搜索结果：tiny

Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory results on tiny objects due to the lack of appearance information. Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors. To alleviate this, we propose a new evaluation metric using Wasserstein distance for tiny object detection. Specifically, we first model the bounding boxes as 2D Gaussian distributions and then propose a new metric dubbed Normalized Wasserstein Distance (NWD) to compute the similarity between them by their corresponding Gaussian distributions. The proposed NWD metric can be easily embedded into the assignment, non-maximum suppression, and loss function of any anchor-based detector to replace the commonly used IoU metric. We evaluate our metric on a new dataset for tiny object detection (AI-TOD) in which the average object size is much smaller than existing object detection datasets. Extensive experiments show that, when equipped with NWD metric, our approach yields performance that is 6.7 AP points higher than a standard fine-tuning baseline, and 6.0 AP points higher than state-of-the-art competitors. Codes are available at: https://github.com/jwwangchn/NWD.

APETALA2/ETHYLENE RESPONSIVE FACTOR (AP2/ERF) family transcription factors have well-documented functions in stress responses, but their roles in brassinosteroid (BR)-regulated growth and stress responses have not been established. Here, we show that the Arabidopsis (Arabidopsis thaliana) stress-inducible AP2/ERF transcription factor TINY inhibits BR-regulated growth while promoting drought responses. TINY-overexpressing plants have stunted growth, increased sensitivity to BR biosynthesis inhibitors, and compromised BR-responsive gene expression. By contrast, tiny tiny2 tiny3 triple mutants have increased BR-regulated growth and BR-responsive gene expression. TINY positively regulates drought responses by activating drought-responsive genes and promoting abscisic acid–mediated stomatal closure. Global gene expression studies revealed that TINY and BRs have opposite effects on plant growth and stress response genes. TINY interacts with and antagonizes BRASSINOSTERIOID INSENSITIVE1-ETHYL METHANESULFONATE SUPRESSOR1 (BES1) in the regulation of these genes. Glycogen synthase kinase 3-like protein kinase BR-INSENSITIVE2 (BIN2), a negative regulator in the BR pathway, phosphorylates and stabilizes TINY, providing a mechanism for BR-mediated downregulation of TINY to prevent activation of stress responses under optimal growth conditions. Taken together, our results demonstrate that BR signaling negatively regulates TINY through BIN2 phosphorylation and TINY positively regulates drought responses, as well as inhibiting BR-mediated growth through TINY-BES1 antagonistic interactions. Our results thus provide insight into the coordination of BR-regulated growth and drought responses.

In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform previous tasks. One way to endow the learner the ability to perform tasks seen in the past is to store a small memory, dubbed episodic memory, that stores few examples from previous tasks and then to replay these examples when training for future tasks. In this work, we empirically analyze the effectiveness of a very small episodic memory in a CL setup where each training example is only seen once. Surprisingly, across four rather different supervised learning benchmarks adapted to CL, a very simple baseline, that jointly trains on both examples from the current task as well as examples stored in the episodic memory, significantly outperforms specifically designed CL approaches with and without episodic memory. Interestingly, we find that repetitive training on even tiny memories of past tasks does not harm generalization, on the contrary, it improves it, with gains between 7\% and 17\% when the memory is populated with a single example per class.

April 8, 2009Groups at MIT and NYU have collected a dataset of millions of tiny colour images from the web. It is, in principle, an excellent dataset for unsupervised training of deep generative models, but previous researchers who have tried this have found it di cult to learn a good set of lters from the images. We show how to train a multi-layer generative model that learns to extract meaningful features which resemble those found in the human visual cortex. Using a novel parallelization algorithm to distribute the work among multiple machines connected on a network, we show how training such a model can be done in reasonable time. A second problematic aspect of the tiny images dataset is that there are no reliable class labels which makes it hard to use for object recognition experiments. We created two sets of reliable labels. The CIFAR-10 set has 6000 examples of each of 10 classes and the CIFAR-100 set has 600 examples of each of 100 non-overlapping classes. Using these labels, we show that object recognition is signi cantly

Visual object detection has achieved unprecedented advance with the rise of deep convolutional neural networks. However, detecting tiny objects (for example tiny persons less than 20 pixels) in large-scale images remains not well investigated. The extremely small objects raise a grand challenge about feature representation while the massive and complex backgrounds aggregate the risk of false alarms. In this paper, we introduce a new benchmark, referred to as TinyPerson, opening up a promising direction for tiny object detection in a long distance and with massive backgrounds. We experimentally find that the scale mismatch between the dataset for network pre-training and the dataset for detector learning could deteriorate the feature representation and the detectors. Accordingly, we propose a simple yet effective Scale Match approach to align the object scales between the two datasets for favorable tiny-object representation. Experiments show the significant performance gain of our proposed approach over state-of-the-art detectors, and the challenging aspects of TinyPerson related to real-world scenarios. The TinyPerson benchmark and the code for our approach will be publicly available <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> .

