Resolving References in Visually-Grounded Dialogue via Text Generation

• URL: http://arxiv.org/abs/2309.13430v1
• Date: Sat, 23 Sep 2023 17:07:54 GMT
• Title: Resolving References in Visually-Grounded Dialogue via Text Generation
• Authors: Bram Willemsen, Livia Qian, Gabriel Skantze
• Abstract summary: Vision-language models (VLMs) have shown to be effective at image retrieval based on simple text queries, but text-image retrieval based on conversational input remains a challenge. We propose fine-tuning a causal large language model (LLM) to generate definite descriptions that summarize coreferential information found in the linguistic context of references. We then use a pretrained VLM to identify referents based on the generated descriptions, zero-shot.
• Score: 3.8673630752805446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) have shown to be effective at image retrieval based on simple text queries, but text-image retrieval based on conversational input remains a challenge. Consequently, if we want to use VLMs for reference resolution in visually-grounded dialogue, the discourse processing capabilities of these models need to be augmented. To address this issue, we propose fine-tuning a causal large language model (LLM) to generate definite descriptions that summarize coreferential information found in the linguistic context of references. We then use a pretrained VLM to identify referents based on the generated descriptions, zero-shot. We evaluate our approach on a manually annotated dataset of visually-grounded dialogues and achieve results that, on average, exceed the performance of the baselines we compare against. Furthermore, we find that using referent descriptions based on larger context windows has the potential to yield higher returns.

Related papers

• Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models [2.3301643766310374]
  By utilizing multi-modal large language models (M-LLMs) that support visual prompting, we can extract image features and convert them into textual data. We show the superior precision and recall performance of our image retrieval method compared to conventional vision-language model-based methods. We also demonstrate that the retrieval performance can be improved by iteratively incorporating keywords into search queries.
  arXiv  Detail & Related papers  (2024-08-29T06:54:03Z)
• Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning? [29.237078890377514]
  Large Vision-Language Models (LVLMs) excel in integrating visual and linguistic contexts to produce detailed content. Using LVLMs to generate descriptions often faces the challenge of object hallucination (OH), where the output text misrepresents actual objects in the input image. This paper proposes a novel decoding strategy, Differentiated Beam Decoding (DBD), along with a reliable new set of evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-18T14:33:56Z)
• Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach [33.231639257323536]
  In this paper, we address the issue of dialogue-form context query within the interactive text-to-image retrieval task. By reformulating the dialogue-form context, we eliminate the necessity of fine-tuning a retrieval model on existing visual dialogue data. We construct the LLM questioner to generate non-redundant questions about the attributes of the target image.
  arXiv  Detail & Related papers  (2024-06-05T16:09:01Z)
• Towards Retrieval-Augmented Architectures for Image Captioning [81.11529834508424]
  This work presents a novel approach towards developing image captioning models that utilize an external kNN memory to improve the generation process. Specifically, we propose two model variants that incorporate a knowledge retriever component that is based on visual similarities. We experimentally validate our approach on COCO and nocaps datasets and demonstrate that incorporating an explicit external memory can significantly enhance the quality of captions.
  arXiv  Detail & Related papers  (2024-05-21T18:02:07Z)
• Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models and Vision Language Models [17.171715290673678]
  We propose an interactive image retrieval system capable of refining queries based on user relevance feedback. This system incorporates a vision language model (VLM) based image captioner to enhance the quality of text-based queries. To evaluate our system, we curate a new dataset by adapting the MSR-VTT video retrieval dataset to the image retrieval task.
  arXiv  Detail & Related papers  (2024-04-29T14:46:35Z)
• Generative Context-aware Fine-tuning of Self-supervised Speech Models [54.389711404209415]
  We study the use of generative large language models (LLM) generated context information. We propose an approach to distill the generated information during fine-tuning of self-supervised speech models. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks: automatic speech recognition, named entity recognition, and sentiment analysis.
  arXiv  Detail & Related papers  (2023-12-15T15:46:02Z)
• Sentence-level Prompts Benefit Composed Image Retrieval [69.78119883060006]
  Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. We propose to leverage pretrained V-L models, e.g., BLIP-2, to generate sentence-level prompts. Our proposed method performs favorably against the state-of-the-art CIR methods on the Fashion-IQ and CIRR datasets.
  arXiv  Detail & Related papers  (2023-10-09T07:31:44Z)
• Advancing Visual Grounding with Scene Knowledge: Benchmark and Method [74.72663425217522]
  Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Most existing VG datasets are constructed using simple description texts. We propose a novel benchmark of underlineScene underlineKnowledge-guided underlineVisual underlineGrounding.
  arXiv  Detail & Related papers  (2023-07-21T13:06:02Z)
• Generating Images with Multimodal Language Models [78.6660334861137]
  We propose a method to fuse frozen text-only large language models with pre-trained image encoder and decoder models. Our model demonstrates a wide suite of multimodal capabilities: image retrieval, novel image generation, and multimodal dialogue.
  arXiv  Detail & Related papers  (2023-05-26T19:22:03Z)
• Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations [3.5813777917429515]
  We focus on resolving references to visualizations on a large screen display in multimodal dialogue. We describe our annotations for user references to visualizations appearing on a large screen via language and hand gesture. We report results on detecting and resolving references, effectiveness of contextual information on the model, and under-specified requests for creating visualizations.
  arXiv  Detail & Related papers  (2022-09-06T04:43:28Z)
• Visually-Augmented Language Modeling [137.36789885105642]
  We propose a novel pre-training framework, named VaLM, to Visually-augment text tokens with retrieved relevant images for Language Modeling. With the visually-augmented context, VaLM uses a visual knowledge fusion layer to enable multimodal grounded language modeling. We evaluate the proposed model on various multimodal commonsense reasoning tasks, which require visual information to excel.
  arXiv  Detail & Related papers  (2022-05-20T13:41:12Z)

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.