MoTaDual: Modality-Task Dual Alignment for Enhanced Zero-shot Composed Image Retrieval

• URL: http://arxiv.org/abs/2410.23736v1
• Date: Thu, 31 Oct 2024 08:49:05 GMT
• Title: MoTaDual: Modality-Task Dual Alignment for Enhanced Zero-shot Composed Image Retrieval
• Authors: Haiwen Li, Fei Su, Zhicheng Zhao,
• Abstract summary: Composed Image Retrieval (CIR) is a challenging vision-language task, utilizing bi-modal (image+text) queries to retrieve target images. In this paper, we propose a two-stage framework to tackle both discrepancies. MoTaDual achieves the state-of-the-art performance across four widely used ZS-CIR benchmarks, while maintaining low training time and computational cost.
• Score: 20.612534837883892
• License:
• Abstract: Composed Image Retrieval (CIR) is a challenging vision-language task, utilizing bi-modal (image+text) queries to retrieve target images. Despite the impressive performance of supervised CIR, the dependence on costly, manually-labeled triplets limits its scalability and zero-shot capability. To address this issue, zero-shot composed image retrieval (ZS-CIR) is presented along with projection-based approaches. However, such methods face two major problems, i.e., task discrepancy between pre-training (image $\leftrightarrow$ text) and inference (image+text $\rightarrow$ image), and modality discrepancy. The latter pertains to approaches based on text-only projection training due to the necessity of feature extraction from the reference image during inference. In this paper, we propose a two-stage framework to tackle both discrepancies. First, to ensure efficiency and scalability, a textual inversion network is pre-trained on large-scale caption datasets. Subsequently, we put forward Modality-Task Dual Alignment (MoTaDual) as the second stage, where large-language models (LLMs) generate triplet data for fine-tuning, and additionally, prompt learning is introduced in a multi-modal context to effectively alleviate both modality and task discrepancies. The experimental results show that our MoTaDual achieves the state-of-the-art performance across four widely used ZS-CIR benchmarks, while maintaining low training time and computational cost. The code will be released soon.

Related papers

• Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity [2.724141845301679]
  Composed image retrieval (CIR) formulates the query as a combination of a reference image and modified text. We introduce a training-free approach for ZS-CIR. Our approach is simple, easy to implement, and its effectiveness is validated through experiments on the FashionIQ and CIRR datasets.
  arXiv  Detail & Related papers  (2024-09-07T21:52:58Z)
• VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models [76.94378391979228]
  We introduce a new, more demanding task known as Interleaved Image-Text (IITC) This task challenges models to discern and disregard superfluous elements in both images and text to accurately answer questions. In support of this task, we further craft a new VEGA dataset, tailored for the IITC task on scientific content, and devised a subtask, Image-Text Association (ITA)
  arXiv  Detail & Related papers  (2024-06-14T17:59:40Z)
• Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval [92.13664084464514]
  The task of composed image retrieval (CIR) aims to retrieve images based on the query image and the text describing the users' intent. Existing methods have made great progress with the advanced large vision-language (VL) model in CIR task, however, they generally suffer from two main issues: lack of labeled triplets for model training and difficulty of deployment on resource-restricted environments. We propose Image2Sentence based Asymmetric zero-shot composed image retrieval (ISA), which takes advantage of the VL model and only relies on unlabeled images for composition learning.
  arXiv  Detail & Related papers  (2024-03-03T07:58:03Z)
• Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking [34.31345844296072]
  Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text. Most current composed image retrieval methods follow a supervised learning approach to training on a costly triplet dataset composed of a reference image, modified text, and a corresponding target image. We present a new training-free zero-shot composed image retrieval method which translates the query into explicit human-understandable text.
  arXiv  Detail & Related papers  (2023-12-14T13:31:01Z)
• Vision-by-Language for Training-Free Compositional Image Retrieval [78.60509831598745]
  Compositional Image Retrieval (CIR) aims to retrieve the relevant target image in a database. Recent research sidesteps this need by using large-scale vision-language models (VLMs) We propose to tackle CIR in a training-free manner via Vision-by-Language (CIReVL)
  arXiv  Detail & Related papers  (2023-10-13T17:59:38Z)
• Cross-Modal Retrieval Meets Inference:Improving Zero-Shot Classification with Cross-Modal Retrieval [29.838375158101027]
  Contrastive language-image pre-training (CLIP) has demonstrated remarkable zero-shot classification ability. We propose X-MoRe, a novel inference method comprising two key steps: (1) cross-modal retrieval and (2) modal-confidence-based ensemble. X-MoRe demonstrates robust performance across a diverse set of tasks without the need for additional training.
  arXiv  Detail & Related papers  (2023-08-29T13:02:35Z)
• Noisy-Correspondence Learning for Text-to-Image Person Re-identification [50.07634676709067]
  We propose a novel Robust Dual Embedding method (RDE) to learn robust visual-semantic associations even with noisy correspondences. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on three datasets.
  arXiv  Detail & Related papers  (2023-08-19T05:34:13Z)
• COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval [59.15034487974549]
  We propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval. Our COTS achieves the highest performance among all two-stream methods and comparable performance with 10,800X faster in inference. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.
  arXiv  Detail & Related papers  (2022-04-15T12:34:47Z)
• SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning [79.30956389694184]
  Iterative Language-Based Image Editing (IL-BIE) tasks follow iterative instructions to edit images step by step. Data scarcity is a significant issue for ILBIE as it is challenging to collect large-scale examples of images before and after instruction-based changes. We introduce a Self-Supervised Counterfactual Reasoning framework that incorporates counterfactual thinking to overcome data scarcity.
  arXiv  Detail & Related papers  (2020-09-21T01:45:58Z)

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.