Object detection in Earth Vision has achieved great progress in recent years. However, tiny object detection in aerial images remains a very challenging problem since the tiny objects contain a small number of pixels and are easily confused with the background. To advance tiny object detection research in aerial images, we present a new dataset for Tiny Object Detection in Aerial Images (AI-TOD). Specifically, AI-TOD comes with 700,621 object instances for eight categories across 28,036 aerial images. Compared to existing object detection datasets in aerial images, the mean size of objects in AI-TOD is about 12.8 pixels, which is much smaller than others. To build a benchmark for tiny object detection in aerial images, we evaluate the state-of-the-art object detectors on our AI-TOD dataset. Experimental results show that direct application of these approaches on AI-TOD produces suboptimal object detection results, thus new specialized detectors for tiny object detection need to be designed. Therefore, we propose a multiple center points based learning network (M-CenterNet) to improve the localization performance of tiny object detection, and experimental results show the significant performance gain over the competitors.

FPN-based detectors have made significant progress in general object detection, e.g., MS COCO and PASCAL VOC. However, these detectors fail in certain application scenarios, e.g., tiny object detection. In this paper, we argue that the top-down connections between adjacent layers in FPN bring two-side influences for tiny object detection, not only positive. We propose a novel concept, fusion factor, to control information that deep layers deliver to shallow layers, for adapting FPN to tiny object detection. After series of experiments and analysis, we explore how to estimate an effective value of fusion factor for a particular dataset by a statistical method. The estimation is dependent on the number of objects distributed in each layer. Comprehensive experiments are conducted on tiny object detection datasets, e.g., TinyPerson and Tiny CityPersons. Our results show that when configuring FPN with a proper fusion factor, the network is able to achieve significant performance gains over the baseline on tiny object detection datasets. Codes and models will be released.

Point spread function (PSF) models are critical to Hubble Space Telescope (HST) data analysis. Astronomers unfamiliar with optical simulation techniques need access to PSF models that properly match the conditions of their observations, so any HST modeling software needs to be both easy-to-use and have detailed information on the telescope and instruments. The Tiny Tim PSF simulation software package has been the standard HST modeling software since its release in early 1992. We discuss the evolution of Tiny Tim over the years as new instruments and optical properties have been incorporated. We also demonstrate how Tiny Tim PSF models have been used for HST data analysis. Tiny Tim is freely available from tinytim.stsci.edu.

A novel transposon-tagging strategy designed to recover dominant gain-of-function alleles was performed with Arabidopsis by using a Dissociation element with a cauliflower mosaic virus 35S promoter transcribing outward over one terminus. Lines containing transposed copies of this transposon were screened for mutants, and a semidominant mutation affecting plant height, hypocotyl elongation, and fertility was recovered. The pleiotropic effects of this mutation appear to result from a general reduction in cell expansion, and some of the effects are similar to those caused by supplying exogenous ethylene or cytokinin to wild-type seedlings. In addition, the arrangement of cells in some organs such as the etiolated hypocotyl, is disorganized. The mutation was called tiny, and the affected gene was cloned by first using transposon sequences to isolate the mutant allele. The predicted protein product of the TINY gene shows strong homology with the DNA binding domain of a recently identified class of plant transcription factors. This domain, called the APETALA2 domain, was initially identified as a duplicated region within the APETALA2 gene of Arabidopsis and then as a conserved region between APETALA2 and the ethylene responsive element binding proteins of tobacco. In the mutant allele, the Dissociation element is inserted in the untranslated leader of the TINY gene, 36 bp from the ATG, and the mutant contains a novel transcript that initiates from the cauliflower mosaic virus 35S promoter within the transposon. This transcript is present in greater abundance than the wild-type TINY transcript; therefore, the semidominant tiny mutation most likely results from increased, or ectopic, expression of the gene.

