Learning the Structure of Deep Convolutional Networks

By Jiashi Feng, Trevor Darrell. 2015

80 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

Citations in the corpus

AutoGrow: Automatic Layer Growing in Deep Convolutional Networks (2019, positive): “ingle training. Structure pruning and growing were proposed for different goals, such as efficient inference [7, 8, 11, 13, 14, 18, 19, 24, 25, 27, 38–40], lifelong learning [41] and model adaptation [10, 29]. However, those works fixed the network depth and limited structure learning within the exi”
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks (2017, methodology): “Other methods to learn the structure of a neural network have been proposed, especially focusing on when and how to expand the size of a neural network [6, 2].”
Learning Structured Sparsity in Deep Neural Networks (2016, background): “[16] learned the appropriate number of filters in DNN.”
Nonparametric Neural Networks (2017, background): “While some of these methods even allow some previously pruned units to be added back in (e.g. Feng & Darrell (2015)), all of these strategies require a high-performing network model as a starting point from which to prune, something that is generally only available in well-studied vision and NLP…”
Deep Multimodal Learning: A Survey on Recent Advances and Trends (2017, methodology): “Recent approaches for DNNs include the works of Feng and Darrel [77], who proposed an evolving grow-and-prune algorithm that optimizes the structure of an Indian buffet process-CNN model, and Yang et al. [78], who introduced network pruning for large, diverse data sets based on sparse…”
Gradient-free Policy Architecture Search and Adaptation (2017, unknown): “…including models which fuse non-parametric Bayesian inference with deep learning to select the number of channels for visual recognition tasks [6], models which use reinforcement learning to directly optimize over deep architectures for recognition [24], and models which use a gradient-free…”
Regularizing Deep Convolutional Neural Networks with a Structured Decorrelation Constraint (2016, methodology): “Feng et al. [33] proposed a novel method for automatically learning aspects of the structure of a deep model in order to improve its performance, especially when labeled training data are scarce.”
PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training (2019, methodology): “Model pruning involves reducing the number of parameters in a dense fixed network (leading to lower memory and inference cost) while retaining the accuracy of the original model; it is already widely used and an active area of research (Wen et al., 2016; 2017; Feng & Darrell, 2015; He et al., 2018).”
Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges (2019, methodology): “approach [225], pruning [226], Bayesian optimization [227], genetic algorithms [228], and the recent reinforcement learning”