Related papers: Unsupervised Stereo via Multi-Baseline Geometry-Co…

Monocular 3D object detection (Mono3D) has achieved unprecedented success with the advent of deep learning techniques and emerging large-scale autonomous driving datasets. However, drastic performance degradation remains an unwell-studied…

Recent supervised multi-view depth estimation networks have achieved promising results. Similar to all supervised approaches, these networks require ground-truth data during training. However, collecting a large amount of multi-view depth…

Solving depth estimation with monocular cameras enables the possibility of widespread use of cameras as low-cost depth estimation sensors in applications such as autonomous driving and robotics. However, learning such a scalable depth…

Self-supervised learning for depth estimation possesses several advantages over supervised learning. The benefits of no need for ground-truth depth, online fine-tuning, and better generalization with unlimited data attract researchers to…

Recently, there are emerging many stereo matching methods for autonomous driving based on unsupervised learning. Most of them take advantage of reconstruction losses to remove dependency on disparity groundtruth. Occlusion handling is a…

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 model with the predicted…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Iterative-based methods have become mainstream in stereo matching due to their high performance. However, these methods heavily rely on labeled data and face challenges with unlabeled real-world data. To this end, we propose a…

Stripe-like space target detection (SSTD) is crucial for space situational awareness. Traditional unsupervised methods often fail in low signal-to-noise ratio and variable stripe-like space targets scenarios, leading to weak generalization.…

Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to…

Current self-supervised methods for monocular depth estimation are largely based on deeply nested convolutional networks that leverage stereo image pairs or monocular sequences during a training phase. However, they often exhibit inaccurate…

Image-based 3D detection is an indispensable component of the perception system for autonomous driving. However, it still suffers from the unsatisfying performance, one of the main reasons for which is the limited training data.…

Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via…

Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's prediction (i.e. the pseudo-parallel data). While self-training…

Despite recent improvement of supervised monocular depth estimation, the lack of high quality pixel-wise ground truth annotations has become a major hurdle for further progress. In this work, we propose a new unsupervised depth estimation…

Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human…

Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…

Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to…

This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1…

Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…