Covariance-Aware Goodness for Scalable Forward-Forward Learning

• URL: http://arxiv.org/abs/2605.04346v1
• Date: Tue, 05 May 2026 23:08:00 GMT
• Title: Covariance-Aware Goodness for Scalable Forward-Forward Learning
• Abstract summary: In convolutional settings, Forward-Forward methods significantly under-perform backpropagation on complex benchmarks.<n>We propose a framework centered on three key components.<n>The resulting BP-free model achieves 73.01% on ImageNet-100 and 50.30% on Tiny-ImageNet.
• Score: 8.12004710498018
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-free FF methods significantly under-perform backpropagation on complex benchmarks such as ImageNet-100 and Tiny-ImageNet. We identify this gap as a structural bottleneck in goodness extraction: standard sum-of-squares formulation collapses feature volumes into channel-wise activation energies which omits critical second-order dependencies. To address this, we propose a framework centered on three key components. First, Bi-axis Covariance Goodness(BiCovG) explicitly augments the standard goodness function with structured second-order information along two axes: cross-channel projections that model inter-feature covariance, and nested multi-scale aggregation that encodes spatial correlation statistics. This provides a tractable approximation to covariance-aware goodness without the prohibitive O(C^2) complexity of explicit matrix estimation. Second, a lightweight Logistic Fusion module aggregates layer-wise predictions, amplifying the contribution of deeper representations. Third, the Feature Alignment Layer(FAL) introduces a zero-initialized correction at block boundaries to mitigate representation misalignment in deep locally trained networks. By introducing these three components, we effectively double the depth of viable Forward-Forward learning, extending robust layer utilization from shallow baselines to 16 layer architectures like VGG-16. The resulting BP-free model achieves 73.01% on ImageNet-100 and 50.30% on Tiny-ImageNet. As a practical extension, Hybrid Goodness Blocks control the scope of gradient propagation via configurable block sizes, further narrowing the ImageNet-100 gap to 3.6% and matching BP on Tiny-ImageNet, while still reducing peak memory by approximately 50% relative to BP.

Related papers

• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• Semantically Stable Image Composition Analysisvia Saliency and Gradient Vector Flow Fusion [0.5249805590164902]
  We introduce VFCNet, which fuses saliency and edge information into a gradient vector flow field.<n>The model computes dual-stream GVF representations, integrates them via attention, and extracts multi-scale flow features.<n>VFCNet achieves state-of-the-art performance on the PICD benchmark.
  arXiv  Detail & Related papers  (2026-04-14T09:53:19Z)
• Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction [9.96771578356719]
  Existing approaches rely on increasingly complex network architectures to regress depth maps.<n>We propose a multilevel conditional random field (CRF) model built upon the Swin Transformer backbone.<n>Our method achieves state-of-the-art performance, reducing Abs Rel to 0.088 ($-$7.4%) and RMSE to 0.316 ($-$5.4%) on NYU Depth v2, while attaining near-perfect threshold accuracy.
  arXiv  Detail & Related papers  (2026-04-03T07:59:26Z)
• VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification [1.9903316442426757]
  This paper introduces VeloxNet, a lightweight CNN architecture that replaces SqueezeNet's fire modules with gated multi-layer perceptron blocks for embedded image classification.<n>We evaluate VeloxNet on three aerial image datasets.
  arXiv  Detail & Related papers  (2026-03-19T21:46:20Z)
• Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation [18.560389397187794]
  We introduce RETA -- a Retrieval and Topology Alignment framework for decoupled DD.<n>First, Dynamic Retrieval Connection (DRC) selects a real patch from a prebuilt pool.<n>Second, Persistent Topology Alignment (PTA) regularizes synthesis with persistent homology.
  arXiv  Detail & Related papers  (2026-02-27T16:21:07Z)
• Binarized Spectral Compressive Imaging [59.18636040850608]
  Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources. We propose a novel method, Binarized Spectral-Redistribution Network (BiSRNet) BiSRNet is derived by using the proposed techniques to binarize the base model.
  arXiv  Detail & Related papers  (2023-05-17T15:36:08Z)
• SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation [65.4396959244269]
  The paper tackles the challenge by designing a general framework to construct 3D learning architectures. The proposed approach can be applied to general backbones like PointNet and DGCNN. Experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation, and accuracy.
  arXiv  Detail & Related papers  (2022-09-13T12:12:19Z)
• Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images [42.26124628784883]
  We propose a compact, efficient, and end-to-end learning-based framework, namely AGD-Net. We first formulate the problem explicitly based on the classic gradient descent algorithm. AGD-Net can improve the reconstruction quality by more than 1.0 dB on average.
  arXiv  Detail & Related papers  (2021-08-12T05:54:09Z)
• Dynamic Convolution for 3D Point Cloud Instance Segmentation [146.7971476424351]
  We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. We gather homogeneous points that have identical semantic categories and close votes for the geometric centroids. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
  arXiv  Detail & Related papers  (2021-07-18T09:05:16Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks [57.0502745301132]
  We propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Our micro-dense block can be integrated with neural architecture search based models to boost their performance.
  arXiv  Detail & Related papers  (2020-04-19T08:34:52Z)

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.