A novel evaluation framework called Image2Text2Image is proposed, which leverages diffusion models, such as Stable Diffusion or DALL-E, for text-to-image generation, and does not rely on human-annotated reference cap-tions, making it a valuable tool for assessing image captioning models.
A multi-dimensional image quality assessment framework for T2I tasks that can not only distinguish overall performance differences across models, but also provide interpretable results at the level of individual dimensions is proposed.
It is argued that annotation at ImageNet scale cannot realistically be completed in one pass, as errors and definitional issues are discovered only through annotating, and the pipeline is built around repeated refinement and error checking.
Failure analysis shows that the leading systems primarily lose points through object miscounting and geometric artifacts, whereas the trailing systems more frequently produce garbled text, and Ideogram 3.0 also frequently omits requested elements.
Sajjad Abdoli, Ghassan Al-Sumaidaee, Ahmed Rashad· 1 citation
Experiments on a new approach for fine-grained evaluation demonstrate that this approach enhances a model’s ability to understand fine-grained differences.
Aozhu Chen, Hazel Doughty, Xirong Li et al.· 0 citations
It is shown that paragraph supervision enables effective use of long token sequences, whereas caption-only training degrades beyond 60 tokens, and paragraph supervision consistently benefits long-description benchmarks and hard negatives prove detrimental in text-only fine-tuning.
Mahyar Ghazanfari, Amin Tabrizian, Arsyi Aziz et al.· 0 citations
The novel task of cross-modal query suggestion is introduced, which interactively guides users by suggesting textual refinements based on visual clusters identified in the retrieval results, and the creation of CroQS, a benchmark dataset comprising 50 diverse queries and 295 semantic clusters in generic domain.
Giacomo Pacini, Nicola Messina, Nicola Tonellotto et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
