# CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer

Source: [CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer](<https://www.sota2.com/research/paper/691d4f0bd6b0dd334292d6f5>)

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

Data updated: 2025-11-26T05:03:02.866Z

Authors: Srivathsan Sivakumar, Faisal Z. Qureshi

Published: 2025-11-18T03:51:15.000Z

## Abstract

Vision Transformers (ViTs) have demonstrated remarkable performance across a range of computer vision tasks; however, their high computational, memory, and energy demands hinder deployment on resource-constrained platforms. In this paper, we propose \\emph{Cascaded-ViT (CViT)}, a lightweight and compute-efficient vision transformer architecture featuring a novel feedforward network design called \\emph{Cascaded-Chunk Feed Forward Network (CCFFN)}. By splitting input features, CCFFN improves parameter and FLOP efficiency without sacrificing accuracy. Experiments on ImageNet-1K show that our \\emph{CViT-XL} model achieves 75.5\\% Top-1 accuracy while reducing FLOPs by 15\\% and energy consumption by 3.3\\% compared to EfficientViT-M5. Across various model sizes, the CViT family consistently exhibits the lowest energy consumption, making it suitable for deployment on battery-constrained devices such as mobile phones and drones. Furthermore, when evaluated using a new metric called \\emph{Accuracy-Per-FLOP (APF)}, which quantifies compute efficiency relative to accuracy, CViT models consistently achieve top-ranking efficiency. Particularly, CViT-L is 2.2\\% more accurate than EfficientViT-M2 while having comparable APF scores.

## 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/2511.14111>)

[PDF](<https://arxiv.org/pdf/2511.14111.pdf>)
