Sequential Monte Carlo filter based on multiple strategies for a scene specialization classifier

Maâmatou, Houda; Chateau, Thierry; Gazzah, Sami; Goyat, Yann; Amara, Najoua Essoukri Ben

doi:10.1186/s13640-016-0143-4

Cited by 6 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are not aware of any other work accelerating NN inference time via task specialization on video. However, related strategies for specialization have been shown to boost accuracy (but not runtime) [65,68], and there are a range of models designed for detecting specific classes of objects in video. One of the most popular video-based object detection tasks is pedestrian detection [15,28], with a range of NN-based approaches (e.g., [84]).…”

Section: Related Workmentioning

confidence: 99%

NoScope: Optimizing Neural Network Queries over Video at Scale

Kang¹,

Emmons²,

Abuzaid³

et al. 2017

Preprint

View full text Add to dashboard Cite

Recent advances in computer vision-in the form of deep neural networks-have made it possible to query increasing volumes of video data with high accuracy. However, neural network inference is computationally expensive at scale: applying a state-of-the-art object detector in real time (i.e., 30+ frames per second) to a single video requires a $4000 GPU. In response, we present NOSCOPE, a system for querying videos that can reduce the cost of neural network video analysis by up to three orders of magnitude via inference-optimized model search. Given a target video, object to detect, and reference neural network, NOSCOPE automatically searches for and trains a sequence, or cascade, of models that preserves the accuracy of the reference network but is specialized to the target video and are therefore far less computationally expensive. NOSCOPE cascades two types of models: specialized models that forego the full generality of the reference model but faithfully mimic its behavior for the target video and object; and difference detectors that highlight temporal differences across frames. We show that the optimal cascade architecture differs across videos and objects, so NOSCOPE uses an efficient cost-based optimizer to search across models and cascades. With this approach, NOSCOPE achieves two to three order of magnitude speed-ups (265-15,500× real-time) on binary classification tasks over fixed-angle webcam and surveillance video while maintaining accuracy within 1-5% of state-of-the-art neural networks.

show abstract

Section: Related Workmentioning

confidence: 99%

NoScope: Optimizing Neural Network Queries over Video at Scale

Kang¹,

Emmons²,

Abuzaid³

et al. 2017

Preprint

View full text Add to dashboard Cite

show abstract

Semi-supervised domain adaptation for pedestrian detection in video surveillance based on maximum independence assumption

Shojaei

Razzazi

2019

Int J Multimed Info Retr

View full text Add to dashboard Cite

Exploiting Target Data to Learn Deep Convolutional Networks for Scene-Adapted Human Detection

Wang

Laganière

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

The difference between sample distributions of public data sets and specific scenes can be very significant. As a result, the deployment of generic human detectors in real-world scenes most often leads to sub-optimal detection performance. To avoid the labor-intensive task of manual annotations, we propose a semi-supervised approach for training deep convolutional networks on partially labeled data. To exploit a large amount of unlabeled target data, the knowledge learnt from public data sets is transferred to new model training by adapting an auxiliary detector to the target scene. We hypothesize that the components of the auxiliary detector capture essential human characteristics useful for constructing a scene-adapted detector. A selective ensemble algorithm is proposed to select a subset of the components relevant to the target scene for recombination. The resulting model is applied for collecting high-confidence samples from unlabeled target data. Furthermore, a deep convolutional network is trained by progressively labeling and selecting new training samples in a self-paced way. The detailed experimental evaluation verifies the effectiveness and superiority of the proposed approach in scene-specific human detection.

show abstract

Sequential Monte Carlo filter based on multiple strategies for a scene specialization classifier

Cited by 6 publications

References 35 publications

NoScope: Optimizing Neural Network Queries over Video at Scale

NoScope: Optimizing Neural Network Queries over Video at Scale

Semi-supervised domain adaptation for pedestrian detection in video surveillance based on maximum independence assumption

Exploiting Target Data to Learn Deep Convolutional Networks for Scene-Adapted Human Detection

Contact Info

Product

Resources

About