When Better Eyes Lead to Blindness: A Diagnostic Study of the Information Bottleneck in CNN-LSTM Image Captioning Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Gupta, Hitesh Kumar
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918128149069824
author Gupta, Hitesh Kumar
author_facet Gupta, Hitesh Kumar
contents Image captioning, situated at the intersection of computer vision and natural language processing, requires a sophisticated understanding of both visual scenes and linguistic structure. While modern approaches are dominated by large-scale Transformer architectures, this paper documents a systematic, iterative development of foundational image captioning models, progressing from a simple CNN-LSTM encoder-decoder to a competitive attention-based system. This paper presents a series of five models, beginning with Genesis and concluding with Nexus, an advanced model featuring an EfficientNetV2B3 backbone and a dynamic attention mechanism. The experiments chart the impact of architectural enhancements and demonstrate a key finding within the classic CNN-LSTM paradigm: merely upgrading the visual backbone without a corresponding attention mechanism can degrade performance, as the single-vector bottleneck cannot transmit the richer visual detail. This insight validates the architectural shift to attention. Trained on the MS COCO 2017 dataset, the final model, Nexus, achieves a BLEU-4 score of 31.4, surpassing several foundational benchmarks and validating the iterative design process. This work provides a clear, replicable blueprint for understanding the core architectural principles that underpin modern vision-language tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18788
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Better Eyes Lead to Blindness: A Diagnostic Study of the Information Bottleneck in CNN-LSTM Image Captioning Models
Gupta, Hitesh Kumar
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Image captioning, situated at the intersection of computer vision and natural language processing, requires a sophisticated understanding of both visual scenes and linguistic structure. While modern approaches are dominated by large-scale Transformer architectures, this paper documents a systematic, iterative development of foundational image captioning models, progressing from a simple CNN-LSTM encoder-decoder to a competitive attention-based system. This paper presents a series of five models, beginning with Genesis and concluding with Nexus, an advanced model featuring an EfficientNetV2B3 backbone and a dynamic attention mechanism. The experiments chart the impact of architectural enhancements and demonstrate a key finding within the classic CNN-LSTM paradigm: merely upgrading the visual backbone without a corresponding attention mechanism can degrade performance, as the single-vector bottleneck cannot transmit the richer visual detail. This insight validates the architectural shift to attention. Trained on the MS COCO 2017 dataset, the final model, Nexus, achieves a BLEU-4 score of 31.4, surpassing several foundational benchmarks and validating the iterative design process. This work provides a clear, replicable blueprint for understanding the core architectural principles that underpin modern vision-language tasks.
title When Better Eyes Lead to Blindness: A Diagnostic Study of the Information Bottleneck in CNN-LSTM Image Captioning Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.18788