{"ID":2891076,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18788","arxiv_id":"2507.18788","title":"When Better Eyes Lead to Blindness: A Diagnostic Study of the Information Bottleneck in CNN-LSTM Image Captioning Models","abstract":"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.","short_abstract":"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 developme...","url_abs":"https://arxiv.org/abs/2507.18788","url_pdf":"https://arxiv.org/pdf/2507.18788v2","authors":"[\"Hitesh Kumar Gupta\"]","published":"2025-07-24T20:20:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}