Mapping Networks
cs.CV
Submitted: 2026-02-22
Updated: 2026-02-22
Comments: 10 pages
Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 36215-36223
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: The escalating parameter counts in modern deep learning models pose a fundamental challenge to efficient training and resolution of overfitting.
Terminology
Abstract
The escalating parameter counts in modern deep learning models pose a fundamental challenge to efficient training and resolution of overfitting. We address this by introducing the Mapping Networks which replace the high dimensional weight space by a compact, trainable latent vector based on the hypothesis that the trained parameters of large networks reside on smooth, low-dimensional manifolds. Henceforth, the Mapping Theorem enforced by a dedicated Mapping Loss, shows the existence of a mapping from this latent space to the target weight space both theoretically and in practice. Mapping Networks significantly reduce overfitting and achieve comparable to better performance than target network across complex vision and sequence tasks, including Image Classification, Deepfake Detection etc, with 99.5%, i.e., around 500 times reduction in trainable parameters.
Sources
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- Measuring the Intrinsic Dimension of Objective Landscapes
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models