In the letter, we propose a novel yet effective knowledge distillation scheme which mimics an all-round learning process of an excellent student from the teacher, i.e, knowledge review, knowledge preview, and knowledge correction, to acquire more informative and complementary knowledge. In the newly proposed method, to better leverage comprehensive feature knowledge from the teacher model, we propose Knowledge Review and Knowledge Preview Distillation to amalgamate multi-level features from different intermediate layers in both forward and backward pathways and fully distill them through hierarchical context loss, which greatly improves the student's feature learning efficiency. Moreover, we further present a Response Correction Mechanism to reinforce the prediction of student, which can more fully excavate the student's own knowledge, effectively alleviating the negative influence caused by the knowledge gap between the teacher and the student. We verify the effectiveness of our method with various networks on the CIFAR-100 datasets and the proposed method achieves competitive results compared with other state-of-the-art competitors. The code will be available athttps://github.com/kbzhang0505/RPC.

In this paper, we establish that the rate region of a large class of IEEE 802.11 mesh networks is log-convex, immediately allowing standard utility fairness methods to be generalized to this class of networks. This creates a solid theoretical underpinning for fairness analysis and resource allocation in this practically important class of networks. For the special case of max-min fairness, we use this new insight to obtain an almost complete characterization of the fair rate allocation and a remarkably simple, practically implementable method for achieving max-min fairness in 802.11 mesh networks.

We consider achieving max-min fairness in 802.11e based multi-hop wireless networks. We propose an approach which makes use of the TXOP mechanism in combination with an automatic contention window size tuning algorithm based on channel state sensing. Simulation results show that the proposed approach can provide a good approximation to per-flow max-min fairness and that this is achieved regardless of the active number of flows and when the channel is noisy.

Computed tomography (CT) systems have the ability to rapidly and nondestructively produce images of both exterior and interior surfaces and regions. Because CT images are densitometrically accurate, complete morphological and part characterization information can be obtained without need of physical sectioning. CT data can be processed to create computer-aided design (CAD) representations of the part, to extract dimensional measurement, or to detect, size and locate defects. The key image processing steps which are required both for CT-assisted reverse engineering and CT-assisted part characterization are examined. Two desirable characteristics of the underlying image processing algorithms are accuracy of the produced results and the ability to handle large volumetric images of complex parts.