PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning

• URL: http://arxiv.org/abs/2602.20537v1
• Date: Tue, 24 Feb 2026 04:31:12 GMT
• Title: PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning
• Authors: Xinyong Cai, Changbin Sun, Yong Wang, Hongyu Yang, Yuankai Wu,
• Abstract summary: PFGNet is a fully convolutional framework that dynamically modulates receptive fields through pixel-wise frequency-guided gating.<n> PFGNet delivers SOTA or near-SOTA forecasting performance with substantially fewer parameters and FLOPs.
• Score: 27.26429269735324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatiotemporal predictive learning (STPL) aims to forecast future frames from past observations and is essential across a wide range of applications. Compared with recurrent or hybrid architectures, pure convolutional models offer superior efficiency and full parallelism, yet their fixed receptive fields limit their ability to adaptively capture spatially varying motion patterns. Inspired by biological center-surround organization and frequency-selective signal processing, we propose PFGNet, a fully convolutional framework that dynamically modulates receptive fields through pixel-wise frequency-guided gating. The core Peripheral Frequency Gating (PFG) block extracts localized spectral cues and adaptively fuses multi-scale large-kernel peripheral responses with learnable center suppression, effectively forming spatially adaptive band-pass filters. To maintain efficiency, all large kernels are decomposed into separable 1D convolutions ($1 \times k$ followed by $k \times 1$), reducing per-channel computational cost from $O(k^2)$ to $O(2k)$. PFGNet enables structure-aware spatiotemporal modeling without recurrence or attention. Experiments on Moving MNIST, TaxiBJ, Human3.6M, and KTH show that PFGNet delivers SOTA or near-SOTA forecasting performance with substantially fewer parameters and FLOPs. Our code is available at https://github.com/fhjdqaq/PFGNet.

Related papers

• GlimmerNet: A Lightweight Grouped Dilated Depthwise Convolutions for UAV-Based Emergency Monitoring [0.0]
  GlimmerNet is an ultra-lightweight convolutional network built on the principle of separating receptive field diversity from feature recombination.<n>With just 31K parameters and 29% fewer FLOPs than the most recent baseline, GlimmerNet achieves a new state-of-the-art weighted F1-score of 0.966 on the UAV-focused Av2 dataset.
  arXiv  Detail & Related papers  (2025-12-08T10:24:19Z)
• SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts [2.200751835496112]
  Long-context transformers face significant efficiency challenges due to the quadratic cost of self-attention.<n>We introduce SPECTRE, a method that replaces each attention head with a fast real FFT.<n>We extend this efficiency to autoregressive generation through our Prefix-FFT cache and enhance local feature representation with an optional wavelet module.
  arXiv  Detail & Related papers  (2025-02-25T17:43:43Z)
• RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations [8.346566205092433]
  RecConv is a decomposition strategy that efficiently constructs multi-frequency representations using small- Kernel convolutions.<n> RecNeXt-M3 outperforms RepViT-M1.1 by 1.9 $APbox$ on COCO with similar FLOPs.
  arXiv  Detail & Related papers  (2024-12-27T13:13:52Z)
• Constraints and Variables Reduction for Optimal Power Flow Using Hierarchical Graph Neural Networks with Virtual Node-Splitting [0.24554686192257422]
  Power system networks are often modeled as homogeneous graphs, which limits the ability of graph neural network (GNN) to capture individual generator features at the same nodes.<n>By introducing the proposed virtual node-splitting strategy, generator-level attributes like costs, limits, and ramp rates can be fully captured by GNN models.<n>Two-stage adaptive hierarchical GNN is developed to (i) predict critical lines that would be congested, and then (ii) predict base generators that would operate at the maximum capacity.
  arXiv  Detail & Related papers  (2024-11-09T19:46:28Z)
• Dynamic Frame Interpolation in Wavelet Domain [57.25341639095404]
  Video frame is an important low-level computation vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts.
  arXiv  Detail & Related papers  (2023-09-07T06:41:15Z)
• Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF [6.135925201075925]
  We propose the dynamic PlenOctree DOT, which adaptively refines the sample distribution to adjust to changing scene complexity. Compared with POT, our DOT outperforms it by enhancing visual quality, reducing over $55.15$/$68.84%$ parameters, and providing 1.7/1.9 times FPS for NeRF-synthetic and Tanks $&$ Temples, respectively.
  arXiv  Detail & Related papers  (2023-07-28T06:21:42Z)
• CFDP: Common Frequency Domain Pruning [0.3021678014343889]
  We introduce a novel end-to-end pipeline for model pruning via the frequency domain. We have achieved state-of-the-art results on CIFAR-10 with GoogLeNet reaching an accuracy of 95.25%, that is, +0.2% from the original model. In addition to notable performances, models produced via CFDP exhibit robustness to a variety of configurations.
  arXiv  Detail & Related papers  (2023-06-07T04:49:26Z)
• Adaptive Split-Fusion Transformer [90.04885335911729]
  We propose an Adaptive Split-Fusion Transformer (ASF-former) to treat convolutional and attention branches differently with adaptive weights. Experiments on standard benchmarks, such as ImageNet-1K, show that our ASF-former outperforms its CNN, transformer counterparts, and hybrid pilots in terms of accuracy.
  arXiv  Detail & Related papers  (2022-04-26T10:00:28Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking [72.65494220685525]
  We propose a new dynamic modality-aware filter generation module (named MFGNet) to boost the message communication between visible and thermal data. We generate dynamic modality-aware filters with two independent networks. The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively. To address issues caused by heavy occlusion, fast motion, and out-of-view, we propose to conduct a joint local and global search by exploiting a new direction-aware target-driven attention mechanism.
  arXiv  Detail & Related papers  (2021-07-22T03:10:51Z)
• Global Filter Networks for Image Classification [90.81352483076323]
  We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
  arXiv  Detail & Related papers  (2021-07-01T17:58:16Z)
• PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer [76.44375136492827]
  Convolutional Neural Networks (CNNs) are often scale-sensitive. We bridge this regret by exploiting multi-scale features in a finer granularity. The proposed convolution operation, named Poly-Scale Convolution (PSConv), mixes up a spectrum of dilation rates.
  arXiv  Detail & Related papers  (2020-07-13T05:14:11Z)

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.