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

2025-03-03 · Pankaj Choudhury, Yogesh Aggarwal, Prabhanjan Jadhav, Prithwijit Guha, Sukumar Nandi

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.

📄 PDF Abstract BibTeX arXiv:2503.01453

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder Image Captioning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…

Image Caption Generation Framework for Assamese News using Attention Mechanism

2021-12-01 · ICON 2021 12 · Ringki Das, Thoudam Doren Singh

Automatic caption generation is an artificial intelligence problem that falls at the intersection of computer vision and natural language processing. Although significant works have been reported in image captioning, the…

Caption Generation Decoder Image Captioning

Image Caption Generation for Low-Resource Assamese Language

2022-11-01 · ROCLING 2022 11 · Prachurya Nath, Prottay Kumar Adhikary, Pankaj Dadure, Partha Pakray 외

Image captioning is a prominent Artificial Intelligence (AI) research area that deals with visual recognition and a linguistic description of the image. It is an interdisciplinary field concerning how computers can see a…

Caption Generation Decoder Image Captioning Machine Translation+1

AsPOS: Assamese Part of Speech Tagger using Deep Learning Approach

2022-12-14 · Dhrubajyoti Pathak, Sukumar Nandi, Priyankoo Sarmah

Part of Speech (POS) tagging is crucial to Natural Language Processing (NLP). It is a well-studied topic in several resource-rich languages. However, the development of computational linguistic resources is still in its …

Deep Learning Part-Of-Speech Tagging POS POS Tagging+1

Enhancing Assamese NLP Capabilities: Introducing a Centralized Dataset Repository

2024-10-15 · S. Tamang, D. J. Bora

This paper introduces a centralized, open-source dataset repository designed to advance NLP and NMT for Assamese, a low-resource language. The repository, available at GitHub, supports various tasks like sentiment analys…

Diversity Machine Translation named-entity-recognition Named Entity Recognition+4

AsNER - Annotated Dataset and Baseline for Assamese Named Entity recognition

2022-06-01 · LREC 2022 6 · Dhrubajyoti Pathak, Sukumar Nandi, Priyankoo Sarmah

We present the AsNER, a named entity annotation dataset for low resource Assamese language with a baseline Assamese NER model. The dataset contains about 99k tokens comprised of text from the speech of the Prime Minister…

named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)NER+1