Data-Side Efficiencies for Lightweight Convolutional Neural Networks
We examine how the choice of data-side attributes for two important visual tasks of image classification and object detection can aid in the choice or design of lightweight convolutional neural networks. We show by experimentation how four data attributes - number of classes, object color, image resolution, and object scale affect neural network model size and efficiency. Intra- and inter-class similarity metrics, based on metric learning, are defined to guide the evaluation of these attributes toward achieving lightweight models. Evaluations made using these metrics are shown to require 30x less computation than running full inference tests. We provide, as an example, applying the metrics and methods to choose a lightweight model for a robot path planning application and achieve computation reduction of 66% and accuracy gain of 3.5% over the pre-method model.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationMetric LearningObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
A Signal Matrix-Based Local Flaw Detection Framework for Steel Wire Ropes Using Convolutional Neural Networks
Steel wire ropes (SWRs) are critical load-bearing components in industrial applications, yet their structural integrity is often compromised by local flaws (LFs). Magnetic Flux Leakage (MFL) is a widely used non-destruct…
Computational EfficiencyDefect DetectionLearning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training
Common practice when training Convolutional Neural Networks (CNNs) is to use randomly shuffled mini-batches. This creates two limitations: slower convergence, and a diminishing learning signal, since many samples are qui…
iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images
We propose iSegFormer, a memory-efficient transformer that combines a Swin transformer with a lightweight multilayer perceptron (MLP) decoder. With the efficient Swin transformer blocks for hierarchical self-attention an…
DecoderImage SegmentationInteractive SegmentationMedical Image Segmentation+1CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction
Convolutional neural networks (CNNs) and vision transformers (ViTs) have become essential in computer vision for local and global feature extraction. However, aggregating these architectures in existing methods often res…
DeepTx: Deep Learning Beamforming with Channel Prediction
Machine learning algorithms have recently been considered for many tasks in the field of wireless communications. Previously, we have proposed the use of a deep fully convolutional neural network (CNN) for receiver proce…
BIG-bench Machine LearningDeep LearningPrediction