Object detection is a major challenge in computer vision, involving both object classification and object localization within a scene. While deep neural networks have been shown in recent years to yield very powerful techniques for tackling the challenge of object detection, one of the biggest challenges with enabling such object detection networks for widespread deployment on embedded devices is high computational and memory requirements. Recently, there has been an increasing focus in exploring small deep neural network architectures for object detection that are more suitable for embedded devices, such as Tiny YOLO and SqueezeDet. Inspired by the efficiency of the Fire microarchitecture introduced in SqueezeNet and the object detection performance of the singleshot detection macroarchitecture introduced in SSD, this paper introduces Tiny SSD, a single-shot detection deep convolutional neural network for real-time embedded object detection that is composed of a highly optimized, non-uniform Fire subnetwork stack and a non-uniform sub-network stack of highly optimized SSD-based auxiliary convolutional feature layers designed specifically to minimize model size while maintaining object detection performance. The resulting Tiny SSD possess a model size of 2.3MB (~26X smaller than Tiny YOLO) while still achieving an mAP of 61.3% on VOC 2007 (~4.2% higher than Tiny YOLO). These experimental results show that very small deep neural network architectures can be designed for real-time object detection that are well-suited for embedded scenarios.

Research Article| February 01, 2007 Zircon Tiny but Timely Simon L. Harley; Simon L. Harley Grant Institute of Earth Science, The University of Edinburgh Edinburgh EH9 3JW, United Kingdom E-mail: Simon.Harley@ed.ac.uk Search for other works by this author on: GSW Google Scholar Nigel M. Kelly Nigel M. Kelly Grant Institute of Earth Science, The University of Edinburgh Edinburgh EH9 3JW, United Kingdom E-mail: Nigel.Kelly@ed.ac.uk Search for other works by this author on: GSW Google Scholar Author and Article Information Simon L. Harley Grant Institute of Earth Science, The University of Edinburgh Edinburgh EH9 3JW, United Kingdom E-mail: Simon.Harley@ed.ac.uk Nigel M. Kelly Grant Institute of Earth Science, The University of Edinburgh Edinburgh EH9 3JW, United Kingdom E-mail: Nigel.Kelly@ed.ac.uk Publisher: Mineralogical Society of America First Online: 09 Mar 2017 Online ISSN: 1811-5217 Print ISSN: 1811-5209 © 2007 by the Mineralogical Society of America Elements (2007) 3 (1): 13–18. https://doi.org/10.2113/gselements.3.1.13 Article history First Online: 09 Mar 2017 Cite View This Citation Add to Citation Manager Share Icon Share Facebook Twitter LinkedIn Email Permissions Search Site Citation Simon L. Harley, Nigel M. Kelly; Zircon Tiny but Timely. Elements 2007;; 3 (1): 13–18. doi: https://doi.org/10.2113/gselements.3.1.13 Download citation file: Ris (Zotero) Refmanager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentBy SocietyElements Search Advanced Search Abstract Where would Earth science be without zircon? Tiny crystals of zircon occur in many rocks, and because their atomic structure remains stable over very long periods of geological time, they are able to provide a picture of the early history of the Earth and of the evolution of the crust and mantle. Zircon has long been recognized as the best geochronometer using the radioactive decay of uranium to lead. Recent developments in analytical techniques, using small-diameter laser, ion and electron beams, high-precision mass spectrometry and a variety of microscopic imaging methods, allow us to obtain the ages of tiny volumes of complex crystals that record stages in their long growth history. Coupled measurements of the isotopes of oxygen and hafnium provide a mineralogical window into the separation of the Earth's crust from the mantle and the temperature and character of processes involved in crustal evolution. Zircon is being used to unravel ever more complex geological systems, presenting exciting opportunities for research on this remarkable mineral. You do not have access to this content, please speak to your institutional administrator if you feel you should have access.

Tiny defect detection (TDD) which aims to perform the quality control of printed circuit boards (PCBs) is a basic and essential task in the production of most electronic products. Though significant progress has been made in PCB defect detection, traditional methods are still difficult to cope with the complex and diverse PCBs. To deal with these problems, this article proposes a tiny defect detection network (TDD‐Net) to improve performance for PCB defect detection. In this method, the inherent multi‐scale and pyramidal hierarchies of deep convolutional networks are exploited to construct feature pyramids. Compared with existing approaches, the TDD‐Net has three novel changes. First, reasonable anchors are designed by using k‐means clustering. Second, TDD‐Net strengthens the relationship of feature maps from different levels and benefits from low‐level structural information, which is suitable for tiny defect detection. Finally, considering the small and imbalance dataset, online hard example mining is adopted in the whole training phase in order to improve the quality of region‐of‐interest (ROI) proposals and make more effective use of data information. Quantitative results on the PCB defect dataset show that the proposed method has better portability and can achieve 98.90% mAP, which outperforms the state‐of‐arts. The code will be publicly available.

