# EVCC: Enhanced Vision Transformer-ConvNeXt-CoAtNet Fusion for Classification

Source: [EVCC: Enhanced Vision Transformer-ConvNeXt-CoAtNet Fusion for Classification](<https://www.sota2.com/research/paper/6925389dd6b0dd334292f964>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-26T05:05:12.736Z

Authors: Kazi Reyazul Hasan, Md Nafiu Rahman, Wasif Jalal, Sadif Ahmed, Shahriar Raj, Mubasshira Musarrat, Muhammad Abdullah Adnan

Published: 2025-11-24T02:11:19.000Z

## Abstract

Hybrid vision architectures combining Transformers and CNNs have significantly advanced image classification, but they usually do so at significant computational cost. We introduce EVCC (Enhanced Vision Transformer-ConvNeXt-CoAtNet), a novel multi-branch architecture integrating the Vision Transformer, lightweight ConvNeXt, and CoAtNet through key innovations: (1) adaptive token pruning with information preservation, (2) gated bidirectional cross-attention for enhanced feature refinement, (3) auxiliary classification heads for multi-task learning, and (4) a dynamic router gate employing context-aware confidence-driven weighting. Experiments across the CIFAR-100, Tobacco3482, CelebA, and Brain Cancer datasets demonstrate EVCC's superiority over powerful models like DeiT-Base, MaxViT-Base, and CrossViT-Base by consistently achieving state-of-the-art accuracy with improvements of up to 2 percentage points, while reducing FLOPs by 25 to 35%. Our adaptive architecture adjusts computational demands to deployment needs by dynamically reducing token count, efficiently balancing the accuracy-efficiency trade-off while combining global context, local details, and hierarchical features for real-world applications. The source code of our implementation is available at https://anonymous.4open.science/r/EVCC.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.18691>)

[PDF](<https://arxiv.org/pdf/2511.18691.pdf>)
