In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation. The motivation behind it comes from the statistic observation that pattern-affinitive pairs recur much frequently across different tasks as well as within a task. Thus, we can conduct two types of propagations, cross-task propagation and task-specific propagation, to adaptively diffuse those similar patterns. The former integrates cross-task affinity patterns to adapt to each task therein through the calculation on non-local relationships. Next the latter performs an iterative diffusion in the feature space so that the cross-task affinity patterns can be widelyspread within the task. Accordingly, the learning of each task can be regularized and boosted by the complementary task-level affinities. Extensive experiments demonstrate the effectiveness and the superiority of our method on the joint three tasks. Meanwhile, we achieve the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.
Online depth learning is the problem of consistently adapting a depth estimation model to handle a continuously changing environment. This problem is challenging due to the network easily overfits on the current environment and forgets its past experiences. To address such problem, this paper presents a novel Learning to Prevent Forgetting (LPF) method for online mono-depth adaptation to new target domains in unsupervised manner. Instead of updating the universal parameters, LPF learns adapter modules to efficiently adjust the feature representation and distribution without losing the pre-learned knowledge in online condition. Specifically, to adapt temporal-continuous depth patterns in videos, we introduce a novel meta-learning approach to learn adapter modules by combining online adaptation process into the learning objective. To further avoid overfitting, we propose a novel temporal-consistent regularization to harmonize the gradient descent procedure at each online learning step. Extensive evaluations on realworld datasets demonstrate that the proposed method, with very limited parameters, significantly improves the estimation quality.
False data injection (FDI) attack is a hot topic in large-scale Cyber-Physical Systems (CPSs), which can cause bad state estimation of controllers. In this paper, we focus on FDI detection on transmission lines of the smart grid. We propose a novel and effective detection framework to identify FDI attacks. Different from the previous methods, there are multi-tier detectors which utilize edge nodes such as the programmable logic controllers (PLCs) instead of the central controller to detect attacks. The proposed framework can decrease the transmission time of data to reduce the latency of decisions because many sensory data need not be transmitted to the central controller for detection. We also develop a detection algorithm which utilizes classifiers based on machine learning to identify FDI. The training process is split from every edge node and is placed on the central node. The detectors are lightweight and are properly adopted in our detection framework. Our simulation experiments show that the proposed detection framework can provide better detection results than the existing detection approaches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.