# AC-Lite : A Lightweight Image Captioning Model for Low-Resource Assamese Language

Source: [AC-Lite : A Lightweight Image Captioning Model for Low-Resource Assamese Language](<https://www.sota2.com/research/paper/68fa785b1e209131cea77f46>)

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

Data updated: 2025-10-26T04:36:17.760Z

Authors: Pankaj Choudhury, Yogesh Aggarwal, Prabhanjan Jadhav, Prithwijit Guha, Sukumar Nandi

Published: 2025-03-03T12:07:52.000Z

## Abstract

Most existing works in image caption synthesis use computation heavy deep neural networks and generates image descriptions in English language. This often restricts this important assistive tool for widespread use across language and accessibility barriers. This work presents AC-Lite, a computationally efficient model for image captioning in low-resource Assamese language. AC-Lite reduces computational requirements by replacing computation-heavy deep network components with lightweight alternatives. The AC-Lite model is designed through extensive ablation experiments with different image feature extractor networks and language decoders. A combination of ShuffleNetv2x1.5 with GRU based language decoder along with bilinear attention is found to provide the best performance with minimum compute. AC-Lite was observed to achieve an 82.3 CIDEr score on the COCO-AC dataset with 2.45 GFLOPs and 22.87M parameters.

## 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/2503.01453>)

[PDF](<https://arxiv.org/pdf/2503.01453.pdf>)