From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Machine-Learning tasks are becoming pervasive in a broad range of domains, and in a broad range of systems (from embedded systems to data centers). At the same time, a small set of machine-learning algorithms (especially Convolutional and Deep Neural Networks, i.e., CNNs and DNNs) are proving to be state-of-the-art across many applications. As architectures evolve towards heterogeneous multi-cores composed of a mix of cores and accelerators, a machine-learning accelerator can achieve the rare combination of efficiency (due to the small number of target algorithms) and broad application scope. Until now, most machine-learning accelerator designs have focused on efficiently implementing the computational part of the algorithms. However, recent state-of-the-art CNNs and DNNs are characterized by their large size. In this study, we design an accelerator for large-scale CNNs and DNNs, with a special emphasis on the impact of memory on accelerator design, performance and energy. We show that it is possible to design an accelerator with a high throughput, capable of performing 452 GOP/s (key NN operations such as synaptic weight multiplications and neurons outputs additions) in a small footprint of 3.02 mm2 and 485 mW; compared to a 128-bit 2GHz SIMD processor, the accelerator is 117.87x faster, and it can reduce the total energy by 21.08x. The accelerator characteristics are obtained after layout at 65 nm. Such a high throughput in a small footprint can open up the usage of state-of-the-art machine-learning algorithms in a broad set of systems and for a broad set of applications.

https://novel.ict.ac.cn/ychen/pdf/DianNao.pdf

DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning

Processing-in-memory (PIM) is a promising solution to address the "memory wall" challenges for future computer systems. Prior proposed PIM architectures put additional computation logic in or near memory. The emerging metal-oxide resistive random access memory (ReRAM) has showed its potential to be used for main memory. Moreover, with its crossbar array structure, ReRAM can perform matrix-vector multiplication efficiently, and has been widely studied to accelerate neural network (NN) applications. In this work, we propose a novel PIM architecture, called PRIME, to accelerate NN applications in ReRAM based main memory. In PRIME, a portion of ReRAM crossbar arrays can be configured as accelerators for NN applications or as normal memory for a larger memory space. We provide microarchitecture and circuit designs to enable the morphable functions with an insignificant area overhead. We also design a software/hardware interface for software developers to implement various NNs on PRIME. Benefiting from both the PIM architecture and the efficiency of using ReRAM for NN computation, PRIME distinguishes itself from prior work on NN acceleration, with significant performance improvement and energy saving. Our experimental results show that, compared with a state-of-the-art neural processing unit design, PRIME improves the performance by ~2360× and the energy consumption by ~895×, across the evaluated machine learning benchmarks.

PRIME: a novel processing-in-memory architecture for neural network computation in ReRAM-based main memory

Large deep neural network models have recently demonstrated state-of-the-art accuracy on hard visual recognition tasks. Unfortunately such models are extremely time consuming to train and require large amount of compute cycles. We describe the design and implementation of a distributed system called Adam comprised of commodity server machines to train such models that exhibits world-class performance, scaling and task accuracy on visual recognition tasks. Adam achieves high efficiency and scalability through whole system co-design that optimizes and balances workload computation and communication. We exploit asynchrony throughout the system to improve performance and show that it additionally improves the accuracy of trained models. Adam is significantly more efficient and scalable than was previously thought possible and used 30x fewer machines to train a large 2 billion connection model to 2x higher accuracy in comparable time on the ImageNet 22,000 category image classification task than the system that previously held the record for this benchmark. We also show that task accuracy improves with larger models. Our results provide compelling evidence that a distributed systems-driven approach to deep learning using current training algorithms is worth pursuing.

/pdf/project-adam-building-an-efficient-and-scalable-deep-mz26kixwji.pdf

Project Adam: building an efficient and scalable deep learning training system

To support bursty traffic on the Internet (and especially WWW) efficiently, optical burst switching (OBS) is proposed as a way to streamline both protocols and hardware in building the future gener...

Optical burst switching (OBS) - a new paradigm for an optical Internet

All-polymer solar cells (all-PSCs) consisting of polymer donors (PDs) and polymer acceptors (PAs) have drawn tremendous research interest in recent years. It is due to not only their tunable optical, electrochemical, and structural properties, but also many superior features that are not readily available in conventional polymer-fullerene solar cells (fullerene-PSCs) including long-term stability, synthetic accessibility, and excellent film-forming properties suitable for large-scale manufacturing. Recent breakthroughs in material design and device engineering have driven the power conversion efficiencies (PCEs) of all-PSCs exceeding 11%, which is comparable to the performance of fullerene-PSCs. Furthermore, outstanding mechanical durability and stretchability have been reported for all-PSCs, which make them stand out from the other small molecule-based PSCs as a promising power supplier for wearable electronic devices. This review provides a comprehensive overview of the important work in all-PSCs, in which pertinent examples are deliberately chosen. First, we describe the key components that enabled the recent progresses of all-PSCs including rational design rules for efficient PDs and PAs, blend morphology control, and light harvesting engineering. We also review the recent work on the understanding of the stability of all-PSCs under various external conditions, which highlights the importance of all-PSCs for future implementation and commercialization. Finally, because all-PSCs have not yet achieved their full potential and are still undergoing rapid development, we offer our views on the current challenges and future prospects.

Recent Advances, Design Guidelines, and Prospects of All-Polymer Solar Cells.

