Pre-Trained CNN Architecture for Transformer-Based Image Caption Generation Model

• URL: http://arxiv.org/abs/2509.17365v1
• Date: Mon, 22 Sep 2025 05:32:52 GMT
• Title: Pre-Trained CNN Architecture for Transformer-Based Image Caption Generation Model
• Authors: Amanuel Tafese Dufera,
• Abstract summary: This project presents a guide to constructing and comprehending transformer models for image captioning.<n>We leverage the well-established Transformer architecture, recognized for its effectiveness in managing sequential data.<n>Our approach exemplifies the utilization of parallelization for efficient training and inference.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic image captioning, a multifaceted task bridging computer vision and natural lan- guage processing, aims to generate descriptive textual content from visual input. While Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks have achieved significant advancements, they present limitations. The inherent sequential nature of RNNs leads to sluggish training and inference times. LSTMs further struggle with retaining information from earlier sequence elements when dealing with very long se- quences. This project presents a comprehensive guide to constructing and comprehending transformer models for image captioning. Transformers employ self-attention mechanisms, capturing both short- and long-range dependencies within the data. This facilitates efficient parallelization during both training and inference phases. We leverage the well-established Transformer architecture, recognized for its effectiveness in managing sequential data, and present a meticulous methodology. Utilizing the Flickr30k dataset, we conduct data pre- processing, construct a model architecture that integrates an EfficientNetB0 CNN for fea- ture extraction, and train the model with attention mechanisms incorporated. Our approach exemplifies the utilization of parallelization for efficient training and inference. You can find the project on GitHub.

Related papers

• Complementary and Contrastive Learning for Audio-Visual Segmentation [74.11434759171199]
  We present Complementary and Contrastive Transformer (CCFormer), a novel framework adept at processing both local and global information.<n>Our method sets new state-of-the-art benchmarks across the S4, MS3 and AVSS datasets.
  arXiv  Detail & Related papers  (2025-10-11T06:36:59Z)
• Foundations and Models in Modern Computer Vision: Key Building Blocks in Landmark Architectures [34.542592986038265]
  This report analyzes the evolution of key design patterns in computer vision by examining six influential papers.<n>We review ResNet, which introduced residual connections to overcome the vanishing gradient problem.<n>We examine the Vision Transformer (ViT), which established a new paradigm by applying the Transformer architecture to sequences of image patches.
  arXiv  Detail & Related papers  (2025-07-31T09:08:11Z)
• Efficient Point Transformer with Dynamic Token Aggregating for LiDAR Point Cloud Processing [19.73918716354272]
  LiDAR point cloud processing and analysis have made great progress due to the development of 3D Transformers.<n>Existing 3D Transformer methods usually are computationally expensive and inefficient due to their huge and redundant attention maps.<n>We propose an efficient point TransFormer with Dynamic Token Aggregating (DTA-Former) for point cloud representation and processing.
  arXiv  Detail & Related papers  (2024-05-23T20:50:50Z)
• Learning with SASQuaTCh: a Novel Variational Quantum Transformer Architecture with Kernel-Based Self-Attention [0.464982780843177]
  We present a variational quantum circuit architecture named Self-Attention Sequential Quantum Transformer Channel (SASQuaT)<n>Our approach leverages recent insights from kernel-based operator learning in the context of predicting vision transformer network using simple gate operations and a set of multi-dimensional quantum Fourier transforms.<n>To validate our approach, we consider image classification tasks in simulation and with hardware, where with only 9 qubits and a handful of parameters we are able to simultaneously embed and classify a grayscale image of handwritten digits with high accuracy.
  arXiv  Detail & Related papers  (2024-03-21T18:00:04Z)
• Todyformer: Towards Holistic Dynamic Graph Transformers with Structure-Aware Tokenization [6.799413002613627]
  Todyformer is a novel Transformer-based neural network tailored for dynamic graphs. It unifies the local encoding capacity of Message-Passing Neural Networks (MPNNs) with the global encoding of Transformers. We show that Todyformer consistently outperforms the state-of-the-art methods for downstream tasks.
  arXiv  Detail & Related papers  (2024-02-02T23:05:30Z)
• ConViViT -- A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition [3.6321891270689055]
  We propose a novel approach that leverages the strengths of both CNNs and Transformers in a hybrid architecture for performing activity recognition using RGB videos. Our architecture has achieved new SOTA results with 90.05 %, 99.6%, and 95.09% on HMDB51, UCF101, and ETRI-Activity3D respectively.
  arXiv  Detail & Related papers  (2023-10-22T21:13:43Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution [64.25751738088015]
  Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks. Transformers that need to incorporate contextual information to extract features dynamically are neglected. We propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer.
  arXiv  Detail & Related papers  (2022-07-06T16:32:29Z)
• Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution [50.10987776141901]
  Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks. We introduce an effective hybrid architecture for super-resolution (SR) tasks, which leverages local features from CNNs and long-range dependencies captured by transformers. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-15T06:52:25Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)
• Curriculum By Smoothing [52.08553521577014]
  Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
  arXiv  Detail & Related papers  (2020-03-03T07:27:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.