YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

低压静电场辅助冷冻对竹笋品质的影响

为研究低压静电场辅助冷冻对竹笋冻结特性的影响，以冻结曲线、硬度、水分损失率、水分迁移、冰晶形态和组织微观结构为指标，探究低压静电场辅助冷冻（－35 ℃）和普通冷冻（－35 ℃）条件下竹笋品质的变化规律。结果表明：低压静电场辅助冷冻提高了冻结效率，改变了冰晶形态及分布，减轻了组织微观结构破损程度，改善了解冻汁液流失情况。与静电板间距10、20、30、40 cm处的冷冻竹笋解冻后水分损失率分别为14.16%、12.58%、9.73%、10.44%，显著低于对照组（21.01%）（P＜0.05），硬度分别为461.19、507.48、496.65 g和455.31 g，显著高于对照组（350.70 g）（P＜0.05）。低场核磁共振分析结果表明，在低压静电场辅助冷冻下竹笋解冻后汁液流失减少，扫描电子显微镜观察结果显示，竹笋纤维排列整齐，组织微观结构保持较好。低压静电场辅助冷冻可有效改善竹笋品质，可为利用低压静电场进行果蔬的冷冻贮藏和冷链运输提供参考。     

Machine fault diagnosis with small sample based on variational information constrained generative adversarial network

In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches.     

Superradiant Emission from Coherent Excitons in van Der Waals Heterostructures

Recent advancements in isolation and stacking of layered van der Waals materials have created an unprecedented paradigm for demonstrating varieties of 2D quantum materials. Rationally designed van der Waals heterostructures composed of monolayer transition-metal dichalcogenides (TMDs) and few-layer hBN show several unique optoelectronic features driven by correlations. However, entangled superradiant excitonic species in such systems have not been observed before. In this report, it is demonstrated that strong suppression of phonon population at low temperature results in a formation of a coherent excitonic-dipoles ensemble in the heterostructure, and the collective oscillation of those dipoles stimulates a robust phase synchronized ultra-narrow band superradiant emission even at extremely low pumping intensity. Such emitters are in high demand for a multitude of applications, including fundamental research on many-body correlations and other state-of-the-art technologies. This timely demonstration paves the way for further exploration of ultralow-threshold quantum-emitting devices with unmatched design freedom and spectral tunability.     

Agronomic performance of high oleic,low linolenic soybean in Tennessee

Soybean oil hydrogenation alters the linolenic acid molecule to prevent the oil from becoming rancid, however, health reports have indicated trans-fat caused by hydrogenation, is not generally regarded as safe. Typical soybeans contain approximately 80 g kg⁻¹ to 120 g kg⁻¹ linolenic acid and 240 g kg⁻¹ of oleic acid. In an effort to accommodate the need for high-quality oil, the United Soybean Board introduced an industry standard for a high oleic acid greater than 750 g kg⁻¹ and linolenic acid less than 30 g kg⁻¹ oil. By combing mutations in the soybean plant at four loci, FAD2-1A and FAD2-1B, oleate desaturase genes and FAD3A and FAD3C, linoleate desaturase genes, and seed oil will not require hydrogenation to prevent oxidation and produce high-quality oil. In 2017 and 2018, a study comparing four near-isogenic lines across multiple Tennessee locations was performed to identify agronomic traits associated with mutations in FAD3A and FAD3C loci, while holding FAD2-1A and FAD2-1B constant in the mutant (high oleic) state. Soybean lines were assessed for yield and oil quality based on mutations at FAD2-1 and FAD3 loci. Variations of wild-type and mutant genotypes were compared at FAD3A and FAD3C loci. Analysis using a generalized linear mixed model in SAS 9.4, indicated no yield drag or other negative agronomic traits associated with the high oleic and low linolenic acid genotype. All four mutations of fad2-1A, fad2-1B, fad3A, and fad3C were determined as necessary to produce a soybean with the new industry standard (>750 g kg⁻¹ oleic and <30 g kg⁻¹ linolenic acid) in a maturity group-IV-Late cultivar for Tennessee growers.     

