Restoring Neural Network Plasticity for Faster Transfer Learning

• URL: http://arxiv.org/abs/2603.20860v1
• Date: Sat, 21 Mar 2026 15:41:58 GMT
• Title: Restoring Neural Network Plasticity for Faster Transfer Learning
• Abstract summary: Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task.<n>We propose the use of a targeted weight re-initialization strategy to restore neural plasticity prior to fine-tuning.<n>Our experiments show that both convolutional neural networks (CNNs) and vision transformers (ViTs) benefit from this approach.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet. However, pretrained weights can become saturated and may yield insignificant gradients, failing to adapt to the downstream task. This hinders the ability of the model to train effectively, and is commonly referred to as loss of neural plasticity. Loss of plasticity may prevent the model from fully adapting to the target domain, especially when the downstream dataset is atypical in nature. While this issue has been widely explored in continual learning, it remains relatively understudied in the context of transfer learning. In this work, we propose the use of a targeted weight re-initialization strategy to restore neural plasticity prior to fine-tuning. Our experiments show that both convolutional neural networks (CNNs) and vision transformers (ViTs) benefit from this approach, yielding higher test accuracy with faster convergence on several image classification benchmarks. Our method introduces negligible computational overhead and is compatible with common transfer learning pipelines.

Related papers

• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Epistemic Modeling Uncertainty of Rapid Neural Network Ensembles for Adaptive Learning [0.0]
  A new type of neural network is presented using the rapid neural network paradigm. It is found that the proposed emulator embedded neural network trains near-instantaneously, typically without loss of prediction accuracy.
  arXiv  Detail & Related papers  (2023-09-12T22:34:34Z)
• Understanding and Improving Transfer Learning of Deep Models via Neural Collapse [37.483109067209504]
  This work investigates the relationship between neural collapse (NC) and transfer learning for classification problems. We find strong correlation between feature collapse and downstream performance. Our proposed fine-tuning methods deliver good performances while reducing fine-tuning parameters by at least 90%.
  arXiv  Detail & Related papers  (2022-12-23T08:48:34Z)
• Random Weight Factorization Improves the Training of Continuous Neural Representations [1.911678487931003]
  Continuous neural representations have emerged as a powerful and flexible alternative to classical discretized representations of signals. We propose random weight factorization as a simple drop-in replacement for parameterizing and initializing conventional linear layers. We show how this factorization alters the underlying loss landscape and effectively enables each neuron in the network to learn using its own self-adaptive learning rate.
  arXiv  Detail & Related papers  (2022-10-03T23:48:48Z)
• Slimmable Networks for Contrastive Self-supervised Learning [69.9454691873866]
  Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. We introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers. A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks.
  arXiv  Detail & Related papers  (2022-09-30T15:15:05Z)
• How Well Do Sparse Imagenet Models Transfer? [75.98123173154605]
  Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" datasets. In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset. We show that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities.
  arXiv  Detail & Related papers  (2021-11-26T11:58:51Z)
• Is Deep Image Prior in Need of a Good Education? [57.3399060347311]
  Deep image prior was introduced as an effective prior for image reconstruction. Despite its impressive reconstructive properties, the approach is slow when compared to learned or traditional reconstruction techniques. We develop a two-stage learning paradigm to address the computational challenge.
  arXiv  Detail & Related papers  (2021-11-23T15:08:26Z)
• On Robustness and Transferability of Convolutional Neural Networks [147.71743081671508]
  Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. We study the interplay between out-of-distribution and transfer performance of modern image classification CNNs for the first time. We find that increasing both the training set and model sizes significantly improve the distributional shift robustness.
  arXiv  Detail & Related papers  (2020-07-16T18:39:04Z)
• Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification [53.735029033681435]
  Transfer learning is a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. In this work, we demonstrate that adversarially-trained models transfer better than non-adversarially-trained models.
  arXiv  Detail & Related papers  (2020-07-11T22:48:42Z)
• Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation [60.80172153614544]
  Un-trained convolutional neural networks have emerged as highly successful tools for image recovery and restoration. We show that an un-trained convolutional neural network can approximately reconstruct signals and images that are sufficiently structured, from a near minimal number of random measurements.
  arXiv  Detail & Related papers  (2020-05-07T15:57:25Z)
• On the interplay between physical and content priors in deep learning for computational imaging [5.486833154281385]
  We use the Phase Extraction Neural Network (PhENN) for quantitative phase retrieval in a lensless phase imaging system. We show that the two questions are related and share a common crux: the choice of the training examples. We also discover that weaker regularization effect leads to better learning of the underlying propagation model.
  arXiv  Detail & Related papers  (2020-04-14T08:36:46Z)

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.