Cover Image

Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jeffrey, Gregory, Jonathan, Chrysos, Grigorios G.
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MetaFormer Baselines for Vision
by: Yu, Weihao, et al.
Published: (2022)

High-throughput digital twin framework for predicting neurite deterioration using MetaFormer attention
by: Qian, Kuanren, et al.
Published: (2024)

Multilinear Operator Networks
by: Cheng, Yixin, et al.
Published: (2024)

Mitigating Diffusion Model Hallucinations with Dynamic Guidance
by: Triaridis, Kostas, et al.
Published: (2025)

Shaken or Stirred? An Analysis of MetaFormer's Token Mixing for Medical Imaging
by: Keuth, Ron, et al.
Published: (2025)

The Last Mile to Supervised Performance: Semi-Supervised Domain Adaptation for Semantic Segmentation
by: Morales-Brotons, Daniel, et al.
Published: (2024)

MetaFormer-driven Encoding Network for Robust Medical Semantic Segmentation
by: Tran, Le-Anh, et al.
Published: (2026)

mRadNet: A Compact Radar Object Detector with MetaFormer
by: Chen, Huaiyu, et al.
Published: (2025)

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
by: Oldfield, James, et al.
Published: (2024)

MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation
by: Kang, Beoungwoo, et al.
Published: (2024)

VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones
by: Shen, Lefei, et al.
Published: (2025)

Rethinking Attention: Polynomial Alternatives to Softmax in Transformers
by: Saratchandran, Hemanth, et al.
Published: (2024)

Vision Backbone Efficient Selection for Image Classification in Low-Data Regimes
by: Guerin, Joris, et al.
Published: (2024)

PNeRV: A Polynomial Neural Representation for Videos
by: Gupta, Sonam, et al.
Published: (2024)

Vision-LSTM: xLSTM as Generic Vision Backbone
by: Alkin, Benedikt, et al.
Published: (2024)

MI-NeRF: Learning a Single Face NeRF from Multiple Identities
by: Chatziagapi, Aggelina, et al.
Published: (2024)

MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition
by: Chatziagapi, Aggelina, et al.
Published: (2024)

AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer
by: Shan, Jiquan, et al.
Published: (2025)

Explaining the Impact of Training on Vision Models via Activation Clustering
by: Boubekki, Ahcène, et al.
Published: (2024)

ViR: Towards Efficient Vision Retention Backbones
by: Hatamizadeh, Ali, et al.
Published: (2023)

Pre-Trained Vision Models as Perception Backbones for Safety Filters in Autonomous Driving
by: Yang, Yuxuan, et al.
Published: (2024)

Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
by: Bellchambers, Gregory
Published: (2025)

Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decomposition
by: Drozdova, Mariia, et al.
Published: (2024)

When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing
by: Sun, Libo, et al.
Published: (2026)

Unlocking Pre-trained Image Backbones for Semantic Image Synthesis
by: Berrada, Tariq, et al.
Published: (2023)

Polyp Segmentation Generalisability of Pretrained Backbones
by: Sanderson, Edward, et al.
Published: (2024)

PerFormer: A Permutation Based Vision Transformer for Remaining Useful Life Prediction
by: Fan, Zhengyang, et al.
Published: (2025)

SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization
by: Hu, Xixu, et al.
Published: (2024)

GeoFormer: A Vision and Sequence Transformer-based Approach for Greenhouse Gas Monitoring
by: Khirwar, Madhav, et al.
Published: (2024)

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
by: Liu, Hui, et al.
Published: (2025)

SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones
by: Khazem, Salim
Published: (2026)

Graph Neural Networks in Vision-Language Image Understanding: A Survey
by: Senior, Henry, et al.
Published: (2023)

JetFormer: An Autoregressive Generative Model of Raw Images and Text
by: Tschannen, Michael, et al.
Published: (2024)

ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding
by: Setyawan, Novendra, et al.
Published: (2024)

MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization
by: Kim, Han-Byul, et al.
Published: (2023)

Enhancing Fingerprint Image Synthesis with GANs, Diffusion Models, and Style Transfer Techniques
by: Tang, W., et al.
Published: (2024)

Balanced Image Stylization with Style Matching Score
by: Jiang, Yuxin, et al.
Published: (2025)

Text-Guided Alternative Image Clustering
by: Stephan, Andreas, et al.
Published: (2024)

Using Backbone Foundation Model for Evaluating Fairness in Chest Radiography Without Demographic Data
by: Queiroz, Dilermando, et al.
Published: (2024)

Flatness Improves Backbone Generalisation in Few-shot Classification
by: Li, Rui, et al.
Published: (2024)