paper-with-me

홈 › Papers

Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation

2022-01-01 · CVPR 2022 1 · Andra Petrovai, Sergiu Nedevschi

We present a novel self-distillation based self-supervised monocular depth estimation (SD-SSMDE) learning framework. In the first step, our network is trained in a self-supervised regime on high-resolution images with the photometric loss. The network is further used to generate pseudo depth labels for all the images in the training set. To improve the performance of our estimates, in the second step, we re-train the network with the scale invariant logarithmic loss supervised by pseudo labels. We resolve scale ambiguity and inter-frame scale consistency by introducing an automatically computed scale in our depth labels. To filter out noisy depth values, we devise a filtering scheme based on the 3D consistency between consecutive views. Extensive experiments demonstrate that each proposed component and the self-supervised learning framework improve the quality of the depth estimation over the baseline and achieve state-of-the-art results on the KITTI and Cityscapes datasets.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationMonocular Depth EstimationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

2022-12-08 · CVPR 2023 1 · Chen Zhang, Guorong Li, Yuankai Qi, Shuhui Wang 외

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseu…

Anomaly DetectionDiversityPseudo LabelVideo Anomaly Detection+1

Self-Taught Metric Learning without Labels

2022-05-04 · CVPR 2022 1 · Sungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak

We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the mode…

Metric Learning

Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning

2022-10-17 · CVPR 2023 1 · Kangning Liu, Weicheng Zhu, Yiqiu Shen, Sheng Liu 외

Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-…

Contrastive Learningimage-classificationImage ClassificationMedical Image Classification+2

Semi-supervised Anatomical Landmark Detection via Shape-regulated Self-training

2021-05-28 · Runnan Chen, Yuexin Ma, Lingjie Liu, Nenglun Chen 외

Well-annotated medical images are costly and sometimes even impossible to acquire, hindering landmark detection accuracy to some extent. Semi-supervised learning alleviates the reliance on large-scale annotated data by e…

Anatomical Landmark Detection

Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels

2022-03-23 · Bing Li, Cheng Zheng, Guohao Li, Bernard Ghanem

We propose a novel scene flow method that captures 3D motions from point clouds without relying on ground-truth scene flow annotations. Due to the irregularity and sparsity of point clouds, it is expensive and time-consu…

Pseudo LabelSelf-Supervised Learning