Naturally tiny regulatory RNAs of about 22 nucleotides were first identified from Caenorhabditis elegans genetics. Artificially induced RNAs of this size are also an intermediate in RNA interference, and both such RNAs use a common biochemical processing pathway. Now three groups have shown that there is an entire world of tiny RNAs that had almost escaped detection until now. These tiny RNAs are likely to regulate the translation of other mRNAs during development and, like the intermediates in RNAi, may be subject to amplification and systemic spread.

Describes Tiny Tera: a small, high-bandwidth, single-stage switch. Tiny Tera has 32 ports switching fixed-size packets, each operating at over 10 Gbps (approximately the Sonet OC-192e rate, a telecom standard for system interconnects). The switch distinguishes four classes of traffic and includes efficient support for multicasting. We aim to demonstrate that it is possible to use currently available CMOS technology to build this compact switch with an aggregate bandwidth of approximately 1 terabit per second and a central hub no larger than a can of soda. Such a switch could serve as a core for an ATM switch or an Internet router. Tiny Tera is an input-buffered switch, which makes it the highest bandwidth switch possible given a particular CMOS and memory technology. The switch consists of three logical elements: ports, a central crossbar switch, and a central scheduler. It queues packets at a port on entry and optionally prior to exit. The scheduler, which has a map of each port's queue occupancy, determines the crossbar configuration every packet time slot. Input queueing, parallelism, and tight integration are the keys to such a high-bandwidth switch. Input queueing reduces the memory bandwidth requirements: When a switch queues packets at the input, the buffer memories need run no faster than the line rate. Thus, there is no need for the speedup required in output-queued switches.

Two small temporal RNAs (stRNAs), lin-4 and let-7, control developmental timing in Caenorhabditis elegans. We find that these two regulatory RNAs are members of a large class of 21- to 24-nucleotide noncoding RNAs, called microRNAs (miRNAs). We report on 55 previously unknown miRNAs in C. elegans. The miRNAs have diverse expression patterns during development: a let-7 paralog is temporally coexpressed with let-7; miRNAs encoded in a single genomic cluster are coexpressed during embryogenesis; and still other miRNAs are expressed constitutively throughout development. Potential orthologs of several of these miRNA genes were identified in Drosophila and human genomes. The abundance of these tiny RNAs, their expression patterns, and their evolutionary conservation imply that, as a class, miRNAs have broad regulatory functions in animals.

Wireless sensor networks are composed of large numbers of tiny networked devices that communicate untethered. For large scale networks, it is important to be able to download code into the network dynamically. We present Contiki, a lightweight operating system with support for dynamic loading and replacement of individual programs and services. Contiki is built around an event-driven kernel but provides optional preemptive multithreading that can be applied to individual processes. We show that dynamic loading and unloading is feasible in a resource constrained environment, while keeping the base system lightweight and compact.

暂无摘要（点击查看原文获取完整内容）

Inspired by spider silk, a series of artificial spider silks with spindle-knots are fabricated. Tiny water drops (tens of picoliters) are driven with controllable direction on the fiber surfaces. The study will help the future design of smart materials and devices to drive tiny water drops in a controllable manner. Detailed facts of importance to specialist readers are published as ”Supporting Information”. Such documents are peer-reviewed, but not copy-edited or typeset. They are made available as submitted by the authors. Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.

Swarms of tiny flying robots hold great potential for exploring unknown, indoor environments. Their small size allows them to move in narrow spaces, and their light weight makes them safe for operating around humans. Until now, this task has been out of reach due to the lack of adequate navigation strategies. The absence of external infrastructure implies that any positioning attempts must be performed by the robots themselves. State-of-the-art solutions, such as simultaneous localization and mapping, are still too resource demanding. This article presents the swarm gradient bug algorithm (SGBA), a minimal navigation solution that allows a swarm of tiny flying robots to autonomously explore an unknown environment and subsequently come back to the departure point. SGBA maximizes coverage by having robots travel in different directions away from the departure point. The robots navigate the environment and deal with static obstacles on the fly by means of visual odometry and wall-following behaviors. Moreover, they communicate with each other to avoid collisions and maximize search efficiency. To come back to the departure point, the robots perform a gradient search toward a home beacon. We studied the collective aspects of SGBA, demonstrating that it allows a group of 33-g commercial off-the-shelf quadrotors to successfully explore a real-world environment. The application potential is illustrated by a proof-of-concept search-and-rescue mission in which the robots captured images to find "victims" in an office environment. The developed algorithms generalize to other robot types and lay the basis for tackling other similarly complex missions with robot swarms in the future.