Learn to Adapt for Monocular Depth Estimation
- URL: http://arxiv.org/abs/2203.14005v1
- Date: Sat, 26 Mar 2022 06:49:22 GMT
- Title: Learn to Adapt for Monocular Depth Estimation
- Authors: Qiyu Sun, Gary G. Yen, Yang Tang, Chaoqiang Zhao
- Abstract summary: We propose an adversarial depth estimation task and train the model in the pipeline of meta-learning.
Our method adapts well to new datasets after few training steps during the test procedure.
- Score: 17.887575611570394
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Monocular depth estimation is one of the fundamental tasks in environmental
perception and has achieved tremendous progress in virtue of deep learning.
However, the performance of trained models tends to degrade or deteriorate when
employed on other new datasets due to the gap between different datasets.
Though some methods utilize domain adaptation technologies to jointly train
different domains and narrow the gap between them, the trained models cannot
generalize to new domains that are not involved in training. To boost the
transferability of depth estimation models, we propose an adversarial depth
estimation task and train the model in the pipeline of meta-learning. Our
proposed adversarial task mitigates the issue of meta-overfitting, since the
network is trained in an adversarial manner and aims to extract domain
invariant representations. In addition, we propose a constraint to impose upon
cross-task depth consistency to compel the depth estimation to be identical in
different adversarial tasks, which improves the performance of our method and
smoothens the training process. Experiments demonstrate that our method adapts
well to new datasets after few training steps during the test procedure.
Related papers
- Transferable Post-training via Inverse Value Learning [83.75002867411263]
We propose modeling changes at the logits level during post-training using a separate neural network (i.e., the value network)
After training this network on a small base model using demonstrations, this network can be seamlessly integrated with other pre-trained models during inference.
We demonstrate that the resulting value network has broad transferability across pre-trained models of different parameter sizes.
arXiv Detail & Related papers (2024-10-28T13:48:43Z) - DepthART: Monocular Depth Estimation as Autoregressive Refinement Task [2.3884184860468136]
We introduce the first autoregressive depth estimation model based on the visual autoregressive transformer.
Our primary contribution is DepthART, a novel training method formulated as Depth Autoregressive Refinement Task.
Our experiments demonstrate that the proposed training approach significantly outperforms visual autoregressive modeling via next-scale prediction in the depth estimation task.
arXiv Detail & Related papers (2024-09-23T13:36:34Z) - Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification [34.37262622415682]
We propose a new adaptation framework called Data Adaptive Traceback.
Specifically, we utilize a zero-shot-based method to extract the most downstream task-related subset of the pre-training data.
We adopt a pseudo-label-based semi-supervised technique to reuse the pre-training images and a vision-language contrastive learning method to address the confirmation bias issue in semi-supervised learning.
arXiv Detail & Related papers (2024-07-11T18:01:58Z) - Continual Learning of Unsupervised Monocular Depth from Videos [19.43053045216986]
We introduce a framework that captures challenges of continual unsupervised depth estimation (CUDE)
We propose a rehearsal-based dual-memory method, MonoDepthCL, which utilizes collected ontemporal consistency for continual learning in depth estimation.
arXiv Detail & Related papers (2023-11-04T12:36:07Z) - MetaComp: Learning to Adapt for Online Depth Completion [47.2074274233496]
We propose MetaComp, which simulates adaptation policies during the training phase and adapts the model to new environments in a self-supervised manner in testing.
Considering that the input is multi-modal data, it would be challenging to adapt a model to variations in two modalities simultaneously.
Experimental results and comprehensive ablations show that our MetaComp is capable of adapting to the depth completion in a new environment effectively and robust to changes in different modalities.
arXiv Detail & Related papers (2022-07-21T17:30:37Z) - 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) - 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) - Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network.
Our motivation is that models are expected to understand complex dynamics from different sources.
Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
arXiv Detail & Related papers (2020-09-24T15:40:55Z) - A Review of Single-Source Deep Unsupervised Visual Domain Adaptation [81.07994783143533]
Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks.
In many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data.
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
arXiv Detail & Related papers (2020-09-01T00:06:50Z) - Learning to Stop While Learning to Predict [85.7136203122784]
Many algorithm-inspired deep models are restricted to a fixed-depth'' for all inputs.
Similar to algorithms, the optimal depth of a deep architecture may be different for different input instances.
In this paper, we tackle this varying depth problem using a steerable architecture.
We show that the learned deep model along with the stopping policy improves the performances on a diverse set of tasks.
arXiv Detail & Related papers (2020-06-09T07:22:01Z)
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.