A 201.4 GOPS real-time multi-object recognition processor is presented with a three-stage pipelined architecture. Visual perception based multi-object recognition algorithm is applied to give multiple attentions to multiple objects in the input image. For human-like multi-object perception, a neural perception engine is proposed with biologically inspired neural networks and fuzzy logic circuits. In the proposed hardware architecture, three recognition tasks (visual perception, descriptor generation, and object decision) are directly mapped to the neural perception engine, 16 SIMD processors including 128 processing elements, and decision processor, respectively, and executed in the pipeline to maximize throughput of the object recognition. For efficient task pipelining, proposed task/power manager balances the execution times of the three stages based on intelligent workload estimations. In addition, a 118.4 GB/s multi-casting network-on-chip is proposed for communication architecture with incorporating overall 21 IP blocks. For low-power object recognition, workload-aware dynamic power management is performed in chip-level. The 49 mm2 chip is fabricated in a 0.13 ?m 8-metal CMOS process and contains 3.7 M gates and 396 KB on-chip SRAM. It achieves 60 frame/sec multi-object recognition up to 10 different objects for VGA (640 × 480) video input while dissipating 496 mW at 1.2 V. The obtained 8.2 mJ/frame energy efficiency is 3.2 times higher than the state-of-the-art recognition processor.

/pdf/a-201-4-gops-496-mw-real-time-multi-object-recognition-3qq4u5qaqm.pdf

A 201.4 GOPS 496 mW Real-Time Multi-Object Recognition Processor With Bio-Inspired Neural Perception Engine

Despite the recent breakthroughs of polymer solar cells (PSCs) exhibiting a power conversion efficiency of over 17%, toxic and hazardous organic solvents such as chloroform and chlorobenzene are still commonly used in their fabrication, which impedes the practical application of PSCs. Thus, the development of eco-friendly processing methods suitable for industrial-scale production is now considered an imperative research focus. This Review provides a roadmap for the design of efficient photoactive materials that are compatible with non-halogenated green solvents (e.g., xylenes, toluene, and tetrahydrofuran). We summarize the recent development of green processing solvents and the processing methods to match with the efficient photoactive materials used in non-fullerene solar cells. We further review progress in the use of more eco-friendly solvents (i.e., water or alcohol) for achieving truly sustainable and eco-friendly PSC fabrication. For example, the concept of water- or alcohol-dispersed nanoparticles made of conjugated materials is introduced. Also, recent important progress and strategies to develop water/alcohol-soluble photoactive materials that completely eliminate the use of conventional toxic solvents are discussed. Finally, we provide our perspectives on the challenges facing the current green processing methods and materials, such as large-area coating techniques and long-term stability. We believe this Review will inform the development of PSCs that are truly clean and renewable energy sources.

Eco-Friendly Polymer Solar Cells: Advances in Green-Solvent Processing and Material Design.

Fast and robust object recognition of cluttered scenes presents two main challenges: (1) the large number of features to process requires high computational power, and (2) false matches from background clutter can degrade recognition accuracy. Previously, saliency based bottom-up visual attention [1,2] increased recognition speed by confining the recognition processing only to the salient regions. But these schemes had an inherent problem: the accuracy of the attention itself. If attention is paid to the false region, which is common when saliency cannot distinguish between clutter and object, recognition accuracy is degraded. In order to improve the attention accuracy, we previously reported an algorithm, the Unified Visual Attention Model (UVAM) [3], which incorporates the familiarity map on top of the saliency map for the search of attentive points. It can cross-check the accuracy of attention deployment by combining top-down attention, searching for “meaningful objects”, and bottom-up attention, just looking for conspicuous points. This paper presents a heterogeneous many-core (note: we use the term “many-core” instead of “multi-core” to emphasize the large number of cores) processor that realizes the UVAM algorithm to achieve fast and robust object recognition of cluttered video sequences.

A 345 mW Heterogeneous Many-Core Processor With an Intelligent Inference Engine for Robust Object Recognition

High fracture resistance of polymer solar cells (PSCs) is of great importance to ensure long-term mechanical reliability, especially considering their potential in roll-to-roll printing processes and flexible devices. In this paper, we compare mechanical properties, such as the cohesive fracture energy, elastic modulus, and crack-onset strain, of all-polymer solar cells (all-PSCs) and fullerene-based solar cells (PCBM–PSCs) based on the same, representative low-bandgap polymer donor (PTB7-Th) as a function of acceptor content. The all-PSCs exhibit higher fracture energy (2.45 J m–2) than PCBM–PSCs (0.29 J m–2) at optimized device conditions. Additionally, a 15-fold higher crack-onset strain is observed in all-PSCs than in PCBM–PSCs. Dramatically different mechanical compliances observed for all-PSCs and PCBM–PSCs are investigated in detail by analysis of the blend morphologies as a function of acceptor content (either P(NDI2HD-T) or PCBM acceptors). The superior fracture resistance of all-PSCs is attribut...

Comparative Study of the Mechanical Properties of All-Polymer and Fullerene–Polymer Solar Cells: The Importance of Polymer Acceptors for High Fracture Resistance

Seungjin Lee

Papers

Recent Advances, Design Guidelines, and Prospects of All-Polymer Solar Cells.

A 201.4 GOPS 496 mW Real-Time Multi-Object Recognition Processor With Bio-Inspired Neural Perception Engine

Eco-Friendly Polymer Solar Cells: Advances in Green-Solvent Processing and Material Design.

A 345 mW Heterogeneous Many-Core Processor With an Intelligent Inference Engine for Robust Object Recognition

Comparative Study of the Mechanical Properties of All-Polymer and Fullerene–Polymer Solar Cells: The Importance of Polymer Acceptors for High Fracture Resistance