Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters

• URL: http://arxiv.org/abs/2606.09924v1
• Date: Sun, 07 Jun 2026 09:19:44 GMT
• Title: Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters
• Abstract summary: We propose a framework that restructures a pretrained dense network into a hierarchical binary tree composed of a shared backbone, hierarchical routers, and specialized leaves.<n>Across CIFAR-100 / ResNet-50, ImageNet-1K / ResNet-50, and ModelNet40 / PointNet++, SigmaB-Net reduces per-inference active parameters by 58-60% while remaining within 1.72 percentage points (pp) of the dense baseline Top-1.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computation: the dense network cannot be retained on-chip, and every parameter must be loaded for every input. Existing model compression reduces this transfer only at the cost of permanent capacity loss. We propose Sigma-Branch (SigmaB), a framework that restructures a pretrained dense network into a hierarchical binary tree composed of a shared backbone, hierarchical routers, and specialized leaves. Pretrained weights are distributed across the tree via activation-based spherical k-means clustering, which jointly initializes router weights and per-branch channel allocations; soft-routing fine-tuning then aligns each leaf with its routed input subset. At inference, the resulting network executes only a single root-to-leaf path, reducing the active-parameter footprint while storing the complete dense parameter set in memory. Across CIFAR-100 / ResNet-50, ImageNet-1K / ResNet-50, and ModelNet40 / PointNet++, SigmaB-Net reduces per-inference active parameters by 58-60% while remaining within 1.72 percentage points (pp) of the dense baseline Top-1. At comparable ImageNet-1K Top-1, the active-parameter reduction exceeds static structured pruning (FPGM, HRank) by 14-23 pp. The cross-modal evaluation, spanning 2D vision and 3D point-cloud backbones, substantiates a framework-level claim that decouples per-inference memory traffic from the total parameter count.

Related papers

• Progressive Supernet Training for Efficient Visual Autoregressive Modeling [56.15415456746672]
  We propose a training strategy that breaks through the frontier of generation quality for both paradigms and the full network.<n>Experiments on ImageNet demonstrate that, compared to the pretrained VAR-d30, VARiant-d16 and VARiant-d8 achieve nearly equivalent quality.<n> VARiant-d2 achieves 3.5 times speedup and 80% memory reduction at moderate quality cost.
  arXiv  Detail & Related papers  (2025-11-20T16:59:24Z)
• Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration [1.3225694028747144]
  This paper presents an efficient Loss-Aware Automatic Selection of Structured Pruning Criteria (LAASP) for slimming and accelerating deep neural networks.<n>The pruning-while-training approach eliminates the first stage and integrates the second and third stages into a single cycle.<n>Experiments on the VGGNet and ResNet models on the CIFAR-10 and ImageNet benchmark datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2025-06-25T06:18:46Z)
• A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks [0.24578723416255746]
  We propose a multi-objective evolutionary algorithm (MOEA) based compression framework independent of neural network architecture, dimension, task, and dataset.<n>We use uniformly sized bins to quantize network weights into a single codebook for efficient weight representation.<n>The experimental results show that we can reduce the neural network memory by $13.72 sim14.98 times$ on CIFAR-10, $11.61 sim 12.99times$ on CIFAR-100, and $7.44 sim 8.58times$ on ImageNet.
  arXiv  Detail & Related papers  (2025-01-06T15:51:29Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Pruning Neural Networks with Interpolative Decompositions [5.377278489623063]
  We introduce a principled approach to neural network pruning that casts the problem as a structured low-rank matrix approximation. We demonstrate how to prune a neural network by first building a set of primitives to prune a single fully connected or convolution layer. We achieve an accuracy of 93.62 $pm$ 0.36% using VGG-16 on CIFAR-10, with a 51% FLOPS reduction.
  arXiv  Detail & Related papers  (2021-07-30T20:13:49Z)
• 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)
• Layer Pruning via Fusible Residual Convolutional Block for Deep Neural Networks [15.64167076052513]
  layer pruning has less inference time and runtime memory usage when the same FLOPs and number of parameters are pruned. We propose a simple layer pruning method using residual convolutional block (ResConv) Our pruning method achieves excellent performance of compression and acceleration over the state-thearts on different datasets.
  arXiv  Detail & Related papers  (2020-11-29T12:51:16Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Towards Lossless Binary Convolutional Neural Networks Using Piecewise Approximation [4.023728681102073]
  CNNs can significantly reduce the number of arithmetic operations and the size of memory storage. However, the accuracy degradation of single and multiple binary CNNs is unacceptable for modern architectures. We propose a Piecewise Approximation scheme for multiple binary CNNs which lessens accuracy loss by approximating full precision weights and activations.
  arXiv  Detail & Related papers  (2020-08-08T13:32:33Z)
• ThriftyNets : Convolutional Neural Networks with Tiny Parameter Budget [4.438259529250529]
  We propose a new convolutional neural network architecture, called ThriftyNet. In ThriftyNet, only one convolutional layer is defined and used recursively, leading to a maximal parameter factorization. We achieve competitive performance on a tiny parameters budget, exceeding 91% accuracy on CIFAR-10 with less than 40K parameters in total, and 74.3% on CIFAR-100 with less than 600K parameters.
  arXiv  Detail & Related papers  (2020-07-20T13:50:51Z)
• DHP: Differentiable Meta Pruning via HyperNetworks [158.69345612783198]
  This paper introduces a differentiable pruning method via hypernetworks for automatic network pruning. Latent vectors control the output channels of the convolutional layers in the backbone network and act as a handle for the pruning of the layers. Experiments are conducted on various networks for image classification, single image super-resolution, and denoising.
  arXiv  Detail & Related papers  (2020-03-30T17:59:18Z)

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.