EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection

@article{Ghafoorian2018ELGANEL,
  title={EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection},
  author={Mohsen Ghafoorian and Cedric Nugteren and N{\'o}ra Baka and Olaf Booij and Michael Hofmann},
  journal={ArXiv},
  year={2018},
  volume={abs/1806.05525}
}
Convolutional neural networks have been successfully applied to semantic segmentation problems. However, there are many problems that are inherently not pixel-wise classification problems but are nevertheless frequently formulated as semantic segmentation. This ill-posed formulation consequently necessitates hand-crafted scenario-specific and computationally expensive post-processing methods to convert the per pixel probability maps to final desired outputs. Generative adversarial networks… 

Figures and Tables from this paper

TopoGAN: A Topology-Aware Generative Adversarial Network
TLDR
A novel GAN model that learns the topology of real images, i.e., connectedness and loopy-ness is proposed, and a new loss is introduced that bridges the gap between synthetic image distribution and real image distribution in the topological feature space.
Calibrated Adversarial Refinement for Multimodal Semantic Segmentation
TLDR
This work proposes a novel two-stage, cascaded strategy for calibrated adversarial refinement, which can be used independently or integrated into any black-box segmentation framework to enable the synthesis of diverse predictions.
Adversarial Loss for Semantic Segmentation of Aerial Imagery
TLDR
A novel loss function combining both adversarial and cross-entropy losses that learn to understand both local and global contexts for semantic segmentation is proposed that improves the structure and refines the edges of buildings without requiring any of the commonly used post-processing methods.
I Bet You Are Wrong: Gambling Adversarial Networks for Structured Semantic Segmentation
TLDR
This paper rethink adversarial training for semantic segmentation and proposes to reformulate the fake/real discrimination framework with a correct/incorrect training objective, replacing the discriminator with a "gambler" network that learns to spot and distribute its budget in areas where the predictions are clearly wrong.
Calibrated Adversarial Refinement for Stochastic Semantic Segmentation
TLDR
This work proposes a novel two-stage, cascaded approach for calibrated adversarial refinement, and shows that the core design can be adapted to other tasks requiring learning a calibrated predictive distribution by experimenting on a toy regression dataset.
On the Benefit of Adversarial Training for Monocular Depth Estimation
Deceiving Image-to-Image Translation Networks for Autonomous Driving With Adversarial Perturbations
TLDR
This letter proposes both quasi-physical and digital adversarial perturbations that can make Im2Im models yield unexpected results, and empirically analyzes these perturgations to show that they generalize well under both paired for image synthesis and unpaired settings for style transfer.
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
TLDR
It is observed that attention maps extracted from a model trained to a reasonable level would encode rich contextual information that can be used as a form of ‘free’ supervision for further representation learning through performing top- down and layer-wise attention distillation within the net- work itself.
Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
TLDR
This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc.
Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation
TLDR
A 3D scene flow benchmark and a novel self-supervised setup for training flow models are proposed and it is found that the setup is able to keep motion coherence and preserve local geometries, which many self- supervised baselines fail to grasp.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Adversarial Structure Matching Loss for Image Segmentation
TLDR
It is demonstrated that ASML outperforms its counterpart CEL especially in context and boundary aspects on figure-ground segmentation and semantic segmentation tasks with various base architectures, such as FCN, U-Net, DeepLab, and PSPNet.
Shadow Detection with Conditional Generative Adversarial Networks
TLDR
This work introduces scGAN, a novel extension of conditional Generative Adversarial Networks (GAN) tailored for the challenging problem of shadow detection in images, and introduces an additional sensitivity parameter to the generator of a conditional GAN.
Adversarial Learning for Semi-supervised Semantic Segmentation
TLDR
It is shown that the proposed discriminator can be used to improve semantic segmentation accuracy by coupling the adversarial loss with the standard cross entropy loss of the proposed model.
SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation
TLDR
A novel end-to-end adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local features that capture long- and short-range spatial relationships between pixels is proposed.
Semantic Segmentation using Adversarial Networks
TLDR
An adversarial training approach to train semantic segmentation models that can detect and correct higher-order inconsistencies between ground truth segmentation maps and the ones produced by the segmentation net.
Image-to-Image Translation with Conditional Adversarial Networks
TLDR
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
TLDR
Markovian Generative Adversarial Networks (MGANs) are proposed, a method for training generative networks for efficient texture synthesis that surpasses previous neural texture synthesizers by a significant margin and applies to texture synthesis, style transfer, and video stylization.
Generative Adversarial Text to Image Synthesis
TLDR
A novel deep architecture and GAN formulation is developed to effectively bridge advances in text and image modeling, translating visual concepts from characters to pixels.
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.
Brain Tumor Segmentation Using an Adversarial Network
TLDR
An adversarial training approach to train the CNN network is proposed and it is demonstrated that the presented method could enhance the spatial contiguity of the segmentsation results and improve the segmentation accuracy.
...
1
2
3
4
5
...