Search

Numerous methods have been proposed for person re-identification (Re-ID) with promising performances. While most of them neglect the matching efficiency which is crucial in real-world applications. Recently, several hashing based approaches have been developed, which consider the importance of matching speed in large-scale datasets. Despite the considerable efficiency of these traditional and deep learning based hashing methods, the concomitant matching accuracy reduction is unacceptable in practical application. Towards this end, we propose a novel deep hashing framework, namely Consistency-Preserving Deep Hashing (CPDH), aiming to bridge the gap between the effective high-dimensional feature and low-dimensional binary vector by focusing on the consistency preservation of hash code. First, CPDH designs a new hash structure to extract the hash code. Next, a noise consistency cost is proposed to improve robustness of both hash code and high-dimensional feature. Finally, a topology consistency cost is provided to maintain the ordinal relation between the high-dimensional feature space and Hamming space. Comprehensive experimental results on three widely-used benchmark datasets demonstrate the superior performance of proposed method as compared with existing state-of-the-art approaches.

Class-incremental learning (CIL) aims to incrementally learn a unified classifier for new classes emerging, which suffers from the catastrophic forgetting problem. To alleviate forgetting and improve the recognition performance, we propose a novel CIL framework, named the topological schemas model (TSM). TSM consists of a Gaussian mixture model arranged on 2D grids (2D-GMM) as the memory of the learned knowledge. To train the 2D-GMM model, we develop a novel competitive expectation-maximization (CEM) method, which contains a global topology embedding step and a local expectation-maximization fine-tuning step. Meanwhile, we choose the image samples of old classes that have the maximum posterior probability with respect to each Gaussian distribution as the episodic points. When finetuning for new classes, we propose the memory preservation loss (MPL) term to ensure episodic points still have maximum probabilities with respect to the corresponding Gaussian distribution. MPL preserves the distribution of 2D-GMM for old knowledge during incremental learning and alleviates catastrophic forgetting. Comprehensive experimental evaluations on two popular CIL benchmarks CIFAR100 and subImageNet demonstrate the superiority of our TSM.

The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates the forgetting of the old classes by stabilizing NG's topology and improves the representation learning for few-shot new classes by growing and adapting NG to new training samples. Comprehensive experimental results demonstrate that our proposed method significantly outperforms other state-of-the-art class-incremental learning methods on CIFAR100, miniImageNet, and CUB200 datasets., Accepted by CVPR 2020 (oral)

A well-known issue for class-incremental learning is the catastrophic forgetting phenomenon, where the network’s recognition performance on old classes degrades severely when incrementally learning new classes. To alleviate forgetting, we put forward to preserve the old class knowledge by maintaining the topology of the network’s feature space. On this basis, we propose a novel topology-preserving class-incremental learning (TPCIL) framework. TPCIL uses an elastic Hebbian graph (EHG) to model the feature space topology, which is constructed with the competitive Hebbian learning rule. To maintain the topology, we develop the topology-preserving loss (TPL) that penalizes the changes of EHG’s neighboring relationships during incremental learning phases. Comprehensive experiments on CIFAR100, ImageNet, and subImageNet datasets demonstrate the power of the TPCIL for continuously learning new classes with less forgetting. The code will be released.

In-field molecular diagnosis of plant diseases via nucleic acid amplification is currently limited by cumbersome protocols for extracting and isolating pathogenic DNA from plant tissues. To address this challenge, a rapid plant DNA extraction method was developed using a disposable polymeric microneedle (MN) patch. By applying MN patches on plant leaves, amplification-assay-ready DNA can be extracted within a minute from different plant species. MN-extracted DNA was used for direct polymerase chain reaction amplification of plant plastid DNA without purification. Furthermore, using this patch device, extraction of plant pathogen DNA ( Phytophthora infestans) from both laboratory-inoculated and field-infected leaf samples was performed for detection of late blight disease in tomato. MN extraction achieved 100% detection rate of late blight infections for samples after 3 days of inoculation when compared to the conventional gold standard cetyltrimethylammonium bromide (CTAB)-based DNA extraction method and 100% detection rate for all blind field samples tested. This simple, cell-lysis-free, and purification-free DNA extraction method could be a transformative approach to facilitate rapid sample preparation for molecular diagnosis of various plant diseases directly in the field.

Semi-supervised learning is important and has become more widespread because obtaining labeled data is expensive and labor-intensive. In this paper, we focus on the challenging semi-supervised person Re-identification (ReID) task, which is a metric learning problem based on the assumption that unlabeled data is open-set. To address this problem, we propose the Transductive Semi-Supervised Metric Learning (TSSML) framework. In TSSML, we propose a graph-based transductive hard mining method for deeply mining hard triplets in unlabeled data and a degree-based relationship confidence scoring method for further reducing incorrect triplets. Moreover, we investigate the feature consistency loss (FCL) and adopt the curriculum learning strategy to improve the representation learning for semi-supervised ReID. Extensive experiments have been conducted on three large-scale ReID datasets and demonstrate the effectiveness of our TSSML framework.

Metal chemical fractions obtained by optimized BCR three-stage extraction procedure and multivariate analysis techniques were exploited for assessing 7 heavy metals (Cr, Pb, Cd, Co, Cu, Zn and Ni) in sediments from Gansu province, Ningxia and Inner Mongolia Autonomous Regions of the Yellow River in Northern China. The results indicated that higher susceptibility and bioavailability of Cr and Cd with a strong anthropogenic source were due to their higher availability in the exchangeable fraction. A portion of Pb, Cd, Co, Zn, and Ni in reducible fraction may be due to the fact that they can form stable complexes with Fe and Mn oxides. Substantial amount of Pb, Co, Ni and Cu was observed as oxidizable fraction because of their strong affinity to the organic matters so that they can complex with humic substances in sediments. The high geo-accumulation indexes (I(geo)) for Cr and Cd showed their higher environmental risk to the aquatic biota. Principal component analysis (PCA) revealed that high toxic Cr and Cd in polluted sites (Cd in S10, S11 and Cr in S13) may be contributed to anthropogenic sources, it was consistent with the results of dual hierarchical clustering analysis (DHCA), which could give more details about contributing sources.