Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent state-of-the-art approaches propose to adopt two-step solutions, i.e. 1) learn to generate pseudo pixel-level masks, and 2) engage FCNs to train the semantic segmentation networks with the pseudo masks. However, the two-step solutions usually employ many bells and whistles in producing high-quality pseudo masks, making this kind of methods complicated and inelegant. In this work, we harness the image-level labels to produce reliable pixel-level annotations and design a fully end-to-end network to learn to predict segmentation maps. Concretely, we firstly leverage an image classification branch to generate class activation maps for the annotated categories, which are further pruned into confident yet tiny object/background regions. Such reliable regions are then directly served as ground-truth labels for the parallel segmentation branch, where a newly designed dense energy loss function is adopted for optimization. Despite its apparent simplicity, our one-step solution achieves competitive mIoU scores (val: 62.6, test: 62.9) on Pascal VOC compared with those two-step state-of-the-arts. By extending our one-step method to two-step, we get a new state-of-the-art performance on the Pascal VOC (val: 66.3, test: 66.5).

No abstract

Sparse labels have been attracting much attention in recent years. However, the performance gap between weakly supervised and fully supervised salient object detection methods is huge, and most previous weakly supervised works adopt complex training methods with many bells and whistles. In this work, we propose a one-round end-to-end training approach for weakly supervised salient object detection via scribble annotations without pre/post-processing operations or extra supervision data. Since scribble labels fail to offer detailed salient regions, we propose a local coherence loss to propagate the labels to unlabeled regions based on image features and pixel distance, so as to predict integral salient regions with complete object structures. We design a saliency structure consistency loss as self-consistent mechanism to ensure consistent saliency maps are predicted with different scales of the same image as input, which could be viewed as a regularization technique to enhance the model generalization ability. Additionally, we design an aggregation module (AGGM) to better integrate high-level features, low-level features and global context information for the decoder to aggregate various information. Extensive experiments show that our method achieves a new state-of-the-art performance on six benchmarks (e.g. for the ECSSD dataset: Fβ = 0.8995, Eξ = 0.9079 and MAE = 0.0489), with an average gain of 4.60% for F-measure, 2.05% for E-measure and 1.88% for MAE over the previous best performing method on this task. Source code is available at http://github.com/siyueyu/SCWSSOD.

No abstract

No abstract

Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bounding box annotations as supervision. To this end, we propose Affinity Attention Graph Neural Network (A 2 GNN). Following previous practices, we first generate pseudo semantic-aware seeds, which are then formed into semantic graphs based on our newly proposed affinity Convolutional Neural Network (CNN). Then the built graphs are input to our A 2 GNN, in which an affinity attention layer is designed to acquire the short-and long-distance information from soft graph edges to accurately propagate semantic labels from the confident seeds to the unlabeled pixels. However, to guarantee the precision of the seeds, we only adopt a limited number of confident pixel seed labels for A 2 GNN, which may lead to insufficient supervision for training. To alleviate this issue, we further introduce a new loss function and a consistency-checking mechanism to leverage the bounding box constraint, so that more reliable guidance can be included for the model optimization. Experiments show that our approach achieves new state-of-the-art performances on Pascal VOC 2012 datasets (val: 76.5%, test: 75.2%). More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset. Our source code will be available at https://github.com/zbf1991/A2GNN.

BackgroundThe Response Evaluation Criteria in Solid Tumors (RECIST) guideline and Common Terminology Criteria for Adverse Events (CTCAE) criteria are used to assess chemotherapy efficiency and toxicity in patients with advanced lung cancer. However, no real-time, synchronous indicators that can evaluate chemotherapy outcomes are available. We wanted to evaluate tumor response and toxicity in advanced lung cancer chemotherapy by using a novel synchronous strategy.ResultsWe enrolled 316 patients with advanced lung cancer who were treated with cisplatin-based therapy and followed up them for 3 years. Plasma was obtained before and after every chemotherapy cycle. We quantitative assayed total plasma DNA and methylation of the APC/RASSF1A genes. Four parameters were assessed: methylation level before chemotherapy (meth0 h), methylation level 24 h after chemotherapy (meth24 h), total plasma DNA concentration before chemotherapy (DNA0 h), and total plasma DNA concentration 24 h after chemotherapy (DNA24 h). When meth24 h > meth0 h of at least one gene was used to predict tumor response, the correct prediction rate was 82.4 %. Additionally, patients for whom DNA24 h/DNA0 h ≤ 2 had mild toxicities. Therefore, meth24 h > meth0 h and DNA24 h/DNA0 h ≤ 2 were defined as criteria for better tumor response and fewer adverse events with a high correct prediction rate (84.7 %).ConclusionsQuantitative analysis of total plasma DNA and plasma APC/RASSF1A methylation provide a real-time synchronous rapid monitoring indicator for therapeutic outcomes of advanced lung cancer, which could be a reference or supplementary guidelines in evaluating chemotherapy effects.Electronic supplementary materialThe online version of this article (doi:10.1186/s13148-015-0150-9) contains supplementary material, which is available to authorized users.

No abstract