An official website of the United States government
In the past decade, Deep Neural Networks (DNNs), e.g., Convolutional Neural Networks, achieved human-level performance in vision tasks such as object classification and detection. However, DNNs are known to be computationally expensive and thus hard to be deployed in real-time and edge applications. Many previous works have focused on DNN model compression to obtain smaller parameter sizes and consequently, less computational cost. Such methods, however, often introduce noticeable accuracy degradation. In this work, we optimize a state-of-the-art DNN-based video detection framework—Deep Feature Flow (DFF) from the cloud end using three proposed ideas. First, we propose Asynchronous DFF (ADFF) to asynchronously execute the neural networks. Second, we propose a Video-based Dynamic Scheduling (VDS) method that decides the detection frequency based on the magnitude of movement between video frames. Last, we propose Spatial Sparsity Inference, which only performs the inference on part of the video frame and thus reduces the computation cost. According to our experimental results, ADFF can reduce the bottleneck latency from 89 to 19 ms. VDS increases the detection accuracy by 0.6% mAP without increasing computation cost. And SSI further saves 0.2 ms with a 0.6% mAP degradation of detection accuracy.
more »
« less
Event Neural Networks
Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated. Such redundancy occurs at multiple levels of complexity, from low-level pixel values to textures and high-level semantics. We propose Event Neural Networks (EvNets), which leverage this redundancy to achieve considerable computation savings during video inference. A defining characteristic of EvNets is that each neuron has state variables that provide it with long-term memory, which allows low-cost, high-accuracy inference even in the presence of significant camera motion. We show that it is possible to transform a wide range of neural networks into EvNets without re-training. We demonstrate our method on state-of-the-art architectures for both high- and low-level visual processing, including pose recognition, object detection, optical flow, and image enhancement. We observe roughly an order-ofmagnitude reduction in computational costs compared to conventional networks, with minimal reductions in model accuracy.
more »
« less
- Award ID(s):
- 1943149
- PAR ID:
- 10525613
- Publisher / Repository:
- Springer (European Conference on Computer Vision - ECCV)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Network quantization is one of the most hardware friendly techniques to enable the deployment of convolutional neural networks (CNNs) on low-power mobile devices. Recent network quantization techniques quantize each weight kernel in a convolutional layer independently for higher inference accuracy, since the weight kernels in a layer exhibit different variances and hence have different amounts of redundancy. The quantization bitwidth or bit number (QBN) directly decides the inference accuracy, latency, energy and hardware overhead. To effectively reduce the redundancy and accelerate CNN inferences, various weight kernels should be quantized with different QBNs. However, prior works use only one QBN to quantize each convolutional layer or the entire CNN, because the design space of searching a QBN for each weight kernel is too large. The hand-crafted heuristic of the kernel-wise QBN search is so sophisticated that domain experts can obtain only sub-optimal results. It is difficult for even deep reinforcement learning (DRL) DDPG-based agents to find a kernel-wise QBN configuration that can achieve reasonable inference accuracy. In this paper, we propose a hierarchical-DRL-based kernel-wise network quantization technique, AutoQ, to automatically search a QBN for each weight kernel, and choose another QBN for each activation layer. Compared to the models quantized by the state-of-the-art DRL-based schemes, on average, the same models quantized by AutoQ reduce the inference latency by 54.06%, and decrease the inference energy consumption by 50.69%, while achieving the same inference accuracy.more » « less
-
Artificial Intelligence (AI) has permeated various domains but is limited by the bottlenecks imposed by data transfer latency inherent in contemporary memory technologies. Matrix multiplication, crucial for neural network training and inference, can be significantly expedited with a complexity of O(1) using Resistive RAM (RRAM) technology, instead of the conventional complexity of O(n2). This positions RRAM as a promising candidate for the efficient hardware implementation of machine learning and neural networks through in-memory computation. However, RRAM manufacturing technology remains in its infancy, rendering it susceptible to soft errors, potentially compromising neural network accuracy and reliability. In this paper, we propose a syndrome-based error correction scheme that employs selective weighted checksums to correct double adjacent column errors in RRAM. The error correction is done on the output of the matrix multiplication thus ensuring correct operation for any number of errors in two adjacent columns. The proposed codes have low redundancy and low decoding latency, making it suitable for high throughput applications. This schemeuses a repeating weight based structure that makes it scalable to large RRAM matrix sizes.more » « less
-
null (Ed.)Deep learning now offers state-of-the-art accuracy for many prediction tasks. A form of deep learning called deep convolutional neural networks (CNNs) are especially popular on image, video, and time series data. Due to its high computational cost, CNN inference is often a bottleneck in analytics tasks on such data. Thus, a lot of work in the computer architecture, systems, and compilers communities study how to make CNN inference faster. In this work, we show that by elevating the abstraction level and re-imagining CNN inference as queries , we can bring to bear database-style query optimization techniques to improve CNN inference efficiency. We focus on tasks that perform CNN inference repeatedly on inputs that are only slightly different . We identify two popular CNN tasks with this behavior: occlusion-based explanations (OBE) and object recognition in videos (ORV). OBE is a popular method for “explaining” CNN predictions. It outputs a heatmap over the input to show which regions (e.g., image pixels) mattered most for a given prediction. It leads to many re-inference requests on locally modified inputs. ORV uses CNNs to identify and track objects across video frames. It also leads to many re-inference requests. We cast such tasks in a unified manner as a novel instance of the incremental view maintenance problem and create a comprehensive algebraic framework for incremental CNN inference that reduces computational costs. We produce materialized views of features produced inside a CNN and connect them with a novel multi-query optimization scheme for CNN re-inference. Finally, we also devise novel OBE-specific and ORV-specific approximate inference optimizations exploiting their semantics. We prototype our ideas in Python to create a tool called Krypton that supports both CPUs and GPUs. Experiments with real data and CNNs show that Krypton reduces runtimes by up to 5× (respectively, 35×) to produce exact (respectively, high-quality approximate) results without raising resource requirements.more » « less
-
null (Ed.)Deep convolutional neural networks (CNNs) achieve state-of-the-art accuracy for many computer vision tasks. But using them for video monitoring applications incurs high computational cost and inference latency. Thus, recent works have studied how to improve system efficiency. But they largely focus on small "closed world" prediction vocabularies even though many applications in surveillance security, traffic analytics, etc. have an ever-growing set of target entities. We call this the "unbounded vocabulary" issue, and it is a key bottleneck for emerging video monitoring applications. We present the first data system for tacking this issue for video querying, Panorama. Our design philosophy is to build a unified and domain-agnostic system that lets application users generalize to unbounded vocabularies in an out-of-the-box manner without tedious manual re-training. To this end, we synthesize and innovate upon an array of techniques from the ML, vision, databases, and multimedia systems literature to devise a new system architecture. We also present techniques to ensure Panorama has high inference efficiency. Experiments with multiple real-world datasets show that Panorama can achieve between 2x to 20x higher efficiency than baseline approaches on in-vocabulary queries, while still yielding comparable accuracy and also generalizing well to unbounded vocabularies.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Proceeding:
- The DOI is not currently available.
