Retracted: FoNet: A Memory-efficient Fourier-based Orthogonal Network for Object Recognition
Why is this work in the frame?
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Post-publication record
OpenAlex flags this work as retracted, but it carries no matching Retraction Watch record in this frame.
Machine scores (provisional)
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
- Teacher spread
- 0.220 · how far apart the two teachers sit on this one work
- Validation status
score_only:v0-immature-baseline· verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it
Abstract
The memory consumption of most Convolutional Neural Network (CNN) architectures grows rapidly with the increasing depth of the network, which is a major constraint for efficient network training and inference on modern GPUs with limited memory. Several studies show that the feature maps (as generated after the convolutional layers) are the big bottleneck in this memory problem. Often, these feature maps mimic natural photographs in the sense that their energy is concentrated in the spectral domain. In this paper, we propose a Fourier-based Orthogonal Network (FoNet) that incorporates orthogonal representations and performs both the convolution and the activation operations in the spectral domain to achieve memory reduction. The performance of our FoNet is evaluated on four standard object recognition benchmarks (i.e., MNIST, CIFAR10, SVHN, and ImageNet), and compared with four state-of-the-art implementations (i.e., LeNet, AlexNet, VGG, and DenseNet). Encouragingly, FoNet is able to reduce memory consumption by about 60% without significant loss of performance for all tested network architectures.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
The record
- Venue
- Topic
- Advanced Neural Network Applications
- Field
- Computer Science
- Canadian institutions
- York University
- Funders
- —
- Keywords
- Computer scienceMNIST databaseConvolutional neural networkConvolution (computer science)BottleneckInferenceFeature (linguistics)Pattern recognition (psychology)Cognitive neuroscience of visual object recognitionKernel (algebra)Domain (mathematical analysis)Artificial intelligenceObject (grammar)Memory managementParallel computingDeep learningArtificial neural networkEmbedded systemComputer hardwareSemiconductor memory
- Has abstract in OpenAlex
- yes