SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation

• URL: http://arxiv.org/abs/2111.09692v2
• Date: Fri, 19 Nov 2021 11:32:25 GMT
• Title: SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation
• Authors: Hang Zhou, Sarah Taylor, David Greenwood
• Abstract summary: SUB-Depth is a universal multi-task training framework for self-supervised monocular depth estimation. Sub-Depth trains a depth network, not only to predict the depth map for an image reconstruction task, but also to distill knowledge from a trained teacher network with unlabelled data. We present extensive evaluations on KITTI to demonstrate the improvements achieved by training a range of existing networks using the proposed framework.
• Score: 12.874712571149725
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose SUB-Depth, a universal multi-task training framework for self-supervised monocular depth estimation (SDE). Depth models trained with SUB-Depth outperform the same models trained in a standard single-task SDE framework. By introducing an additional self-distillation task into a standard SDE training framework, SUB-Depth trains a depth network, not only to predict the depth map for an image reconstruction task, but also to distill knowledge from a trained teacher network with unlabelled data. To take advantage of this multi-task setting, we propose homoscedastic uncertainty formulations for each task to penalize areas likely to be affected by teacher network noise, or violate SDE assumptions. We present extensive evaluations on KITTI to demonstrate the improvements achieved by training a range of existing networks using the proposed framework, and we achieve state-of-the-art performance on this task. Additionally, SUB-Depth enables models to estimate uncertainty on depth output.

Related papers

• HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection [66.42229859018775]
  We introduce a unified, high-capacity weakly supervised object detection (WSOD) network called HUWSOD. HUWSOD incorporates a self-supervised proposal generator and an autoencoder proposal generator with a multi-rate re-supervised pyramid to replace traditional object proposals. Our findings indicate that randomly boxes, although significantly different from well-designed offline object proposals, are effective for WSOD training.
  arXiv  Detail & Related papers  (2024-06-27T17:59:49Z)
• Scale-Invariant Monocular Depth Estimation via SSI Depth [0.6554326244334868]
  Current methods for scale-invariant monocular depth estimation (SI MDE) often struggle due to the complexity of the task. We present a novel approach that leverages SSI inputs to enhance SI depth estimation, streamlining the network's role and facilitating in-the-wild generalization.
  arXiv  Detail & Related papers  (2024-06-13T17:52:47Z)
• Adaptive Discrete Disparity Volume for Self-supervised Monocular Depth Estimation [0.0]
  In this paper, we propose a learnable module, Adaptive Discrete Disparity Volume (ADDV) ADDV is capable of dynamically sensing depth distributions in different RGB images and generating adaptive bins for them. We also introduce novel training strategies - uniformizing and sharpening - to provide regularizations under self-supervised conditions.
  arXiv  Detail & Related papers  (2024-04-04T04:22:25Z)
• Stealing Stable Diffusion Prior for Robust Monocular Depth Estimation [33.140210057065644]
  This paper introduces a novel approach named Stealing Stable Diffusion (SSD) prior for robust monocular depth estimation. The approach addresses this limitation by utilizing stable diffusion to generate synthetic images that mimic challenging conditions. The effectiveness of the approach is evaluated on nuScenes and Oxford RobotCar, two challenging public datasets.
  arXiv  Detail & Related papers  (2024-03-08T05:06:31Z)
• SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes [58.89295356901823]
  Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions. We introduce an external pretrained monocular depth estimation model for generating single-image depth prior. Our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes.
  arXiv  Detail & Related papers  (2022-11-07T16:17:47Z)
• Dense Depth Distillation with Out-of-Distribution Simulated Images [30.79756881887895]
  We study data-free knowledge distillation (KD) for monocular depth estimation (MDE) KD learns a lightweight model for real-world depth perception tasks by compressing it from a trained teacher model while lacking training data in the target domain. We show that our method outperforms the baseline KD by a good margin and even slightly better performance with as few as 1/6 of training images.
  arXiv  Detail & Related papers  (2022-08-26T07:10:01Z)
• X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation [69.9604394044652]
  We propose a novel method to improve the self-supervised training of monocular depth via cross-task knowledge distillation. During training, we utilize a pretrained semantic segmentation teacher network and transfer its semantic knowledge to the depth network. We extensively evaluate the efficacy of our proposed approach on the KITTI benchmark and compare it with the latest state of the art.
  arXiv  Detail & Related papers  (2021-10-24T19:47:14Z)
• How and When Adversarial Robustness Transfers in Knowledge Distillation? [137.11016173468457]
  This paper studies how and when the adversarial robustness can be transferred from a teacher model to a student model in Knowledge distillation (KD) We show that standard KD training fails to preserve adversarial robustness, and we propose KD with input gradient alignment (KDIGA) for remedy. Under certain assumptions, we prove that the student model using our proposed KDIGA can achieve at least the same certified robustness as the teacher model.
  arXiv  Detail & Related papers  (2021-10-22T21:30:53Z)
• Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network [90.20878165546361]
  We propose a new unsupervised depth estimation method based on pseudo supervision mechanism. It strategically integrates the advantages of supervised and unsupervised monocular depth estimation. Our experimental results demonstrate that the proposed method outperforms the state-of-the-art on the KITTI benchmark.
  arXiv  Detail & Related papers  (2021-10-22T01:08:36Z)
• Self-Supervised Monocular Depth Estimation with Internal Feature Fusion [12.874712571149725]
  Self-supervised learning for depth estimation uses geometry in image sequences for supervision. We propose a novel depth estimation networkDIFFNet, which can make use of semantic information in down and upsampling procedures.
  arXiv  Detail & Related papers  (2021-10-18T17:31:11Z)
• Unsupervised Scale-consistent Depth Learning from Video [131.3074342883371]
  We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training. Thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
  arXiv  Detail & Related papers  (2021-05-25T02:17:56Z)

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.