Unsupervised Monocular Training Method for Depth Estimation Using Statistical Masks

Wang, Xiangtong; Li, Wei; Yang, Menglong; Cheng, Peng; Liang, Binbin

doi:10.1109/access.2020.3032582

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lighting conditions. Previous study 20,34 show that during the depth estimation model training, the low-texture areas caused by insufficient lighting or overexposure will produce problem pixels in depth estimation.…”

Section: Factors That Affect the Train Of Mdementioning

confidence: 99%

What makes the unsupervised monocular depth estimation (UMDE) model training better

Wang

Liang

Yang

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow segmentation and depth estimation. In practice, manual labeling for dense estimation tasks is very difficult or even impossible, and the scenes of the dataset are often restricted to a small range, which dramatically limits the development of the community. To overcome this deficiency, we propose a synthetic dataset generation method to obtain the expandable dataset without burdensome manual workforce. By this method, we construct a dataset called MineNavi containing video footages from first-perspective-view of the aircraft matched with accurate ground truth for depth estimation in aircraft navigation application. We also provide quantitative experiments to prove that pre-training via our MineNavi dataset can improve the performance of depth estimation model and speed up the convergence of the model on real scene data. Since the synthetic dataset has a similar effect to the real-world dataset in the training process of deep model, we finally conduct the experiments on MineNavi with unsupervised monocular depth estimation (UMDE) deep learning models to demonstrate the impact of various factors in our dataset such as lighting conditions and motion mode, aiming to explore what makes this kind of models training better.

show abstract

Section: Factors That Affect the Train Of Mdementioning

confidence: 99%

What makes the unsupervised monocular depth estimation (UMDE) model training better

Wang

Liang

Yang

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…PRESENCE is an online and adaptive data reweighting method that uses self-influence scores to weigh samples in a training batch. We note that during pre-training, the training loss decreases exponentially in the initial steps, with a minimal decrease in loss values in the subsequent stages (Yang et al, 2021). Furthermore, well-trained models can identify noisy samples better when used to calculate SI scores, as compared to models in very early stages of training (Pruthi et al, 2020).…”

Section: Introductionmentioning

confidence: 96%

Self-Influence Guided Data Reweighting for Language Model Pre-training

Thakkar,

Bolukbasi,

Ganapathy

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Language Models (LMs) pre-trained with selfsupervision on large text corpora have become the default starting point for developing models for various NLP tasks. Once the pre-training corpus has been assembled, all data samples in the corpus are treated with equal importance during LM pre-training. However, due to varying levels of relevance and quality of data, equal importance to all the data samples may not be the optimal choice. While data reweighting has been explored in the context of task-specific supervised learning and LM fine-tuning, model-driven reweighting for pretraining data has not been explored. We fill this important gap and propose PRESENCE, a method for jointly reweighting samples by leveraging self-influence (SI) scores as an indicator of sample importance and pre-training. PRESENCE promotes novelty and stability for model pre-training. Through extensive analysis spanning multiple model sizes, datasets, and tasks, we present PRESENCE as an important first step in the research direction of sample reweighting for pre-training language models.

show abstract

Unsupervised Monocular Training Method for Depth Estimation Using Statistical Masks

Cited by 2 publications

References 19 publications

What makes the unsupervised monocular depth estimation (UMDE) model training better

What makes the unsupervised monocular depth estimation (UMDE) model training better

Self-Influence Guided Data Reweighting for Language Model Pre-training

Contact Info

Product

Resources

About