Pith. sign in

REVIEW 1 cited by

A Frustratingly Simple Approach for End-to-End Image Captioning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.12723 v3 pith:RJT4TC3M submitted 2022-01-30 cs.CV cs.CL

classification cs.CVcs.CL
keywords captioningimageobjecttrainingcross-modalmodelsdetectordetectors
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works follow a traditional two-stage training paradigm. Before training the captioning models, an extra object detector is utilized to recognize the objects in the image at first. However, they require sizeable datasets with fine-grained object annotation for training the object detector, which is a daunting task. In addition, the errors of the object detectors are easy to propagate to the following captioning models, degenerating models' performance. To alleviate such defects, we propose a frustratingly simple but highly effective end-to-end image captioning framework, Visual Conditioned GPT (VC-GPT), by connecting the pre-trained visual encoder (CLIP-ViT) and language decoder (GPT2). Different from the vanilla connection method that directly inserts the cross-attention modules into GPT2, we come up with a self-ensemble cross-modal fusion mechanism that comprehensively considers both the single- and cross-modal knowledge. As a result, we do not need extra object detectors for model training. Experimental results conducted on three popular image captioning benchmarks (MSCOCO, Flickr30k and NoCaps) demonstrate that our VC-GPT achieves either the best or the second-best performance across all evaluation metrics over extensive baseline systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. EnVisionVR: A Scene Interpretation Tool for Visual Accessibility in Virtual Reality

    cs.HC 2025-02 conditional novelty 6.0 of 10

    A VLM-based VR accessibility tool significantly improved object localization for blind and low vision users, but did not significantly improve scene understanding or overall object interaction in a 12-participant evaluation.

Pith tools