Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Reducing Line Loss01:18

Reducing Line Loss

250
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 in...
250
Survival Tree01:19

Survival Tree

216
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
216
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

1.1K
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
1.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

12.2K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
12.2K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.3K
3.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Pruning Self-Attentions Into Convolutional Layers in Single Path.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

End-to-End One-Shot Human Parsing.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Single-Path Bit Sharing for Automatic Loss-Aware Model Compression.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Effective Training of Convolutional Neural Networks With Low-Bitwidth Weights and Activations.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

TasselNet: counting maize tassels in the wild via local counts regression network.

Plant methods·2017
Same author

Visual tracking via discriminative sparse similarity map.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2014
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Nov 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

760

Discrimination-Aware Network Pruning for Deep Model Compression.

Jing Liu, Bohan Zhuang, Zhuangwei Zhuang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |March 23, 2021
    PubMed
    Summary
    This summary is machine-generated.

    We introduce discrimination-aware pruning (DCP) to efficiently remove redundant channels and kernels in deep networks. This method enhances model performance and inference speed, outperforming existing techniques.

    Related Experiment Videos

    Last Updated: Nov 11, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    760

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Model Compression

    Background:

    • Deep neural networks require significant computational resources for inference.
    • Network pruning aims to reduce model size and accelerate inference by removing redundant components.
    • Existing pruning methods have limitations, including high computational cost or neglecting channel discriminative power.

    Purpose of the Study:

    • To propose a novel and effective network pruning method, Discrimination-Aware Channel Pruning (DCP).
    • To address limitations of existing methods by considering both reconstruction error and channel discriminative power.
    • To introduce Discrimination-Aware Kernel Pruning (DKP) for further compression by removing redundant kernels.

    Main Methods:

    • Introduced additional discrimination-aware losses to enhance intermediate layer discriminative power.
    • Selected channels based on both discrimination-aware loss and reconstruction error.
    • Formulated channel pruning as a sparsity-inducing optimization problem solved by a greedy algorithm.
    • Developed Discrimination-Aware Kernel Pruning (DKP) to remove redundant kernels within channels.
    • Proposed adaptive stopping conditions for automatic determination of pruning rates.

    Main Results:

    • Achieved improved performance and efficiency on image classification and face recognition tasks.
    • ResNet-50 with 30% channel reduction on ILSVRC-12 surpassed the baseline accuracy by 0.36% Top-1.
    • Pruned MobileNetV1 and MobileNetV2 achieved 1.93x and 1.42x inference acceleration on a smartphone.
    • Demonstrated negligible performance degradation with significant model compression and speed-up.

    Conclusions:

    • Discrimination-Aware Pruning (DCP) and DKP are effective methods for compressing deep neural networks.
    • The proposed methods enhance inference speed and accuracy, outperforming traditional pruning techniques.
    • Adaptive stopping conditions enable automatic and efficient model compression for practical deployment.