Related papers: ADU-Depth: Attention-based Distillation with Uncer…
Monocular depth estimation plays a crucial role in 3D recognition and understanding. One key limitation of existing approaches lies in their lack of structural information exploitation, which leads to inaccurate spatial layout,…
Depth completion involves predicting dense depth maps from sparse LiDAR inputs. However, sparse depth annotations from sensors limit the availability of dense supervision, which is necessary for learning detailed geometric features. In this…
Knowledge distillation has emerged as a powerful technique for model compression, enabling the transfer of knowledge from large teacher networks to compact student models. However, traditional knowledge distillation methods treat all…
Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a…
We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge…
Knowledge Distillation (KD) is a strategy for the definition of a set of transferability gangways to improve the efficiency of Convolutional Neural Networks. Feature-based Knowledge Distillation is a subfield of KD that relies on…
Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned…
Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…
Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackle this, a few recent studies have proposed to supervise the…
Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view…
Monocular depth estimation has become one of the most studied applications in computer vision, where the most accurate approaches are based on fully supervised learning models. However, the acquisition of accurate and large ground truth…
Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in…
Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult.…
3D object detection is a fundamental and challenging task for 3D scene understanding, and the monocular-based methods can serve as an economical alternative to the stereo-based or LiDAR-based methods. However, accurately detecting objects…
Knowledge distillation based on student-teacher network is one of the mainstream solution paradigms for the challenging unsupervised Anomaly Detection task, utilizing the difference in representation capabilities of the teacher and student…
Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart. In these methods, the masked regions need to be properly selected, such…
Self-supervised learning has shown very promising results for monocular depth estimation. Scene structure and local details both are significant clues for high-quality depth estimation. Recent works suffer from the lack of explicit modeling…
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…
Depth information is the foundation of perception, essential for autonomous driving, robotics, and other source-constrained applications. Promptly obtaining accurate and efficient depth information allows for a rapid response in dynamic…
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…