Related Experiment Video
Updated: Jul 11, 2025
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
559
DRF-DRC: dynamic receptive field and dense residual connections for model compression
Wei Wang1, Yongde Zhang1, Liqiang Zhu2
1Avic Xi'an Aircraft Industry Group Company Ltd., Xi'an, 710089 China.
Cognitive Neurodynamics
|November 17, 2023
Summary
This study introduces DRENet, a novel neural architecture search method using dynamic receptive field operations and dense residual connections. DRENet efficiently designs computer vision networks, achieving superior performance across multiple benchmarks.
Area of Science:
- Computer Vision
- Artificial Intelligence
- Machine Learning
Background:
- Deep convolutional neural networks (CNNs) have advanced computer vision but manual architecture design is inefficient.
- Neural Architecture Search (NAS) is a critical research area for automating network design.
Purpose of the Study:
- To propose a novel NAS method, DRENet, for designing efficient deep neural networks.
- To introduce dynamic receptive field (DRF) operations and measurable dense residual connections (DRC) into the NAS search space.
Main Methods:
- Developed DRENet incorporating DRF and DRC within a MobileNetV2-based search space.
- Evaluated DRENet on diverse benchmark datasets including CIFAR10/100, SVHN, CUB-200-2011, ImageNet, and COCO.
- Applied DRENet to a railway intelligent surveillance system for practical validation.
Main Results:
- DRENet demonstrated superior performance across multiple computer vision benchmark datasets.
- The proposed DRF operation and DRC enhance network efficiency and effectiveness.
- Successful application in a real-world railway intelligent surveillance system.
Conclusions:
- DRENet offers an effective and efficient approach to neural architecture search for computer vision.
- The integration of DRF and DRC contributes to improved network design and performance.
- The method shows promise for practical applications in intelligent surveillance and beyond.
Related Concept Videos
01:18Reducing Line Loss
155
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
155
01:11Residuals and Least-Squares Property
7.4K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.4K
01:22Chunking and Rehearsal in Sensory Memory
218
Improving short-term memory can be achieved through techniques like chunking and rehearsal. Chunking involves organizing information into larger, more manageable units. This technique is particularly useful for information that exceeds the typical memory span of between five and nine items. For instance, logging into an online account with a password like "ta89vq0179gz" involves grouping letters and numbers into three chunks—ta89, vq01, and 79gz. It makes large amounts of...
218
01:20Deconvolution
163
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
163
01:17Convolution Properties II
209
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
209
01:19The Role of Ion Channels in Neuronal Computation
3.2K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.2K