Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation
149
0
0.0
(
0
)
Added by
Yihao Zhang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system is initially bootstrapped with supervised training on a labeled dataset and we look for a self-supervised training method that can subsequently improve the system over the supervised training baseline using only unlabeled data. In this work, we leverage temporal consistency between frames in monocular video to perform this bootstrapped self-supervised training. We show that a well-trained state-of-the-art semantic segmentation network can be further improved through our method. In addition, we show that the bootstrapped self-supervised training framework can help a network learn depth estimation better than pure supervised training or self-supervised training.
rate research
Read More
Self-supervised depth estimation has shown its great effectiveness in producing high quality depth maps given only image sequences as input. However, its performance usually drops when estimating on border areas or objects with thin structures due to the limited depth representation ability. In this paper, we address this problem by proposing a semantic-guided depth representation enhancement method, which promotes both local and global depth feature representations by leveraging rich contextual information. In stead of a single depth network as used in conventional paradigms, we propose an extra semantic segmentation branch to offer extra contextual features for depth estimation. Based on this framework, we enhance the local feature representation by sampling and feeding the point-based features that locate on the semantic edges to an individual Semantic-guided Edge Enhancement module (SEEM), which is specifically designed for promoting depth estimation on the challenging semantic borders. Then, we improve the global feature representation by proposing a semantic-guided multi-level attention mechanism, which enhances the semantic and depth features by exploring pixel-wise correlations in the multi-level depth decoding scheme. Extensive experiments validate the distinct superiority of our method in capturing highly accurate depth on the challenging image areas such as semantic category borders and thin objects. Both quantitative and qualitative experiments on KITTI show that our method outperforms the state-of-the-art methods.
Image-based learning methods for autonomous vehicle perception tasks require large quantities of labelled, real data in order to properly train without overfitting, which can often be incredibly costly. While leveraging the power of simulated data can potentially aid in mitigating these costs, networks trained in the simulation domain usually fail to perform adequately when applied to images in the real domain. Recent advances in domain adaptation have indicated that a shared latent space assumption can help to bridge the gap between the simulation and real domains, allowing the transference of the predictive capabilities of a network from the simulation domain to the real domain. We demonstrate that a twin VAE-based architecture with a shared latent space and auxiliary decoders is able to bridge the sim2real gap without requiring any paired, ground-truth data in the real domain. Using only paired, ground-truth data in the simulation domain, this architecture has the potential to generate perception tasks such as depth and segmentation maps. We compare this method to networks trained in a supervised manner to indicate the merit of these results.
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised and domain-adaptive semantic segmentation, which is enhanced by self-supervised monocular depth estimation (SDE) trained only on unlabeled image sequences. In particular, we utilize SDE as an auxiliary task comprehensively across the entire learning framework: First, we automatically select the most useful samples to be annotated for semantic segmentation based on the correlation of sample diversity and difficulty between SDE and semantic segmentation. Second, we implement a strong data augmentation by mixing images and labels using the geometry of the scene. Third, we transfer knowledge from features learned during SDE to semantic segmentation by means of transfer and multi-task learning. And fourth, we exploit additional labeled synthetic data with Cross-Domain DepthMix and Matching Geometry Sampling to align synthetic and real data. We validate the proposed model on the Cityscapes dataset, where all four contributions demonstrate significant performance gains, and achieve state-of-the-art results for semi-supervised semantic segmentation as well as for semi-supervised domain adaptation. In particular, with only 1/30 of the Cityscapes labels, our method achieves 92% of the fully-supervised baseline performance and even 97% when exploiting additional data from GTA. The source code is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.
In the recent years, many methods demonstrated the ability of neural networks tolearn depth and pose changes in a sequence of images, using only self-supervision as thetraining signal. Whilst the networks achieve good performance, the often over-lookeddetail is that due to the inherent ambiguity of monocular vision they predict depth up to aunknown scaling factor. The scaling factor is then typically obtained from the LiDARground truth at test time, which severely limits practical applications of these methods.In this paper, we show that incorporating prior information about the camera configu-ration and the environment, we can remove the scale ambiguity and predict depth directly,still using the self-supervised formulation and not relying on any additional sensors.
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics applications,multiple views of a scene may or may not be available, depend-ing on the actions of the robot, switching between monocularand multi-view reconstruction. To address this mixed setting,we proposed a new approach that extends any off-the-shelfself-supervised monocular depth reconstruction system to usemore than one image at test time. Our method builds on astandard prior learned to perform monocular reconstruction,but uses self-supervision at test time to further improve thereconstruction accuracy when multiple images are available.When used to update the correct components of the model, thisapproach is highly-effective. On the standard KITTI bench-mark, our self-supervised method consistently outperformsall the previous methods with an average 25% reduction inabsolute error for the three common setups (monocular, stereoand monocular+stereo), and comes very close in accuracy whencompared to the fully-supervised state-of-the-art methods.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
