pith. sign in

arxiv: 2410.07336 · v2 · pith:ZHQV4COBnew · submitted 2024-10-09 · 💻 cs.CV · cs.AI· cs.CL· cs.MM

Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training

classification 💻 cs.CV cs.AIcs.CLcs.MM
keywords captionspac-scaptioningevaluationfine-tuningmetricsmodelmodels
0
0 comments X
read the original abstract

Despite significant advancements in caption generation, existing evaluation metrics often fail to capture the full quality or fine-grained details of captions. This is mainly due to their reliance on non-specific human-written references or noisy pre-training data. Still, finding an effective metric is crucial not only for captions evaluation but also for the generation phase. Metrics can indeed play a key role in the fine-tuning stage of captioning models, ultimately enhancing the quality of the generated captions. In this paper, we propose PAC-S++, a learnable metric that leverages the CLIP model, pre-trained on both web-collected and cleaned data and regularized through additional pairs of generated visual and textual positive samples. Exploiting this stronger and curated pre-training, we also apply PAC-S++ as a reward in the Self-Critical Sequence Training (SCST) stage typically employed to fine-tune captioning models. Extensive experiments on different image and video datasets highlight the effectiveness of PAC-S++ compared to popular metrics for the task, including its sensitivity to object hallucinations. Furthermore, we show that integrating PAC-S++ into the fine-tuning stage of a captioning model results in semantically richer captions with fewer repetitions and grammatical errors. Evaluations on out-of-domain benchmarks further demonstrate the efficacy of our fine-tuning approach in enhancing model capabilities. Source code and trained models are publicly available at: https://github.com/aimagelab/pacscore.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. Do Image-Text Metrics Respect Semantic Invariances?

    cs.CV 2026-05 unverdicted novelty 7.0

    Five image-text metrics exhibit non-semantic sensitivities to spatial, object, and socio-linguistic perturbations, shifting scores by 6-9% on average and flipping rankings in up to 37% of cases, with a proposed post-h...