2.3–21 GHz broadband and high linearity distributed low noise amplifier

This paper focuses on the design of a 2.3–21 GHz Distributed Low Noise Amplifier (LNA) with low noise figure (NF), high gain (S₂₁), and high linearity (IIP3) for broadband applications. This distributed amplifier (DA) includes S/C/X/Ku/K-band, which makes it very suitable for heterodyne receivers. The proposed DA uses a 0.18 μm GaAs pHEMT process (OMMIC ED02AH) in cascade architecture with lines adaptation and equalization of phase velocity techniques, to absorb their parasitic capacitances into the gate and drain transmission lines in order to achieve wide bandwidth and to enhance gain and linearity. The proposed broadband DA achieved an excellent gain in the flatness of 13.5 ± 0.2 dB, a low noise figure of 3.44 ± 1.12 dB, and a small group delay variation of ±19.721 ps over the range of 2.3–21 GHz. The input and output reflection coefficients S₁₁ and S₂₂ are less than −10 dB. The input compression point (P_1dB) and input third-order intercept point (IIP3) are −1.5 dBm and 11.5 dBm, respectively at 13 GHz. The dissipated power is 282 mW and the core layout size is 2.2 × 0.8 mm².     

中低温煤焦油基炭微球的制备

通过馏分切割、温和加氢相结合对中低温煤焦油进行精制处理，精制后的原料采用分级热聚制备中间相炭微球。考察了精制处理条件对原料性质、中间相炭微球宏观外貌及微晶结构的影响。采用FTIR、GC-MS、族组成、元素分析对原料进行表征，采用SEM、XRD对中间相炭微球进行表征。结果表明：中低温煤焦油中300～430℃馏分油是制备中间相炭微球的较佳馏分。300～430℃馏分油中正庚烷可溶物（HS）质量分数高达84.76%，吡啶不溶物（PI）质量分数低至0.23%，杂原子含量低，芳烃化合物的环数为2～4环。300～430℃馏分油在T_H=350℃、p=8MPa、t=1.5h、剂油比1∶40（质量比）的条件下温和加氢得到的精制原料，经420℃热聚6h得制备的中间相炭微球宏观外貌、微晶结构较好。中低温煤焦油基炭微球的粒径范围为5～15μm，小球表面光滑，微观结构为地球仪型，经1450℃高温煅烧后，石墨化度达到12.33%。     

喷油方式对斜齿轮齿面温度的影响

为探讨喷油方式对齿面温度的影响，以斜齿轮为研究对象，通过CFD仿真和试验研究不同喷油方式对斜齿轮齿面温度的影响。针对斜齿轮喷油润滑过程的特点，分析其齿面摩擦生热量，简化轮齿喷油润滑计算模型，并基于CFX进行齿面对流换热仿真研究，得到了不同喷油方式下的齿面温度；基于功率开放式斜齿轮试验平台，对不同喷油方式下的齿面温度进行了试验测量，与仿真计算结果进行对比分析。结果表明：在高速重载斜齿轮传动系统中，啮出侧喷油润滑的方式比啮入侧喷油润滑方式的冷却降温效果要好。     

多先验融合的图像显著性目标检测算法

为了更加准确地检测出图像中的显著性目标，提出了多先验融合的显著性目标检测算法。针对传统中心先验对偏离图像中心的显著性目标会出现检测失效的情况，提出在多颜色空间下求显著性目标的最小凸包交集来确定目标的大致位置，以凸包区域中心计算中心先验。同时通过融合策略将凸包区域中心先验、颜色对比先验和背景先验融合并集成到特征矩阵中。最后通过低秩矩阵恢复模型生成结果显著图。在公开数据集MSRA1000和ESSCD上的仿真实验结果表明，MPLRR能够得到清晰高亮的显著性目标视觉效果图，同时F，AUC，MAE等评价指标也比现有的许多方法有明显提升。