Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval

• URL: http://arxiv.org/abs/2311.16515v4
• Date: Tue, 20 May 2025 16:29:22 GMT
• Title: Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
• Authors: Delong Liu, Haiwen Li, Zhaohui Hou, Zhicheng Zhao, Fei Su, Yuan Dong,
• Abstract summary: We propose a new Composed Person Retrieval task, which combines visual and textual queries to identify individuals of interest from large-scale person image databases.<n>The foremost difficulty of the CPR task is the lack of available annotated datasets.<n>A multimodal filtering method is designed to ensure the resulting SynCPR dataset retains 1.15 million high-quality and fully synthetic triplets.
• Score: 20.225737169253826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Person retrieval has attracted rising attention. Existing methods are mainly divided into two retrieval modes, namely image-only and text-only. However, they are unable to make full use of the available information and are difficult to meet diverse application requirements. To address the above limitations, we propose a new Composed Person Retrieval (CPR) task, which combines visual and textual queries to identify individuals of interest from large-scale person image databases. Nevertheless, the foremost difficulty of the CPR task is the lack of available annotated datasets. Therefore, we first introduce a scalable automatic data synthesis pipeline, which decomposes complex multimodal data generation into the creation of textual quadruples followed by identity-consistent image synthesis using fine-tuned generative models. Meanwhile, a multimodal filtering method is designed to ensure the resulting SynCPR dataset retains 1.15 million high-quality and fully synthetic triplets. Additionally, to improve the representation of composed person queries, we propose a novel Fine-grained Adaptive Feature Alignment (FAFA) framework through fine-grained dynamic alignment and masked feature reasoning. Moreover, for objective evaluation, we manually annotate the Image-Text Composed Person Retrieval (ITCPR) test set. The extensive experiments demonstrate the effectiveness of the SynCPR dataset and the superiority of the proposed FAFA framework when compared with the state-of-the-art methods. All code and data will be provided at https://github.com/Delong-liu-bupt/Composed_Person_Retrieval.

