DESC: Domain Adaptation for Depth Estimation via Semantic Consistency

Lopez-Rodriguez, Adrian; Mikolajczyk, Krystian

doi:10.1007/s11263-022-01718-1

Cited by 22 publications

(14 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…My algorithm is based on the GASDA algorithm, and it has a convincing improvement compared with the classical algorithm and the GASDA [15] algorithm. Compared with the state-of-the-art algorithms, the DESC algorithm proposed by Mikolajczyk et al [32] requires additional semantic segmentation of the source domain and ground truth labels of edge images in order to effectively improve the performance of the algorithm.This process is complex and resource-intensive In contrast, we have achieved some surpassing indicators by using only simpler and less prior information.The following five scale-invariant metrics are used to measure the performance of the algorithm: Here, T represents the total number of pixels across all test images. d k ,d gt k represent the predicted depth and ground-truth depth, respectively, corresponding to the kth pixel.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…This approach involves a synthetic data corpus and their labeled counterparts as the source domain, with real but unlabeled data as the target domain. The objective is to train a depth estimation task network in the source domain in a supervised manner and then generalize it to the target domain, creating a network model that can predict depth in the target domain [1,[31][32][33]. The UDA depth estimation algorithm has undergone multiple iterative improvements.…”

Section: Unsupervised Domain Adaptative Depth Estimationmentioning

confidence: 99%

“…In the above pixel-wise image tasks, edge information is usually superimposed with the input to achieve the enhancement of high-frequency information in a single domain [23,25,32,43,44]. While performing domain-adaptive depth estimation, we prefer to use edge information to guide single-domain attention and establish edge consistency constraints in the output part to strengthen the correlation between two domains.…”

Section: Edge Information For Pixel-wise Image Tasksmentioning

confidence: 99%

See 2 more Smart Citations

WITHDRAWN: Outdoor UDA Depth Estimation with Intra-domain Attention and Cross-domain Edge Constraint

Peng,

Pan,

et al. 2023

Preprint

View full text Add to dashboard Cite

In the unsupervised domain adaptation (UDA) depth estimation task, a new adaptive approach is to use the bidirectional transformation network to transfer the style between the target and source domain inputs, and then train the depth estimation network in their respective domains. However, the domain adaptation process and the style transfer may result in defects and biases.Especially in outdoor environments with long distances and complex surroundings, it often leads to map holes and missing areas in the target domain's depth output. To address these issues, We propose a training network that has been improved in terms of model structure and supervision constraints. First, we introduce a edge-guided self-attention mechanism in the task network of each domain to enhance the network's attention to high-frequency edge features, maintain clear boundaries and fill in missing areas of depth. Furthermore, we utilize an edge detection algorithm to extract edge features from the input of the target domain. Then we establish edge consistency constraints between inter-domain entities in order to narrow the gap between domains and make domain-to-domain transfers easier. Our experimental demonstrate that our proposed method effectively solve the aforementioned problem, resulting in a higher quality depth map and outperforming existing state-of-the-art methods.Our code and datasets are all open-sourced at the following address:https://github.com/chongagp/UDA-depth-estimation-under-intra-domain-self-attention-guidance-and-cross-domain-edge-constraints

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Section: Unsupervised Domain Adaptative Depth Estimationmentioning

confidence: 99%

Section: Edge Information For Pixel-wise Image Tasksmentioning

confidence: 99%

See 1 more Smart Citation

WITHDRAWN: Outdoor UDA Depth Estimation with Intra-domain Attention and Cross-domain Edge Constraint

Peng,

Pan,

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Unsupervised domain adaptative object detectors are proposed with various domain adaptation mechanisms. These mechanism can be listed as based on adversarial learning, 14,15,[25][26][27][28] image-toimage translation, [28][29][30] pseudo-label self training, 16,[31][32][33][34] mean-teacher training for cross domain. 35,36 Many domain adaptive object detectors are proposed based on adversarial learning.…”

Section: Related Workmentioning

confidence: 99%

Pixel-level transformations in domain adaptive object detection for thermal imagery

Ayerden

Altinel

2023

Multimodal Image Exploitation and Learning 2023

View full text Add to dashboard Cite

Object detection is a common task for defense and intelligence applications in the visible spectrum. Deep learning models achieve state-of-the-art performance for this task. Besides, thermal cameras are more robust against real-world computer vision problems such as illumination changes. Thus, they are commonly used in military applications and security surveillance tasks. Recently, significant improvements have been made by exploiting numerous data for object detection. However, collecting and labeling a vast number of samples is challenging, especially for applications on the thermal spectrum. Since deep networks are sensitive to domain shift, a deep model trained on visible spectrum data may fail to generalize thermal spectrum data. Therefore, developing a method to adapt models to different domains, e.g., visible-to-thermal, is crucial. Feature-level unsupervised domain adaptation methods train a model that maps both domains into a common feature space without requiring image pairs. Such methods reduce the domain gap between two different domains.Besides feature-level adaptation, we propose applying pixel-level transformations on the source domain, e.g., visible spectrum images, to reduce further the domain gap between the visible and thermal spectrum. This results in a significant improvement in the performance of domain adaptive object detection methods. We propose to apply gray-scale conversion, histogram matching, histogram equalization, gamma correction, adaptive gamma correction, and Fourier domain adaptation as pixel-level transformations on visible spectrum images. We conduct experiments on real-world datasets. The evaluations use Cityscapes as the visible spectrum dataset and FLIR ADAS as the thermal spectrum dataset.

show abstract

“…Hence, the goal is to close the gap between both domains. There is already a large body of literature on UDA for 2D object detection in driving scenes [5,10,11,15,38,40,49,54,66]. Due to the growing number of publicly available large-scale autonomous driving datasets, UDA on 3D point cloud data has gained more interest recently [1,12,30,62].…”

Section: Related Workmentioning

confidence: 99%

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

Christian¹,

Opitz²,

Possegger³

et al. 2022

Preprint

View full text Add to dashboard Cite

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (\eg, geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. % which contains additional information.To address this issue, we propose a flow-aware self-training method which enables unsupervised domain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker, that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art.

show abstract

DESC: Domain Adaptation for Depth Estimation via Semantic Consistency

Cited by 22 publications

References 68 publications

WITHDRAWN: Outdoor UDA Depth Estimation with Intra-domain Attention and Cross-domain Edge Constraint

WITHDRAWN: Outdoor UDA Depth Estimation with Intra-domain Attention and Cross-domain Edge Constraint

Pixel-level transformations in domain adaptive object detection for thermal imagery

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

Contact Info

Product

Resources

About