Focus on Semantic Consistency for Cross-domain Crowd Understanding
- URL: http://arxiv.org/abs/2002.08623v1
- Date: Thu, 20 Feb 2020 08:51:05 GMT
- Title: Focus on Semantic Consistency for Cross-domain Crowd Understanding
- Authors: Tao Han, Junyu Gao, Yuan Yuan, Qi Wang
- Abstract summary: Some domain adaptation algorithms try to liberate it by training models with synthetic data.
We found that a mass of estimation errors in the background areas impede the performance of the existing methods.
In this paper, we propose a domain adaptation method to eliminate it.
- Score: 34.560447389853614
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: For pixel-level crowd understanding, it is time-consuming and laborious in
data collection and annotation. Some domain adaptation algorithms try to
liberate it by training models with synthetic data, and the results in some
recent works have proved the feasibility. However, we found that a mass of
estimation errors in the background areas impede the performance of the
existing methods. In this paper, we propose a domain adaptation method to
eliminate it. According to the semantic consistency, a similar distribution in
deep layer's features of the synthetic and real-world crowd area, we first
introduce a semantic extractor to effectively distinguish crowd and background
in high-level semantic information. Besides, to further enhance the adapted
model, we adopt adversarial learning to align features in the semantic space.
Experiments on three representative real datasets show that the proposed domain
adaptation scheme achieves the state-of-the-art for cross-domain counting
problems.
Related papers
- Graph-Boosted Attentive Network for Semantic Body Parsing [1.4042211166197214]
This paper proposes a novel approach to decomposing multiple human bodies into semantic part regions in unconstrained environments.
We propose a convolutional neural network architecture which comprises of novel semantic and contour attention mechanisms across feature hierarchy.
Our proposed method achieves the state-of-art results on the challenging Pascal Person-Part dataset.
arXiv Detail & Related papers (2024-07-08T13:32:01Z) - Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration [64.84134880709625]
We show that it is possible to perform domain adaptation via the noise space using diffusion models.
In particular, by leveraging the unique property of how auxiliary conditional inputs influence the multi-step denoising process, we derive a meaningful diffusion loss.
We present crucial strategies such as channel-shuffling layer and residual-swapping contrastive learning in the diffusion model.
arXiv Detail & Related papers (2024-06-26T17:40:30Z) - Diffusion Features to Bridge Domain Gap for Semantic Segmentation [2.8616666231199424]
This paper investigates the approach that leverages the sampling and fusion techniques to harness the features of diffusion models efficiently.
By leveraging the strength of text-to-image generation capability, we introduce a new training framework designed to implicitly learn posterior knowledge from it.
arXiv Detail & Related papers (2024-06-02T15:33:46Z) - Unsupervised Contrastive Domain Adaptation for Semantic Segmentation [75.37470873764855]
We introduce contrastive learning for feature alignment in cross-domain adaptation.
The proposed approach consistently outperforms state-of-the-art methods for domain adaptation.
It achieves 60.2% mIoU on the Cityscapes dataset.
arXiv Detail & Related papers (2022-04-18T16:50:46Z) - On Generalizing Beyond Domains in Cross-Domain Continual Learning [91.56748415975683]
Deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.
Our proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
arXiv Detail & Related papers (2022-03-08T09:57:48Z) - Unsupervised Domain Adaptation for Semantic Segmentation via Low-level
Edge Information Transfer [27.64947077788111]
Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data adapt to real images.
Previous feature-level adversarial learning methods only consider adapting models on the high-level semantic features.
We present the first attempt at explicitly using low-level edge information, which has a small inter-domain gap, to guide the transfer of semantic information.
arXiv Detail & Related papers (2021-09-18T11:51:31Z) - Content Disentanglement for Semantically Consistent
Synthetic-to-RealDomain Adaptation in Urban Traffic Scenes [39.38387505091648]
Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving.
Deep learning techniques trained solely on synthetic data encounter dramatic performance drops when they are tested on real data.
We propose a new, unsupervised, end-to-end domain adaptation network architecture that enables semantically consistent domain adaptation between synthetic and real data.
arXiv Detail & Related papers (2021-05-18T17:42:26Z) - Pixel-Level Cycle Association: A New Perspective for Domain Adaptive
Semantic Segmentation [169.82760468633236]
We propose to build the pixel-level cycle association between source and target pixel pairs.
Our method can be trained end-to-end in one stage and introduces no additional parameters.
arXiv Detail & Related papers (2020-10-31T00:11:36Z) - Domain Adaptation for Semantic Parsing [68.81787666086554]
We propose a novel semantic for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain.
Our semantic benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages.
Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies.
arXiv Detail & Related papers (2020-06-23T14:47:41Z) - Unsupervised Intra-domain Adaptation for Semantic Segmentation through
Self-Supervision [73.76277367528657]
Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation.
To cope with this limitation, automatically annotated data generated from graphic engines are used to train segmentation models.
We propose a two-step self-supervised domain adaptation approach to minimize the inter-domain and intra-domain gap together.
arXiv Detail & Related papers (2020-04-16T15:24:11Z)
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.