models, offer strong generalization but require extensive annotations. Interactive models need repeated user prompts for each image, while…
Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to…
Weakly supervised instance segmentation (WSIS) using only image-level labels is a challenging task due to the difficulty of aligning coarse annotations with the finer task. However, with the advancement of deep neural networks (DNNs), WSIS…
We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation. This reduction allows to train feed-forward non-recurrent deep instance segmentation systems in an end-to-end fashion using…
Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel…
Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose…
The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class…