KAN-FPN-Stem:A KAN-Enhanced Feature Pyramid Stem for Boosting ViT-based Pose Estimation

• URL: http://arxiv.org/abs/2512.22228v1
• Date: Tue, 23 Dec 2025 03:57:41 GMT
• Title: KAN-FPN-Stem:A KAN-Enhanced Feature Pyramid Stem for Boosting ViT-based Pose Estimation
• Authors: HaoNan Tang,
• Abstract summary: Vision Transformers (ViT) have demonstrated significant promise in dense prediction tasks such as pose estimation.<n>ViT front-end often lies not in 'feature refinement' (Attention) but in the quality of 'feature fusion' (Fusion)
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers (ViT) have demonstrated significant promise in dense prediction tasks such as pose estimation. However, their performance is frequently constrained by the overly simplistic front-end designs employed in models like ViTPose. This naive patchification mechanism struggles to effectively handle multi-scale variations and results in irreversible information loss during the initial feature extraction phase. To overcome this limitation, we introduce a novel KAN-enhanced FPN-Stem architecture. Through rigorous ablation studies, we first identified that the true bottleneck for performance improvement lies not in plug-and-play attention modules (e.g., CBAM), but in the post-fusion non-linear smoothing step within the FPN. Guided by this insight, our core innovation is to retain the classic "upsample-and-add" fusion stream of the FPN, but replace its terminal, standard linear 3x3 smoothing convolution with a powerful KAN-based convolutional layer. Leveraging its superior non-linear modeling capabilities, this KAN-based layer adaptively learns and rectifies the "artifacts" generated during the multi-scale fusion process. Extensive experiments on the COCO dataset demonstrate that our KAN-FPN-Stem achieves a significant performance boost of up to +2.0 AP over the lightweight ViTPose-S baseline. This work not only delivers a plug-and-play, high-performance module but, more importantly, reveals that: the performance bottleneck in ViT front-end often lies not in 'feature refinement' (Attention), but in the quality of 'feature fusion' (Fusion). Furthermore, it provides an effective path to address this bottleneck through the introduction of the KAN operator.

Related papers

• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation [47.409626500688866]
  We present the DINO Spherical Autoencoder (DINO-SAE), a framework that bridges semantic representation and pixel-level reconstruction.<n>Our approach achieves state-of-the-art reconstruction quality, reaching 0.37 rFID and 26.2 dB PSNR, while maintaining strong semantic alignment to the pretrained VFM.
  arXiv  Detail & Related papers  (2026-01-30T12:25:34Z)
• One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion [57.824020826432815]
  We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images.<n>We design a Dual-Domain Detail Perception Module, which enables handling high-resolution images without being limited by the ViT backbone.<n>We develop a feature-guided diffusion network, which can preserve high-frequency details during the restoration process.
  arXiv  Detail & Related papers  (2026-01-20T17:11:55Z)
• KANMixer: Can KAN Serve as a New Modeling Core for Long-term Time Series Forecasting? [17.96421618979159]
  We introduce KANMixer, a concise architecture integrating a multi-scale mixing backbone that fully leverages KAN's adaptive capabilities.<n>We show that KANMixer achieves state-of-the-art performance in 16 out of 28 experiments across seven benchmark datasets.
  arXiv  Detail & Related papers  (2025-08-03T04:03:13Z)
• EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning [27.081942683329416]
  We propose an effective approach to consolidate feature representations by regularizing drift in directions highly relevant to previous tasks.<n>EFC++ is better able to learn new tasks by maintaining model plasticity and significantly outperforms the state-of-the-art.
  arXiv  Detail & Related papers  (2025-03-13T15:01:19Z)
• ViKANformer: Embedding Kolmogorov Arnold Networks in Vision Transformers for Pattern-Based Learning [0.0]
  Vision Transformers (ViTs) have significantly advanced image classification by applying self-attention on patch embeddings.<n>In this paper, we propose ViKANformer, a Vision Transformer where we replace the sub-layers with Kolmogorov-Arnold Network (KAN) expansions.
  arXiv  Detail & Related papers  (2025-03-03T03:10:26Z)
• Towards Scalable and Deep Graph Neural Networks via Noise Masking [59.058558158296265]
  Graph Neural Networks (GNNs) have achieved remarkable success in many graph mining tasks.<n> scaling them to large graphs is challenging due to the high computational and storage costs.<n>We present random walk with noise masking (RMask), a plug-and-play module compatible with the existing model-simplification works.
  arXiv  Detail & Related papers  (2024-12-19T07:48:14Z)
• Visual Fourier Prompt Tuning [63.66866445034855]
  We propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based models. Our approach incorporates the Fast Fourier Transform into prompt embeddings and harmoniously considers both spatial and frequency domain information. Our results demonstrate that our approach outperforms current state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2024-11-02T18:18:35Z)
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection [54.545054873239295]
  Deepfakes have recently raised significant trust issues and security concerns among the public.<n>ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance.<n>This work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach.
  arXiv  Detail & Related papers  (2024-04-12T13:02:08Z)
• VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations [25.88881764546414]
  VQ-NeRF is an efficient pipeline for enhancing implicit neural representations via vector quantization. We present an innovative multi-scale NeRF sampling scheme that concurrently optimize the NeRF model at both compressed and original scales. We incorporate a semantic loss function to improve the geometric fidelity and semantic coherence of our 3D reconstructions.
  arXiv  Detail & Related papers  (2023-10-23T01:41:38Z)
• Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning [96.75889543560497]
  In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. We propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations.
  arXiv  Detail & Related papers  (2021-03-01T21:14:33Z)

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.