Improved Projection Learning for Lower Dimensional Feature Maps
The requirement to repeatedly move large feature maps off- and on-chip during inference with convolutional neural networks (CNNs) imposes high costs in terms of both energy and time. In this work we explore an improved method for compressing all feature maps of pre-trained CNNs to below a specified limit. This is done by means of learned projections trained via end-to-end finetuning, which can then be folded and fused into the pre-trained network. We also introduce a new `ceiling compression' framework in which evaluate such techniques in view of the future goal of performing inference fully on-chip.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Random Feature Maps via a Layered Random Projection (LaRP) Framework for Object Classification
The approximation of nonlinear kernels via linear feature maps has recently gained interest due to their applications in reducing the training and testing time of kernel-based learning algorithms. Current random projecti…
General ClassificationObjectUDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection
Dimensional reduction~(DR) maps high-dimensional data into a lower dimensions latent space with minimized defined optimization objectives. The DR method usually falls into feature selection~(FS) and feature projection~(F…
Data AugmentationDimensionality Reductionfeature selectionOptimal Discriminant Analysis in High-Dimensional Latent Factor Models
In high-dimensional classification problems, a commonly used approach is to first project the high-dimensional features into a lower dimensional space, and base the classification on the resulting lower dimensional proje…
validVocal Bursts Intensity PredictionBinary Random Projections with Controllable Sparsity Patterns
Random projection is often used to project higher-dimensional vectors onto a lower-dimensional space, while approximately preserving their pairwise distances. It has emerged as a powerful tool in various data processing …
AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
A key factor in effective Self-Supervised learning (SSL) is preventing dimensional collapse, which is where higher-dimensional representation spaces span a lower-dimensional subspace. Therefore, SSL optimization strategi…
Self-Supervised Learning