RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr

• URL: http://arxiv.org/abs/2007.03349v1
• Date: Tue, 7 Jul 2020 11:27:43 GMT
• Title: RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
• Authors: Xingjian Li, Haoyi Xiong, Haozhe An, Chengzhong Xu, Dejing Dou
• Abstract summary: Fine-tuning the deep convolution neural network(CNN) using a pre-trained model helps transfer knowledge learned from larger datasets to the target task. We propose RIFLE - a strategy that deepens backpropagation in transfer learning settings. RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning.
• Score: 60.07531696857743
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning the deep convolution neural network(CNN) using a pre-trained model helps transfer knowledge learned from larger datasets to the target task. While the accuracy could be largely improved even when the training dataset is small, the transfer learning outcome is usually constrained by the pre-trained model with close CNN weights (Liu et al., 2019), as the backpropagation here brings smaller updates to deeper CNN layers. In this work, we propose RIFLE - a simple yet effective strategy that deepens backpropagation in transfer learning settings, through periodically Re-Initializing the Fully-connected LayEr with random scratch during the fine-tuning procedure. RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure. The experiments show that the use of RIFLE significantly improves deep transfer learning accuracy on a wide range of datasets, out-performing known tricks for the similar purpose, such as Dropout, DropConnect, StochasticDepth, Disturb Label and Cyclic Learning Rate, under the same settings with 0.5% -2% higher testing accuracy. Empirical cases and ablation studies further indicate RIFLE brings meaningful updates to deep CNN layers with accuracy improved.

Related papers

• Diffusion-based Neural Network Weights Generation [85.6725307453325]
  We propose an efficient and adaptive transfer learning scheme through dataset-conditioned pretrained weights sampling. Specifically, we use a latent diffusion model with a variational autoencoder that can reconstruct the neural network weights.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training [2.8804804517897935]
  We propose a method for hiding the least-important samples during the training of deep neural networks. We adaptively find samples to exclude in a given epoch based on their contribution to the overall learning process. Our method can reduce total training time by up to 22% impacting accuracy only by 0.4% compared to the baseline.
  arXiv  Detail & Related papers  (2023-10-16T06:19:29Z)
• Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data [24.86314525762012]
  We show that ReLU CNN trained by gradient descent can achieve near Bayes-optimal accuracy. Our result demonstrates that CNNs have a remarkable capacity to efficiently learn XOR problems, even in the presence of highly correlated features.
  arXiv  Detail & Related papers  (2023-10-03T11:31:37Z)
• Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networks [12.525959293825318]
  We introduce Learn, Unlearn, and Relearn (LURE) an online learning paradigm for deep neural networks (DNNs) LURE interchanges between the unlearning phase, which selectively forgets the undesirable information in the model, and the relearning phase, which emphasizes learning on generalizable features. We show that our training paradigm provides consistent performance gains across datasets in both classification and few-shot settings.
  arXiv  Detail & Related papers  (2023-03-18T16:45:54Z)
• Single image calibration using knowledge distillation approaches [1.7205106391379026]
  We build upon a CNN architecture to automatically estimate camera parameters. We adapt four common incremental learning strategies to preserve knowledge when updating the network for new data distributions. Experiment results were significant and indicated which method was better for the camera calibration estimation.
  arXiv  Detail & Related papers  (2022-12-05T15:59:35Z)
• Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings [89.63764845984076]
  We present Stored Embeddings for Efficient Reinforcement Learning (SEER) SEER is a simple modification of existing off-policy deep reinforcement learning methods. We show that SEER does not degrade the performance of RLizable agents while significantly saving computation and memory.
  arXiv  Detail & Related papers  (2021-03-04T08:14:10Z)
• Temporal Calibrated Regularization for Robust Noisy Label Learning [60.90967240168525]
  Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and error-prone so that it is difficult to guarantee the annotation quality. We propose a Temporal Calibrated Regularization (TCR) in which we utilize the original labels and the predictions in the previous epoch together.
  arXiv  Detail & Related papers  (2020-07-01T04:48:49Z)
• Learning across label confidence distributions using Filtered Transfer Learning [0.44040106718326594]
  We propose a transfer learning approach to improve predictive power in noisy data systems with large variable confidence datasets. We propose a deep neural network method called Filtered Transfer Learning (FTL) that defines multiple tiers of data confidence as separate tasks. We demonstrate that using FTL to learn stepwise, across the label confidence distribution, results in higher performance compared to deep neural network models trained on a single confidence range.
  arXiv  Detail & Related papers  (2020-06-03T21:00:11Z)
• Curriculum By Smoothing [52.08553521577014]
  Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
  arXiv  Detail & Related papers  (2020-03-03T07:27:44Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.