Weakly Supervised Learning弱监督学习,介于有监督和无监督之间的一种学习方式。本论文集收集了通过弱监督学习方法实现的语义分割、图像分割的相关论文。
AAAI, pp.10762-10769, (2020)
Our approach achieves the new state-of-the-art on VOC 2012 dataset for imagelevel label based semantic segmentation
Cited by6BibtexViews193DOI
3
0
NeurIPS, (2020)
In Section 4.3, we demonstrate that Context Adjustment can improve pseudo-marks by 2.0% mean Intersection over Union on average and overall achieves a new state-of-the-art by 66.1% mIoU on the val set and 66.7% mIoU on the test set of PASCAL VOC 2012, and 33.4% mIoU on the val se...
Cited by3BibtexViews484DOI
0
0
CVPR, pp.12272-12281, (2020)
We propose a self-supervised equivariant attention mechanism to narrow the supervision gap between fully and weakly supervised semantic segmentation by introducing additional self-supervision
Cited by1BibtexViews89DOI
0
0
CVPR, pp.13703-13712, (2020)
We made a discovery that only a few labelled points is needed for existing point cloud encoder networks to produce very competitive performance for the point cloud segmentation task
Cited by1BibtexViews49DOI
0
0
AAAI, pp.12765-12772, (2020)
We proposed the Reliable Region Mining, an end-to-end network for image-level weakly supervised semantic segmentation
Cited by1BibtexViews92DOI
1
0
Hui Qu, Pengxiang Wu,Qiaoying Huang, Jingru Yi, Zhennan Yan, Kang Li, Gregory M Riedlinger, Subhajyoti De, Shaoting Zhang, Dimitris N Metaxas
IEEE Trans. Medical Imaging, no. 11 (2020): 3655-3666
Nuclei segmentation is a critical step in the automatic analysis of histopathology images, because the nuclear features such as average size, density and nucleusto-cytoplasm ratio are related to the clinical diagnosis and management of cancer
Cited by0BibtexViews37DOI
1
0
CVPR, pp.9898-9908, (2020)
A two-stage framework called WS2 is proposed to overcome common challenges faced by many synthesize-refine scheme-based methods that are most successful in weakly-supervised video object segmentation
Cited by0BibtexViews68DOI
0
0
CVPR, pp.4282-4291, (2020)
We propose an efficient end-to-end Intra-Class Discriminator approach, which dedicates to the intra-class discrimination between the foreground and the background pixels in each image
Cited by0BibtexViews93DOI
0
0
CVPR, pp.4252-4261, (2020)
We proposed a practical approach to weakly supervised semantic segmentation, which comprises a single segmentation network trained in one round
Cited by0BibtexViews80DOI
0
0
International Journal of Computer Vision, no. 6 (2020): 1736-1749
Our framework consists of a unary segmentation network to predict the class probability map, and a pairwise affinity network to learn affinity and refine the results of the unary network
Cited by0BibtexViews62DOI
0
0
Weide Liu, Chi Zhang,Guosheng Lin, Tzu-Yi HUNG,Chunyan Miao
MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA ..., pp.2085-2094, (2020)
In the weakly supervised segmentation task with only image-level labels, a common step in many existing algorithms is first to locate the image regions corresponding to each existing class with the Class Activation Maps (CAMs), and then generate the pseudo ground truth masks base...
Cited by0BibtexViews27DOI
0
0
european conference on computer vision, pp.571-587, (2020)
Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In this work, we propose a novel framework...
Cited by0BibtexViews34DOI
0
0
european conference on computer vision, pp.254-270, (2020)
Following the same evaluation protocol from other competing approaches, we report mean average precision with four intersection over union thresholds, denoted by mAPkr where k denotes the different values of IoU and k = {0.25, 0.50, 0.70, 0.75}
Cited by0BibtexViews64DOI
0
0
european conference on computer vision, pp.430-446, (2020)
We introduce Adaptive Pseudo Labeling for the positive pseudo labeling step, which dynamically selects the positive pseudo labels without the need of determining the threshold traditionally used in Pseudo Labeling
Cited by0BibtexViews37DOI
0
0
Guolei Sun, Wenguan Wang, Jifeng Dai, Luc Van Gool
european conference on computer vision, pp.347-365, (2020)
Experimental Results: The final results with the standard mean intersection over union criterion for weakly supervised semantic segmentation track of both LID19 and LID20 challenges are shown in Table 3
Cited by0BibtexViews44DOI
0
0
IJCAI, pp.860-867, (2020)
In this paper we proposed a multi-modal interaction module that relates the support set image and query image using both visual and word embeddings
Cited by0BibtexViews46DOI
0
0
CVPR, pp.8988-8997, (2020)
Since the ground truth labels are not available for sub-categories, we present visualizations of clustering results in Figure 5 to measure the quality, in which each parent class shows 3 example clusters
Cited by0BibtexViews170DOI
0
0
Jiacheng Wei,Guosheng Lin,Kim-Hui Yap, Tzu-Yi Hung,Lihua Xie
CVPR, pp.4383-4392, (2020)
Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large scale 3D dataset is no longer a cumber...
Cited by0BibtexViews40DOI
0
0
Mustafa Umit Oner, Hwee Kuan Lee, Wing-Kin Sung
ICLR, (2020)
We introduce a novel Multiple instance learning task based on a new kind of bag level label called unique class count, which is the number of unique classes or the number of clusters among all the instances inside the bag
Cited by0BibtexViews44DOI
0
0
Schmitt Michael, Prexl Jonathan, Ebel Patrick, Liebel Lukas,Zhu Xiao Xiang
We have used the SEN12MS dataset and the data provided in the frame of the IEEE-GRSS 2020 Data Fusion Contest to address the challenge of learning semantic segmentation models for global land cover mapping from inaccurate and inexact labels
Cited by0BibtexViews27DOI
0
0