Recent years have witnessed the breakthrough success of deep convolutional neural networks (DCNNs) in image classification and other vision applications. Although freeing users from the troublesome handcrafted feature extraction by providing a uniform feature extraction-classification framework, DCNNs still require a handcrafted design of their architectures. In this paper, we propose the genetic DCNN designer, an autonomous learning algorithm can generate a DCNN architecture automatically based on the data available for a specific image classification problem. We first partition a DCNN into multiple stacked meta convolutional blocks and fully connected blocks, each containing the operations of convolution, pooling, fully connection, batch normalization, activation and drop out, and thus convert the architecture into an integer vector. Then, we use refined evolutionary operations, including selection, mutation and crossover to evolve a population of DCNN architectures. Our results on the MNIST, Fashion-MNIST, EMNIST-Digit, EMNIST-Letter, CIFAR10 and CIFAR100 datasets suggest that the proposed genetic DCNN designer is able to produce automatically DCNN architectures, whose performance is comparable to, if not better than, that of stateof-the-art DCNN models.

Abstract-Feature selection has always been a critical step in pattern recognition, in which evolutionary algorithms, such as the genetic algorithm (GA), are most commonly used. However, the individual encoding scheme used in various GAs would either pose a bias on the solution or require a pre-specified number of features, and hence may lead to less accurate results. In this paper, a tribe competition-based genetic algorithm (TCbGA) is proposed for feature selection in pattern classification. The population of individuals is divided into multiple tribes, and the initialization and evolutionary operations are modified to ensure that the number of selected features in each tribe follows a Gaussian distribution. Thus each tribe focuses on exploring a specific part of the solution space. Meanwhile, tribe competition is introduced to the evolution process, which allows the winning tribes, which produce better individuals, to enlarge their sizes, i.e. having more individuals to search their parts of the solution space. This algorithm, therefore, avoids the bias on solutions and requirement of a pre-specified number of features. We have evaluated our algorithm against several state-of-the-art feature selection approaches on 20 benchmark datasets. Our results suggest that the proposed TCbGA algorithm can identify the optimal feature subset more effectively and produce more accurate pattern classification.

No abstract

Deep learning-based face restoration models, increasingly prevalent in smart devices, have become targets for sophisticated backdoor attacks. These attacks, through subtle trigger injection into input face images, can lead to unexpected restoration outcomes. Unlike conventional methods focused on classification tasks, our approach introduces a unique degradation objective tailored for attacking restoration models. Moreover, we propose the Adaptive Selective Frequency Injection Backdoor Attack (AS-FIBA) framework, employing a neural network for input-specific trigger generation in the frequency domain, seamlessly blending triggers with benign images. This results in imperceptible yet effective attacks, guiding restoration predictions towards subtly degraded outputs rather than conspicuous targets. Extensive experiments demonstrate the efficacy of the degradation objective on state-of-the-art face restoration models. Additionally, it is notable that AS-FIBA can insert effective backdoors that are more imperceptible than existing backdoor attack methods, including WaNet, ISSBA, and FIBA.

BackgroundsDiabetic retinopathy (DR) is a common diabetic ocular disease characterized by retinal ganglion cell (RGC) changes. An abnormal environment, hyperglycemia, may progressively alter the structure and function of RGCs, which is a primary pathological feature of retinal neurodegeneration in DR. Accumulated studies confirmed autophagy and senescence play a vital role in DR; however, the underlying mechanisms need to be clarified.MethodsThis study included the microarray expression profiling dataset GSE60436 from Gene Expression Omnibus (GEO) to conduct the bioinformatics analysis. The R software was used to identify autophagy-related genes (ARGs) that were differentially expressed in fibrovascular membranes (FVMs) and normal retinas. Co-expression and tissue-specific expression were elicited for the filtered genes. The genes were then analyzed by ontology (GO) enrichment analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis and Gene Set Enrichment Analysis (GSEA). R28 cells were cultured with high glucose, detected by reverse transcription-quantitative (RT-qPCR) and stained by apoptosis kit.ResultsIn the retina, 31 differentially expressed ARGs (24 up-regulated genes) were discovered and enriched. The enrichment results revealed that differentially expressed ARGs were significantly enriched in autophagy, apoptosis, aging, and neural function. Four hub genes (i.e., TP53, CASP1, CCL2, and CASP1) were significantly up-regulated. Upregulation of cellular autophagy and apoptosis level was detected in the hyperglycemia model in vitro.ConclusionsOur results provide evidence for the autophagy and cellular senescence mechanisms involved in retinal hyperglycemia injury, and the protective function of autophagy is limited. Further study may favour understanding the disease progression and neuroprotection of DR.