Deep clustering for weakly-supervised semantic segmentation in autonomous driving scenes
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2019.11.019
Abstract: Abstract Weakly-supervised semantic segmentation (WSSS) using only tags can significantly ease the label costing, because full supervision needs pixel-level labeling. It is, however, a very challenging task because it is not straightforward to associate tags… read more here.
Keywords: image; weakly supervised; segmentation; semantic segmentation ... See more keywords
Adversarial Dual-Student With Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2022.3206496
Abstract: A common challenge posed to robust semantic segmentation is the expensive data annotation cost. Existing semi-supervised solutions show great potential for solving this problem. Their key idea is constructing consistency regularization with unsupervised data augmentation… read more here.
Keywords: semi supervised; dual student; supervised semantic; semantic segmentation ... See more keywords
Weakly Supervised Semantic Segmentation in Aerial Imagery via Explicit Pixel-Level Constraints
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2022.3224477
Abstract: In recent years, image-level weakly supervised semantic segmentation (WSSS) has developed rapidly in natural scenes due to the easy availability of classification tags. However, limited to complex backgrounds, multicategory scenes, and dense small targets in… read more here.
Keywords: weakly supervised; image level; level; segmentation ... See more keywords
Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2023.3275913
Abstract: Weakly supervised semantic segmentation (WSSS) models relying on class activation maps (CAMs) have achieved desirable performance comparing to the non-CAMs-based counterparts. However, to guarantee WSSS task feasible, we need to generate pseudo labels by expanding… read more here.
Keywords: bidirectional alignment; weakly supervised; class; segmentation ... See more keywords
Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2019.2914870
Abstract: Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other forms of weak supervision, image… read more here.
Keywords: attention; spatial neural; semantic segmentation; supervised semantic ... See more keywords
A Componentwise Approach to Weakly Supervised Semantic Segmentation Using Dual-Feedback Network.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3144194
Abstract: Recent weakly supervised semantic segmentation methods generate pseudolabels to recover the lost position information in weak labels for training the segmentation network. Unfortunately, those pseudolabels often contain mislabeled regions and inaccurate boundaries due to the… read more here.
Keywords: information; network; weakly supervised; segmentation ... See more keywords
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2022.3166916
Abstract: Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide pixel-level localization, but their focus… read more here.
Keywords: localization; weakly supervised; object localization; supervised semantic ... See more keywords
Looking Beyond Single Images for Weakly Supervised Semantic Segmentation Learning.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2022.3168530
Abstract: This article studies the problem of learning weakly supervised semantic segmentation (WSSS) from image-level supervision only. Rather than previous efforts that primarily focus on intra-image information, we address the value of cross-image semantic relations for… read more here.
Keywords: semantic segmentation; supervised semantic; image; weakly supervised ... See more keywords
Saliency as Pseudo-Pixel Supervision for Weakly and Semi-Supervised Semantic Segmentation.
Sign Up to like & getrecommendations! Published in 2023 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2023.3273592
Abstract: Existing studies on semantic segmentation using image-level weak supervision have several limitations, including sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To overcome these challenges, we propose a novel framework, an… read more here.
Keywords: saliency; supervision; pseudo; supervised semantic ... See more keywords