The ability to attend to salient regions of a visual scene is an innate and necessary preprocessing step for both biological and engineered systems performing high-level visual tasks (e.g. object detection, tracking, and classification). Computational efficiency, in regard to processing bandwidth and speed, is improved by only devoting computational resources to salient regions of the visual stimuli. In this paper, we first present a neuromorphic, bottom-up, dynamic visual saliency model based on the notion of proto-objects. This is achieved by incorporating the temporal characteristics of the visual stimulus into the model, similarly to the manner in which early stages of the human visual system extracts temporal information. This neuromorphic model outperforms state-of-the-art dynamic visual saliency models in predicting human eye fixations on a commonly used video dataset with associated eye tracking data. Secondly, for this model to have practical applications, it must be capable of performing its computations in real-time under low-power, small-size, and lightweight constraints. To address this, we introduce a Field-Programmable Gate Array implementation of the model on an Opal Kelly 7350 Kintex-7 board. This novel hardware implementation allows for processing of up to 23.35 frames per second running on a 100 MHz clock - better than 26x speedup from the software implementation.
Birla Institute of Technology & Science (BITS) Pilani（比拉理工学院（BITS）皮拉尼分校）
Neuromorphic engineering is essentially the development of artificial systems, such as electronic analog circuits that employ information representations found in biological nervous systems. Despite being faster and more accurate than the human brain, computers lag behind in recognition capability. However, it is envisioned that the advancement in neuromorphics, pertaining to the fields of computer vision and image processing will provide a considerable improvement in the way computers can interpret and analyze information. In this paper, we explore the implementation of visual tasks such as i…
Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activation maps (CAMs) to locate the object regions for pseudo label generation. However, CAMs can only discover the most discriminative parts of objects, thus leading to inferior pixel-level pseudo labels. To address this issue, we propose a saliency guided Inter- and Intra-Class Relation Constrained (I$^2$CRC) framework to assist the expansion of the activated object regions in CAMs. Specifically, we propose a saliency gu…
We propose an augmentation policy for Contrastive Self-Supervised Learning (SSL) in the form of an already established Salient Image Segmentation technique entitled Global Contrast based Salient Region Detection. This detection technique, which had been devised for unrelated Computer Vision tasks, was empirically observed to play the role of an augmentation facilitator within the SSL protocol. This observation is rooted in our practical attempts to learn, by SSL-fashion, aerial imagery of solar panels, which exhibit challenging boundary patterns. Upon the successful integration of this techniq…
TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection
XJTLU（西交利物浦大学）；University of Liverpool（利物浦大学）；China University of Petroleum (East China)（中国石油大学（华东））；Nanjing University of Information Science and Technology（南京信息工程大学）
Temporal Neural Networks (TNNs) use time as a resource to represent and process information, mimicking the behavior of the mammalian neocortex. This work focuses on implementing TNNs using off-the-shelf digital CMOS technology. A microarchitecture framework is introduced with a hierarchy of building blocks including: multi-neuron columns, multi-column layers, and multi-layer TNNs. We present the direct CMOS gate-level implementation of the multi-neuron column model as the key building block for TNNs. Post-synthesis results are obtained using Synopsys tools and the 45 nm CMOS standard cell libr…
Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a `basin' of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics su…
Neuromorphic Pseudo-Random Number Generators with a Low Power Hardware Implementation
Hotchkiss Brain Institute, University of Calgary（卡尔加里大学霍奇金斯脑研究所）；Biomedical Engineering, University of Calgary（卡尔加里大学生物医学工程系）；Electrical and Software Engineering, University of Calgary（卡尔加里大学电气与软件工程系）；Creative Destruction Lab（创意破坏实验室）；ACHRI, University of Calgary（卡尔加里大学应用计算健康研究 institute）
Neuromorphic devices represent an attempt to mimic aspects of the brain's architecture and dynamics with the aim of replicating its hallmark functional capabilities in terms of computational power, robust learning and energy efficiency. We employ a single-chip prototype of the BrainScaleS 2 neuromorphic system to implement a proof-of-concept demonstration of reward-modulated spike-timing-dependent plasticity in a spiking network that learns to play the Pong video game by smooth pursuit. This system combines an electronic mixed-signal substrate for emulating neuron and synapse dynamics with an …
In this paper, we describe a new neuro-inspired, hardware-friendly readout stage for the liquid state machine (LSM), a popular model for reservoir computing. Compared to the parallel perceptron architecture trained by the p-delta algorithm, which is the state of the art in terms of performance of readout stages, our readout architecture and learning algorithm can attain better performance with significantly less synaptic resources making it attractive for VLSI implementation. Inspired by the nonlinear properties of dendrites in biological neurons, our readout stage incorporates neurons having …
Zernike Institute for Advanced Materials, University of Groningen（格罗宁根大学泽尼克先进材料研究所）；Groningen Cognitive Systems and Materials Center (CogniGron), University of Groningen（格罗宁根大学格罗宁根认知系统与材料中心）
