Updating CLIP to Prefer Descriptions Over Captions

• URL: http://arxiv.org/abs/2406.09458v2
• Date: Thu, 03 Oct 2024 22:10:20 GMT
• Title: Updating CLIP to Prefer Descriptions Over Captions
• Authors: Amir Zur, Elisa Kreiss, Karel D'Oosterlinck, Christopher Potts, Atticus Geiger,
• Abstract summary: We update the CLIP model to assign higher scores to descriptions than captions. This model correlates with the judgements of blind and low-vision people while preserving transfer capabilities.
• Score: 21.909877614471178
• License:
• Abstract: Although CLIPScore is a powerful generic metric that captures the similarity between a text and an image, it fails to distinguish between a caption that is meant to complement the information in an image and a description that is meant to replace an image entirely, e.g., for accessibility. We address this shortcoming by updating the CLIP model with the Concadia dataset to assign higher scores to descriptions than captions using parameter efficient fine-tuning and a loss objective derived from work on causal interpretability. This model correlates with the judgements of blind and low-vision people while preserving transfer capabilities and has interpretable structure that sheds light on the caption--description distinction.

Related papers

• TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives [65.82577305915643]
  Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. We show that generating hard'' negative captions via in-context learning and corresponding negative images with text-to-image generators offers a solution. We demonstrate that our method, named TripletCLIP, enhances the compositional capabilities of CLIP, resulting in an absolute improvement of over 9% on the SugarCrepe benchmark.
  arXiv  Detail & Related papers  (2024-11-04T19:24:59Z)
• Finetuning CLIP to Reason about Pairwise Differences [52.028073305958074]
  We propose an approach to train vision-language models such as CLIP in a contrastive manner to reason about differences in embedding space. We first demonstrate that our approach yields significantly improved capabilities in ranking images by a certain attribute. We also illustrate that the resulting embeddings obey a larger degree of geometric properties in embedding space.
  arXiv  Detail & Related papers  (2024-09-15T13:02:14Z)
• 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)
• Interpreting CLIP's Image Representation via Text-Based Decomposition [73.54377859089801]
  We investigate the CLIP image encoder by analyzing how individual model components affect the final representation. We decompose the image representation as a sum across individual image patches, model layers, and attention heads. We use this understanding to remove spurious features from CLIP and to create a strong zero-shot image segmenter.
  arXiv  Detail & Related papers  (2023-10-09T17:59:04Z)
• Cross-Domain Image Captioning with Discriminative Finetuning [20.585138136033905]
  Fine-tuning an out-of-the-box neural captioner with a self-supervised discriminative communication objective helps to recover a plain, visually descriptive language. We show that discriminatively finetuned captions are more helpful than either vanilla ClipCap captions or ground-truth captions for human annotators tasked with an image discrimination task.
  arXiv  Detail & Related papers  (2023-04-04T09:33:16Z)
• Fine-grained Image Captioning with CLIP Reward [104.71533106301598]
  We propose using CLIP, a multimodal encoder trained on huge image-text pairs from web, to calculate multimodal similarity and use it as a reward function. We also propose a simple finetuning strategy of the CLIP text encoder to improve grammar that does not require extra text annotation. In experiments on text-to-image retrieval and FineCapEval, the proposed CLIP-guided model generates more distinctive captions than the CIDEr-optimized model.
  arXiv  Detail & Related papers  (2022-05-26T02:46:09Z)
• No Token Left Behind: Explainability-Aided Image Classification and Generation [79.4957965474334]
  We present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input. Our method yields an improvement in the recognition rate, without additional training or fine-tuning.
  arXiv  Detail & Related papers  (2022-04-11T07:16:39Z)
• Intrinsic Image Captioning Evaluation [53.51379676690971]
  We propose a learning based metrics for image captioning, which we call Intrinsic Image Captioning Evaluation(I2CE) Experiment results show that our proposed method can keep robust performance and give more flexible scores to candidate captions when encountered with semantic similar expression or less aligned semantics.
  arXiv  Detail & Related papers  (2020-12-14T08:36:05Z)

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.