A survey on deep semi-supervised learning

X Yang, Z Song, I King, Z Xu - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Deep semi-supervised learning is a fast-growing field with a range of practical applications.
This paper provides a comprehensive survey on both fundamentals and recent advances in …

Methods for image denoising using convolutional neural network: a review

AE Ilesanmi, TO Ilesanmi - Complex & Intelligent Systems, 2021 - Springer
Image denoising faces significant challenges, arising from the sources of noise. Specifically,
Gaussian, impulse, salt, pepper, and speckle noise are complicated sources of noise in …

Multi-class token transformer for weakly supervised semantic segmentation

L Xu, W Ouyang, M Bennamoun… - Proceedings of the …, 2022 - openaccess.thecvf.com
This paper proposes a new transformer-based framework to learn class-specific object
localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS) …

Layercam: Exploring hierarchical class activation maps for localization

PT Jiang, CB Zhang, Q Hou… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Regional semantic contrast and aggregation for weakly supervised semantic segmentation

T Zhou, M Zhang, F Zhao, J Li - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Learning semantic segmentation from weakly-labeled (eg, image tags only) data is
challenging since it is hard to infer dense object regions from sparse semantic tags. Despite …

Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation

Q Chen, L Yang, JH Lai, X Xie - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels
has attracted much attention due to low annotation costs. Existing methods often rely on …

L2g: A simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation

PT Jiang, Y Yang, Q Hou, Y Wei - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Mining precise class-aware attention maps, aka, class activation maps, is essential for
weakly supervised semantic segmentation. In this paper, we present L2G, a simple online …

Causal intervention for weakly-supervised semantic segmentation

D Zhang, H Zhang, J Tang… - Advances in Neural …, 2020 - proceedings.neurips.cc
We present a causal inference framework to improve Weakly-Supervised Semantic
Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by …

Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation

S Lee, M Lee, J Lee, H Shim - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level
weak supervision have several limitations: sparse object coverage, inaccurate object …

Semi-supervised semantic segmentation with cross-consistency training

Y Ouali, C Hudelot, M Tami - Proceedings of the IEEE/CVF …, 2020 - openaccess.thecvf.com
In this paper, we present a novel cross-consistency based semi-supervised approach for
semantic segmentation. Consistency training has proven to be a powerful semi-supervised …