Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning

• URL: http://arxiv.org/abs/2607.13043v1
• Date: Sat, 13 Jun 2026 13:46:24 GMT
• Title: Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning
• Abstract summary: Deep learning models achieve state-of-the-art image classification but face deployment challenges due to computational costs and energy demands.<n>We propose a lightweight training strategy that adapts normalization layers of the model to the new domain.<n>Our approach significantly reduces the required training time with only a marginal accuracy trade-off, often matching or surpassing baseline performance.
• Score: 1.8798171797988195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning models achieve state-of-the-art image classification but face deployment challenges due to computational costs and energy demands. We propose a lightweight training strategy that adapts normalization layers of the model to the new domain and decouples feature extraction from classifier optimization, reducing overhead by precomputing features only once. A redesigned classifier head with margin-based weighted loss further minimizes ambiguity without end-to-end backpropagation. Evaluated across four CNN architectures (ResNet18, ResNet50, MobileNet, DenseNet121), three Transformer models (ViT, Swin and DeiT) and three medical datasets (Brain Cancer MRI, BreakHis and PatchCamelyon), our approach significantly reduces the required training time with only a marginal accuracy trade-off, often matching or surpassing baseline performance. This efficiency translates to reducing CO2 by orders of magnitude, offering a practical and environmentally sustainable solution for resource-constrained clinical or prototyping environments.

Related papers

• Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning [49.751529745537546]
  We propose DualOpt, a novel approach that decouples optimization techniques specifically tailored for training from scratch.<n>For training from scratch, we introduce real-time layer-wise weight decay, designed to enhance both convergence and generalization.<n>We extend the layer-wise weight decay to dynamically adjust the rollback levels across layers, adapting to the varying demands of different downstream tasks.
  arXiv  Detail & Related papers  (2026-04-21T06:27:18Z)
• GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control [0.0]
  We introduce GIRL (Generative Imagination Reinforcement Learning), a latent world-model framework that addresses this failure mode with two key components.<n> GIRL reduces latent rollout drift by 38 to 61 percent across tasks relative to DreamerV3, improves return, and requires fewer environment interactions on long-horizon tasks.<n>A distilled-prior variant reduces overhead and improves computational efficiency relative to the full model.
  arXiv  Detail & Related papers  (2026-04-08T17:14:21Z)
• The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning [62.72522261010872]
  Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity.<n>We study the plasticity loss problem from the theoretical perspective of network optimization.<n>We propose Sample Weight Decay -- a lightweight method to restore gradient magnitude.
  arXiv  Detail & Related papers  (2026-04-02T11:29:46Z)
• CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems [3.343542849202802]
  We introduce CAMP-HiVe, a cyclic pair merging-based pruning with Hessian Vector approximation.<n>Our experimental results demonstrate that our proposed method achieves significant reductions in computational requirements.<n>It outperforms the existing state-of-the-art neural pruning methods.
  arXiv  Detail & Related papers  (2025-11-09T07:58:36Z)
• Automated Evolutionary Optimization for Resource-Efficient Neural Network Training [0.3905614402386577]
  We have developed a new automated machine learning (AutoML) framework, Efficient Training with Robust Automation (PETRA)<n>It applies evolutionary optimization to model architecture and training strategy.<n>PETRA includes pruning, quantization, and loss regularization.
  arXiv  Detail & Related papers  (2025-10-10T17:17:49Z)
• Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation [5.013248430919224]
  We propose a hybrid training methodology that enables efficient on-device domain adaptation.<n>The method begins with a deep neural network trained offline using Backpropagation to achieve high initial performance.<n> Predictive Coding is employed for online adaptation, allowing the model to recover accuracy lost due to shifts in the input data distribution.
  arXiv  Detail & Related papers  (2025-09-24T16:03:27Z)
• Auto-Compressing Networks [51.221103189527014]
  We introduce Auto-compression Networks (ACNs), an architectural variant where long feedforward connections from each layer replace traditional short residual connections.<n>We show that ACNs exhibit enhanced noise compared to residual networks, superior performance in low-data settings, and mitigate catastrophic forgetting.<n>These findings establish ACNs as a practical approach to developing efficient neural architectures.
  arXiv  Detail & Related papers  (2025-06-11T13:26:09Z)
• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices [3.591566487849146]
  Binary neural networks (BNNs) tackle the issue with extreme compression and speed-up gains compared to real-valued models. We propose a simple but effective method to accelerate inference through unifying BNNs with an early-exiting strategy. Our approach allows simple instances to exit early based on a decision threshold and utilizes output layers added to different intermediate layers to avoid executing the entire binary model.
  arXiv  Detail & Related papers  (2022-06-17T22:11:11Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)

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.