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.     

Twining Poly(polyoxometalate) Chains into Nanoropes

Organic polymers and inorganic clusters belong to two different disciplines and have completely different properties and structures. When a cluster is attached to the backbone of a polymer as a pendant, the resultant hybrid polymers (polyclusters) exhibit unique behaviours totally different from those of conventional polymers owing to the nanoscale size of the cluster and its particular interactions. Herein, the aggregation of a poly(polyoxometalate)—a polynorbornene backbone with inorganic polyoxometalate cluster pendants—upon addition of a non-solvent to its dilute solution is reported. A three-dimensional network of tangled and snake-like nanothreads was observed. Direct visualisation of individual nanoscale clusters enabled identification of single chains within the nanothreads. These observations suggest that during the process of aggregation, the hybrid polymer forms curved or extended chains as a consequence of an armouring effect in which the collapsed cluster pendants wrap around the backbone. The collapse occurs because they become less soluble in the solvent/non-solvent mixture. The extended chains then become entwined and form nanoropes consisting of multiple chains wound around each other. This study provides a deeper understanding of the nature of polyclusters and should also prove useful for their future development and application.     

Attribute Allocation and Retrieval Scheme for Large-Scale Sensor Networks

Wireless sensor network is an emerging technology that enables remote monitoring of large geographical regions. In this paper, we address the problem of distributing attributes over such a large-scale sensor network so that the cost of data retrieval is minimized. The proposed scheme is a data-centric storage scheme where the attributes are distributed over the network depending on the correlations between them. The problem addressed here is similar to the Allocation Problem of distributed databases. In this paper, we have defined the Allocation Problem in the context of sensor networks and have proposed a scheme for finding a good distribution of attributes to the sensor network. We also propose an architecture for query processing given such a distribution of attributes. We analytically determine the conditions under which the proposed architecture is beneficial and present simulation results to demonstrate the same. To the best of our knowledge, this is the first attempt to determine an allocation of attributes over a sensor network based on the correlations between attributes.     

分子聚集理论在医药学研究中的应用

本文利用聚集型状态方程，克拉贝龙方程以及临界条件推出聚集活性参量方程．分析结果表明，医药的药理活性是可以用聚集活性参量予以定量表征．本文给出了某些医药的主要的药物成分，如氧化亚氮 乙醚、氯仿和水杨酸甲酯等嘛醉剂），一氧化氮（硝酸甘油）、乙醇胺（医药活性剂）和多巴胺（神经递质）的生物活性数据．实践经验表明，这些化学品分别在生命体的心血管系统、神经系统和免疫系统中起着重要的药理功能作用．这表明，本文研究的内容在医药学研究领域有其重要意义．     

Dependence of the kinetics of the anionic polymerization of methyl methacrylate on the concentration in active centers

Studies on the anionic polymerization of methyl methacrylate in tetrahydrofuran and in the presence of sparteine have revealed a beneficial effect due to this additive, resulting in a decrease in the extent of termination. Better control of the definition of the polymers formed can thus be achieved in the presence of this additive. On the other hand, macromolecular engineering requires a range of active species concentrations lower than 10^?3 mol L^?1 and particularly the synthesis of polymers of high molar masses. For a better understanding of the mechanism of chain growth under such concentration conditions, the kinetics of polymerization have been investigated with a technique based on adiabatic calorimetry. Sparteine has been found to lack sufficient cation‐binding power to prevent the propagating enolate ion pairs from aggregating. The rate constant of propagation of nonaggregated species has been estimated, as well as the aggregation constant of equilibrium. For very low initiator concentrations, termination reactions have been shown to profoundly alter the control of the polymerization and to prevent a quantitative monomer conversion. Theoretical maximal conversions have been calculated from kinetic data and compare well with the experimental values. © 2004 Wiley Periodicals, Inc. J Polym Sci Part A: Polym Chem 42: 4964–4975, 2004     

Iterative variable aggregation and disaggregation in IP: An application

This paper, using the Unconstrained Shape Matrix Optimization Problem as a test bed, we investigate various aspects of variable aggregation and disaggregation for a class of integer programs that contains binary expansion. We present theoretical and numerical results, and propose an iterative algorithm for exact solutions.     

Prefiltration technique via aggregation for constructing low‐density high‐quality factorized sparse approximate inverse preconditionings

This paper considers a new approach to a priori sparsification of the sparsity pattern of the factorized approximate inverses (FSAI) preconditioner using the so‐called vector aggregation technique. The suggested approach consists in construction of the FSAI preconditioner to the aggregated matrix with a prescribed sparsity pattern. Then small entries of the computed ‘aggregated’ FSAI preconditioning matrix are dropped, and the resulting pointwise sparsity pattern is used to construct the low‐density block sparsity pattern of the FSAI preconditioning matrix to the original matrix. This approach allows to minimize (sometimes significantly) the construction costs of low‐density high‐quality FSAI preconditioners. Numerical results with sample matrices from structural mechanics and thin shell problems are presented. Copyright © 2002 John Wiley & Sons, Ltd.     

Physicochemical studies on hydrophobic PEO‐PPO‐PEO triblock copolymer micelles in SDS micellar environment

The shape, size, aggregation, hydration, and correlation times of water insoluble PEO‐PPO‐PEO triblock copolymer micelles with sodium dodecylsulfate (SDS) micelles were investigated using transport studies and dynamic light scattering technique. From the conductance of micellar solutions of the polymer in 25 mM SDS and 5 mM NaCl, the hydration of polymer micelles were determined using the principle of obstruction of electrolyte migration by the polymer. The asymmetry of the micellar particles of polymer and polymer‐SDS mixed micellar systems in 5 mM NaCl and their average axial ratios were calculated using intrinsic viscosity and hydration data obeying Simha–Einstein equation. Hydration number and micellar sizes were variable with temperature. The shape of the polymer micelles has been ellipsoidal rather than spherical. The micellar volume, hydrodynamic radius, radius of gyration, diffusional coefficients as well as translational, rotational and effective correlation times have been calculated from the absolute values of the axes. The partial molal volume of polymer micelles has also been determined and its comparison with the molar volume of pure polymer suggested a volume contraction due to immobilization of the water phase by the hydrophilic head groups of the polymer. The thermodynamic activation parameters for viscous flow favor a more ordered water structure around polymer micelles at higher temperatures. © 2007 Wiley Periodicals, Inc. J Polym Sci Part B: Polym Phys 45: 2410–2420, 2007