Construction of CdS@g-C3N4 heterojunction photocatalyst for highly efficient degradation of gaseous toluene.

Exploring efficient photocatalysts for the degradation of VOCs under visible light is a challenge. CdS@g-C3N4 heterojunction photocatalytic materials were developed in this study using a microwave-assisted sol-gel process. CdS@g-C3N4(0.2) photocatalyzed the maximum degradation of gaseous toluene under visible light irradiation, and the time required to achieve the same degradation rate was reduced by 270 min when compared to pure CdS. The morphological characterization, photoelectric property analysis, and DFT calculations all verified that the CdS nanoparticles were uniformly disseminated on the surface of g-C3N4, and that the interfaces were closely contacted to form a heterojunction interface with a built-in field. This enhances charge transfer from CdS to g-C3N4 while successfully decreasing electron-hole pair recombination caused by light. Furthermore, the energy band structure was altered to absorb longer wavelengths of light and extend the absorption spectral range, improving the photocatalytic material's efficacy for broad-spectrum light such as sunshine. This paper proposes methods for predicting and optimizing the surface structure of catalysts, as well as developing high-performance multi-heterojunction photocatalysts for the degradation of indoor VOCs.

Diverse Sample Generation: Pushing the Limit of Generative Data-Free Quantization.

Generative data-free quantization emerges as a practical compression approach that quantizes deep neural networks to low bit-width without accessing the real data. This approach generates data utilizing batch normalization (BN) statistics of the full-precision networks to quantize the networks. However, it always faces the serious challenges of accuracy degradation in practice. We first give a theoretical analysis that the diversity of synthetic samples is crucial for the data-free quantization, while in existing approaches, the synthetic data completely constrained by BN statistics experimentally exhibit severe homogenization at distribution and sample levels. This paper presents a generic Diverse Sample Generation (DSG) scheme for the generative data-free quantization, to mitigate detrimental homogenization. We first slack the statistics alignment for features in the BN layer to relax the distribution constraint. Then, we strengthen the loss impact of the specific BN layers for different samples and inhibit the correlation among samples in the generation process, to diversify samples from the statistical and spatial perspectives, respectively. Comprehensive experiments show that for large-scale image classification tasks, our DSG can consistently quantization performance on different neural architectures, especially under ultra-low bit-width. And data diversification caused by our DSG brings a general gain to various quantization-aware training and post-training quantization approaches, demonstrating its generality and effectiveness.

BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance.

Deep neural networks, such as the deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network compression technologies such as binarization are studied to deploy KWS models on edge. In this article, we present a strong yet efficient binary neural network for KWS, namely, BiFSMNv2, pushing it to the real-network accuracy performance. First, we present a dual-scale thinnable 1-bit-architecture (DTA) to recover the representation capability of the binarized computation units by dual-scale activation binarization and liberate the speedup potential from an overall architecture perspective. Second, we also construct a frequency-independent distillation (FID) scheme for KWS binarization-aware training, which distills the high-and low-frequency components independently to mitigate the information mismatch between full-precision and binarized representations. Moreover, we propose the learning propagation binarizer (LPB), a general and efficient binarizer that enables the forward and backward propagation of binary KWS networks to be continuously improved through learning. We implement and deploy BiFSMNv2 on ARMv8 real-world hardware with a novel fast bitwise computation kernel (FBCK), which is proposed to fully use registers and increase instruction throughput. Comprehensive experiments show our BiFSMNv2 outperforms the existing binary networks for KWS by convincing margins across different datasets and achieves comparable accuracy with the full-precision networks (only a tiny 1.51% drop on Speech Commands V1-12). We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25.1 × speedup and 20.2 × storage-saving on edge hardware.