Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization

• URL: http://arxiv.org/abs/2408.14547v1
• Date: Mon, 26 Aug 2024 18:00:33 GMT
• Title: Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization
• Authors: Nicholas Moratelli, Davide Caffagni, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara,
• Abstract summary: We propose a new training paradigm termed Direct CLIP-Based Optimization (DiCO) Our approach jointly learns and optimize a reward model that is distilled from a learnable captioning evaluator with high human correlation. DiCO not only exhibits improved stability and enhanced quality in the generated captions but also aligns more closely with human preferences compared to existing methods.
• Score: 44.008094698200026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when attempting to optimize modern and higher-quality metrics like CLIP-Score and PAC-Score, this training method often encounters instability and fails to acquire the genuine descriptive capabilities needed to produce fluent and informative captions. In this paper, we propose a new training paradigm termed Direct CLIP-Based Optimization (DiCO). Our approach jointly learns and optimizes a reward model that is distilled from a learnable captioning evaluator with high human correlation. This is done by solving a weighted classification problem directly inside the captioner. At the same time, DiCO prevents divergence from the original model, ensuring that fluency is maintained. DiCO not only exhibits improved stability and enhanced quality in the generated captions but also aligns more closely with human preferences compared to existing methods, especially in modern metrics. Additionally, it maintains competitive performance in traditional metrics. Our source code and trained models are publicly available at https://github.com/aimagelab/DiCO.

Related papers

• Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training [44.008094698200026]
  PAC-S++ is a learnable metric that leverages the CLIP model, pre-trained on both web-collected and cleaned data. 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.
  arXiv  Detail & Related papers  (2024-10-09T18:00:09Z)
• Fluent and Accurate Image Captioning with a Self-Trained Reward Model [47.213906345208315]
  We propose Self-Cap, a captioning approach that relies on a learnable reward model based on self-generated negatives. Our discriminator is a fine-tuned contrastive image-text model trained to promote caption correctness.
  arXiv  Detail & Related papers  (2024-08-29T18:00:03Z)
• Class Incremental Learning with Pre-trained Vision-Language Models [59.15538370859431]
  We propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation. Experiments on several conventional benchmarks consistently show a significant margin of improvement over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-10-31T10:45:03Z)
• Image Captioners Are Scalable Vision Learners Too [61.98796478791261]
  Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones. Our results show that plain image captioning is a more powerful pretraining strategy than was previously believed.
  arXiv  Detail & Related papers  (2023-06-13T17:18:01Z)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)
• Efficient Modeling of Future Context for Image Captioning [38.52032153180971]
  Non-Autoregressive Image Captioning ( NAIC) can leverage two-side relation with modified mask operation. Our proposed approach clearly surpass the state-of-the-art baselines in both automatic metrics and human evaluations.
  arXiv  Detail & Related papers  (2022-07-22T06:21:43Z)
• Prompt-based Learning for Unpaired Image Captioning [86.44188293709307]
  Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Recent successes of Vision-Language Pre-Trained Models (VL-PTMs) have triggered the development of prompt-based learning. We present in this paper a novel scheme based on prompt to train the UIC model, making best use of the powerful generalization ability.
  arXiv  Detail & Related papers  (2022-05-26T03:13:43Z)
• ClipCap: CLIP Prefix for Image Captioning [6.69087470775851]
  We use CLIP encoding as a prefix to the caption, by employing a simple mapping network, and then fine-tunes a language model to generate the image captions. We demonstrate our model achieves comparable results to state-of-the-art methods on the challenging Conceptual Captions and nocaps datasets.
  arXiv  Detail & Related papers  (2021-11-18T14:49:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.