5 July 2018 in International Journal of Pavement Engineering
Based on the indoor crack monitoring test, the feasibility of monitoring base crack with sensing optical fibre and the appropriate optical fibre category are studied in detail. Through the field monitoring test of cement stabilised macadam, the crack development law in the early stage of cement stabilised base layer was researched. The test results show that the proposed sensing fibre can be used in researching the crack development law of cement stabilised macadam base. The initiation of crack in cement stabilised macadam base occurs mainly in the first 3 days after construction, in which the dry shrinkage crack is dominant. The development of the dry shrinkage probably ended in about 30 days. The dry shrinkage stress is the main factor of crack initiation and crack spacing. The influence of thermal stress on early crack spacing is very weak, and the thermal stress strongly affects the crack width. The thermal cracks basically appear in the location where the dry shrinkage stress displays peaks during the dry shrinkage phase. When the subbase and base layers were constructed continuously, the transverse cracks in cement stabilised macadam are always penetrating cracks.
13 November 2020 in International Journal of Pavement Research and Technology
14 January 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Few-Shot Class-Incremental Learning (FSCIL) has gained considerable attention in recent years for its pivotal role in addressing continuously arriving classes. However, it encounters additional challenges. The scarcity of samples in new sessions intensifies overfitting, causing incompatibility between the output features of new and old classes, thereby escalating catastrophic forgetting. A prevalent strategy involves mitigating catastrophic forgetting through the Explicit Memory (EM), which comprise of class prototypes. However, current EM-based methods retrieves memory globally by performing Vector-to-Vector (V2V) interaction between features corresponding to the input and prototypes stored in EM, neglecting the geometric structure of local features. This hinders the accurate modeling of their positional relationships. To incorporate information of local geometric structure, we extend the V2V interaction to Graph-to-Graph (G2G) interaction. For enhancing local structures for better G2G alignment and the prevention of local feature collapse, we propose the Local Graph Preservation (LGP) mechanism. Additionally, to address sample scarcity in classes from new sessions, the Contrast-Augmented G2G (CAG2G) is introduced to promote the aggregation of same class features thus helps few-shot learning. Extensive comparisons on CIFAR100, CUB200, and the challenging ImageNet-R dataset demonstrate the superiority of our method over existing methods.
15 April 2024 in IEEE Signal Processing Letters
From the perspective of information bottleneck (IB) theory, we propose a novel framework for performing black-box transferable adversarial attacks named IBTA, which leverages advancements in invariant features. Intuitively, diminishing the reliance of adversarial perturbations on the original data, under equivalent attack performance constraints, encourages a greater reliance on invariant features that contributes most to classification, thereby enhancing the transferability of adversarial attacks. Building on this motivation, we redefine the optimization of transferable attacks using a novel theoretical framework that centers around IB. Specifically, to overcome the challenge of unoptimizable mutual information, we propose a simple and efficient mutual information lower bound (MILB) for approximating computation. Moreover, to quantitatively evaluate mutual information, we utilize the Mutual Information Neural Estimator (MINE) to perform a thorough analysis. Our experiments on the ImageNet dataset well demonstrate the efficiency and scalability of IBTA and derived MILB. Our code is available at github.com/IBTA.