Related papers

• Automatic Synthesis of High-Quality Triplet Data for Composed Image Retrieval [19.520776313567737]
  Composed Image Retrieval (CIR) aims to retrieve target images using multimodal (image+text) queries.<n>We propose a scalable pipeline for automatic triplet generation, along with a fully synthetic dataset named Composed Image Retrieval on High-quality Synthetic Triplets (CIRHS)
  arXiv  Detail & Related papers  (2025-07-08T13:24:05Z)
• An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval [51.10419281315848]
  We conduct an empirical study to explore the potential of synthetic data for Text-Based Person Retrieval (TBPR) research.<n>We propose an inter-class image generation pipeline, in which an automatic prompt construction strategy is introduced.<n>We develop an intra-class image augmentation pipeline, in which the generative AI models are applied to further edit the images.
  arXiv  Detail & Related papers  (2025-03-28T06:18:15Z)
• Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval [13.315951821189538]
  Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition processes. We propose to explore the intrinsic potential of Contrastive Language-Image Pre-training (CLIP) for OCR-free scene text retrieval.
  arXiv  Detail & Related papers  (2024-08-01T10:25:14Z)
• Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval [66.61856014573742]
  Text-based person retrieval (TPR) is a challenging task that involves retrieving a specific individual based on a textual description. Previous methods have attempted to align text and image samples in a modal-shared space. We propose an effective bi-directional one-to-many embedding paradigm that offers a clear optimization direction for each sample.
  arXiv  Detail & Related papers  (2024-06-09T03:06:55Z)
• Data Augmentation for Text-based Person Retrieval Using Large Language Models [16.120524750964016]
  Text-based Person Retrieval (TPR) aims to retrieve person images that match the description given a text query. It is difficult to construct a large-scale, high-quality TPR dataset due to expensive annotation and privacy protection. This paper proposes an LLM-based Data Augmentation (LLM-DA) method for TPR.
  arXiv  Detail & Related papers  (2024-05-20T11:57:50Z)
• RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning [69.23782518456932]
  We propose a novel zero-shot video captioning framework named Retrieval-Enhanced Test-Time Adaptation (RETTA) We bridge video and text using four key models: a general video-text retrieval model XCLIP, a general image-text matching model CLIP, a text alignment model AnglE, and a text generation model GPT-2. To address this problem, we propose using learnable tokens as a communication medium among these four frozen models GPT-2, XCLIP, CLIP, and AnglE.
  arXiv  Detail & Related papers  (2024-05-11T16:22:00Z)
• Adapting Dual-encoder Vision-language Models for Paraphrased Retrieval [55.90407811819347]
  We consider the task of paraphrased text-to-image retrieval where a model aims to return similar results given a pair of paraphrased queries. We train a dual-encoder model starting from a language model pretrained on a large text corpus. Compared to public dual-encoder models such as CLIP and OpenCLIP, the model trained with our best adaptation strategy achieves a significantly higher ranking similarity for paraphrased queries.
  arXiv  Detail & Related papers  (2024-05-06T06:30:17Z)
• Cross-lingual Contextualized Phrase Retrieval [63.80154430930898]
  We propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval. We train our Cross-lingual Contextualized Phrase Retriever (CCPR) using contrastive learning. On the phrase retrieval task, CCPR surpasses baselines by a significant margin, achieving a top-1 accuracy that is at least 13 points higher.
  arXiv  Detail & Related papers  (2024-03-25T14:46:51Z)
• Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training [33.51524424536508]
  Iterative Prompt Relabeling (IPR) is a novel algorithm that aligns images to text through iterative image sampling and prompt relabeling with feedback. We conduct thorough experiments on SDv2 and SDXL, testing their capability to follow instructions on spatial relations.
  arXiv  Detail & Related papers  (2023-12-23T11:10:43Z)
• Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search [60.626459715780605]
  Given a descriptive text query, text-based person search aims to retrieve the best-matched target person from an image gallery. Such a cross-modal retrieval task is quite challenging due to significant modality gap, fine-grained differences and insufficiency of annotated data. In this paper, we propose a simple yet effective dual Transformer model for text-based person search.
  arXiv  Detail & Related papers  (2023-11-15T16:26:49Z)
• Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification [42.791647210424664]
  The pre-training task is indispensable for the text-to-image person re-identification (T2I-ReID) task. There are two underlying inconsistencies between these two tasks that may impact the performance. We present a new unified pre-training pipeline (UniPT) designed specifically for the T2I-ReID task.
  arXiv  Detail & Related papers  (2023-09-04T08:11:36Z)
• Zero-shot Composed Text-Image Retrieval [72.43790281036584]
  We consider the problem of composed image retrieval (CIR) It aims to train a model that can fuse multi-modal information, e.g., text and images, to accurately retrieve images that match the query, extending the user's expression ability.
  arXiv  Detail & Related papers  (2023-06-12T17:56:01Z)
• TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision [61.186488081379]
  We propose TextFormer, a query-based end-to-end text spotter with Transformer architecture. TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multi-task modeling. It allows for mutual training and optimization of classification, segmentation, and recognition branches, resulting in deeper feature sharing.
  arXiv  Detail & Related papers  (2023-06-06T03:37:41Z)
• Text-based Person Search without Parallel Image-Text Data [52.63433741872629]
  Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description. Existing methods are dominated by training models with parallel image-text pairs, which are very costly to collect. In this paper, we make the first attempt to explore TBPS without parallel image-text data.
  arXiv  Detail & Related papers  (2023-05-22T12:13:08Z)
• Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening [53.1711708318581]
  Current image-text retrieval methods suffer from $N$-related time complexity. This paper presents a simple and effective keyword-guided pre-screening framework for the image-text retrieval.
  arXiv  Detail & Related papers  (2023-03-14T09:36:42Z)
• LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval [55.097573036580066]
  Experimental results show that LaPraDoR achieves state-of-the-art performance compared with supervised dense retrieval models. Compared to re-ranking, our lexicon-enhanced approach can be run in milliseconds (22.5x faster) while achieving superior performance.
  arXiv  Detail & Related papers  (2022-03-11T18:53:12Z)
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification [101.1886788396803]
  Person re-identification (re-ID) has gained more and more attention due to its widespread applications in video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models. In this paper, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them.
  arXiv  Detail & Related papers  (2021-09-12T15:51:41Z)
• Part2Whole: Iteratively Enrich Detail for Cross-Modal Retrieval with Partial Query [25.398090300086302]
  We propose an interactive retrieval framework called Part2Whole to tackle this problem. An Interactive Retrieval Agent is trained to build an optimal policy to refine the initial query. We present a weakly-supervised reinforcement learning method that needs no human-annotated data other than the text-image dataset.
  arXiv  Detail & Related papers  (2021-03-02T11:27:05Z)
• TAP: Text-Aware Pre-training for Text-VQA and Text-Caption [75.44716665758415]
  We propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. TAP explicitly incorporates scene text (generated from OCR engines) in pre-training. Our approach outperforms the state of the art by large margins on multiple tasks.
  arXiv  Detail & Related papers  (2020-12-08T18:55:21Z)

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.