Synthetic Convolutional Features for Improved Semantic Segmentation
- URL: http://arxiv.org/abs/2009.08849v1
- Date: Fri, 18 Sep 2020 14:12:50 GMT
- Title: Synthetic Convolutional Features for Improved Semantic Segmentation
- Authors: Yang He and Bernt Schiele and Mario Fritz
- Abstract summary: We suggest to generate intermediate convolutional features and propose the first synthesis approach that is catered to such intermediate convolutional features.
This allows us to generate new features from label masks and include them successfully into the training procedure.
Experimental results and analysis on two challenging datasets Cityscapes and ADE20K show that our generated feature improves performance on segmentation tasks.
- Score: 139.5772851285601
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, learning-based image synthesis has enabled to generate
high-resolution images, either applying popular adversarial training or a
powerful perceptual loss. However, it remains challenging to successfully
leverage synthetic data for improving semantic segmentation with additional
synthetic images. Therefore, we suggest to generate intermediate convolutional
features and propose the first synthesis approach that is catered to such
intermediate convolutional features. This allows us to generate new features
from label masks and include them successfully into the training procedure in
order to improve the performance of semantic segmentation. Experimental results
and analysis on two challenging datasets Cityscapes and ADE20K show that our
generated feature improves performance on segmentation tasks.
Related papers
- IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation [77.06177202334398]
We identify two critical challenges in CISS that contribute to semantic drift and degrade performance.
First, we highlight the issue of separate optimization, where different parts of the model are optimized in distinct incremental stages.
Second, we identify noisy semantics arising from inappropriate pseudo-labeling, which results in sub-optimal results.
arXiv Detail & Related papers (2025-02-07T12:19:37Z) - Adversarial Semantic Augmentation for Training Generative Adversarial Networks under Limited Data [27.27230943686822]
We propose an adversarial semantic augmentation (ASA) technique to enlarge the training data at the semantic level instead of the image level.
Our method consistently improve the synthesis quality under various data regimes.
arXiv Detail & Related papers (2025-02-02T13:50:38Z) - HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization [15.13875300007579]
HisynSeg is a weakly-supervised semantic segmentation framework based on image-mixing synthesis and consistency regularization.
HisynSeg achieves a state-of-the-art performance on three datasets.
arXiv Detail & Related papers (2024-12-30T13:10:48Z) - Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance [1.1027204173383738]
We introduce an effective data augmentation pipeline for semantic segmentation using Controllable Diffusion model.
Our proposed method includes efficient prompt generation using textitClass-Prompt Appending and textitVisual Prior Blending.
Our pipeline demonstrates its effectiveness in generating high-quality synthetic images for semantic segmentation.
arXiv Detail & Related papers (2024-09-09T19:01:14Z) - Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability.
We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images.
Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
arXiv Detail & Related papers (2024-03-28T22:25:05Z) - Deep Semantic Statistics Matching (D2SM) Denoising Network [70.01091467628068]
We introduce the Deep Semantic Statistics Matching (D2SM) Denoising Network.
It exploits semantic features of pretrained classification networks, then it implicitly matches the probabilistic distribution of clear images at the semantic feature space.
By learning to preserve the semantic distribution of denoised images, we empirically find our method significantly improves the denoising capabilities of networks.
arXiv Detail & Related papers (2022-07-19T14:35:42Z) - Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of
Semantics and Depth [83.94528876742096]
We tackle the MTL problem of two dense tasks, ie, semantic segmentation and depth estimation, and present a novel attention module called Cross-Channel Attention Module (CCAM)
In a true symbiotic spirit, we then formulate a novel data augmentation for the semantic segmentation task using predicted depth called AffineMix, and a simple depth augmentation using predicted semantics called ColorAug.
Finally, we validate the performance gain of the proposed method on the Cityscapes dataset, which helps us achieve state-of-the-art results for a semi-supervised joint model based on depth and semantic
arXiv Detail & Related papers (2022-06-21T17:40:55Z) - Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for
Semantic Segmentation [68.8204255655161]
We provide the first study on semantic image segmentation and introduce two new approaches: textitSmartAugment and textitSmartSamplingAugment.
SmartAugment uses Bayesian Optimization to search over a rich space of augmentation strategies and achieves a new state-of-the-art performance in all semantic segmentation tasks we consider.
SmartSamplingAugment, a simple parameter-free approach with a fixed augmentation strategy competes in performance with the existing resource-intensive approaches and outperforms cheap state-of-the-art data augmentation methods.
arXiv Detail & Related papers (2021-10-31T13:04:45Z) - Improving Augmentation and Evaluation Schemes for Semantic Image
Synthesis [16.097324852253912]
We introduce a novel augmentation scheme designed specifically for generative adversarial networks (GANs)
We propose to randomly warp object shapes in the semantic label maps used as an input to the generator.
The local shape discrepancies between the warped and non-warped label maps and images enable the GAN to learn better the structural and geometric details of the scene.
arXiv Detail & Related papers (2020-11-25T10:55:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.