SORCE: Small Object Retrieval in Complex Environments

• URL: http://arxiv.org/abs/2505.24441v1
• Date: Fri, 30 May 2025 10:23:05 GMT
• Title: SORCE: Small Object Retrieval in Complex Environments
• Authors: Chunxu Liu, Chi Xie, Xiaxu Chen, Wei Li, Feng Zhu, Rui Zhao, Limin Wang,
• Abstract summary: We introduce SORCE (Small Object Retrieval in Complex Environments), a new subfield of T2IR, focusing on retrieving small objects in complex images with textual queries.<n>Preliminary analysis on SORCE-1K finds that existing T2IR methods struggle to capture small objects and encode all the semantics into a single embedding.<n>We leverage Multimodal Large Language Models (MLLMs) to extract multiple embeddings for each image instructed by a set of Regional Prompts (ReP)
• Score: 19.406708973678608
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-Image Retrieval (T2IR) is a highly valuable task that aims to match a given textual query to images in a gallery. Existing benchmarks primarily focus on textual queries describing overall image semantics or foreground salient objects, possibly overlooking inconspicuous small objects, especially in complex environments. Such small object retrieval is crucial, as in real-world applications, the targets of interest are not always prominent in the image. Thus, we introduce SORCE (Small Object Retrieval in Complex Environments), a new subfield of T2IR, focusing on retrieving small objects in complex images with textual queries. We propose a new benchmark, SORCE-1K, consisting of images with complex environments and textual queries describing less conspicuous small objects with minimal contextual cues from other salient objects. Preliminary analysis on SORCE-1K finds that existing T2IR methods struggle to capture small objects and encode all the semantics into a single embedding, leading to poor retrieval performance on SORCE-1K. Therefore, we propose to represent each image with multiple distinctive embeddings. We leverage Multimodal Large Language Models (MLLMs) to extract multiple embeddings for each image instructed by a set of Regional Prompts (ReP). Experimental results show that our multi-embedding approach through MLLM and ReP significantly outperforms existing T2IR methods on SORCE-1K. Our experiments validate the effectiveness of SORCE-1K for benchmarking SORCE performances, highlighting the potential of multi-embedding representation and text-customized MLLM features for addressing this task.

Related papers

• Composed Object Retrieval: Object-level Retrieval via Composed Expressions [71.47650333199628]
  Composed Object Retrieval (COR) is a brand-new task that goes beyond image-level retrieval to achieve object-level precision.<n>We construct COR127K, the first large-scale COR benchmark that contains 127,166 retrieval triplets with various semantic transformations in 408 categories.<n>We also present CORE, a unified end-to-end model that integrates reference region encoding, adaptive visual-textual interaction, and region-level contrastive learning.
  arXiv  Detail & Related papers  (2025-08-06T13:11:40Z)
• Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval [13.296362770269452]
  Mask-aware TIR (MaTIR) aims to find relevant images based on a textual query.<n>We propose a two-stage framework, comprising a first stage for segmentation-aware image retrieval and a second stage for reranking and object grounding.<n>We evaluate our approach on COCO and D$3$ datasets, demonstrating significant improvements in both retrieval accuracy and segmentation quality over previous methods.
  arXiv  Detail & Related papers  (2025-06-28T12:19:49Z)
• Referring Expression Instance Retrieval and A Strong End-to-End Baseline [37.47466772169063]
  Text-Image Retrieval retrieves a target image from a gallery based on an image-level description.<n>Referring Expression localizes a target object within a given image using an instance-level description.<n>We introduce a new task called textbfReferring Expression Instance Retrieval (REIR), which supports both instance-level retrieval and localization.
  arXiv  Detail & Related papers  (2025-06-23T02:28:44Z)
• Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization [5.2337753974570616]
  We address the challenge of Small Object Image Retrieval (SoIR), where the goal is to retrieve images containing a specific small object, in a cluttered scene.<n>Key challenge is constructing a single image descriptor, for scalable and efficient search, that effectively represents all objects in the image.<n>We introduce Multi-object Attention Optimization (MaO), a novel retrieval framework which incorporates a dedicated multi-object pre-training phase.
  arXiv  Detail & Related papers  (2025-03-10T08:27:02Z)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models [2.331828779757202]
  We present CALICO, the first Large Vision-Language Models (LVLM) designed for multi-image part-level reasoning segmentation.<n> CALICO features two key components, a novel Correspondence Extraction Module that identifies semantic part-level correspondences, and Adaptation Correspondence Modules that embed this information into the LVLM.<n>We show that CALICO, with just 0.3% of its parameters finetuned, achieves strong performance on this challenging task.
  arXiv  Detail & Related papers  (2024-12-26T18:59:37Z)
• MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs [61.56904387052982]
  This paper proposes a new visual grounding task called multi-context visual grounding. It aims to localize instances of interest across multiple images based on open-ended text prompts. We benchmark over 20 state-of-the-art MLLMs and foundation models with potential multi-context visual grounding capabilities.
  arXiv  Detail & Related papers  (2024-10-16T07:52:57Z)
• Object-Centric Open-Vocabulary Image-Retrieval with Aggregated Features [11.112981323262337]
  We present a simple yet effective approach to object-centric open-vocabulary image retrieval.<n>Our approach aggregates dense embeddings extracted from CLIP into a compact representation.<n>We show the effectiveness of our scheme to the task by achieving significantly better results than global feature approaches on three datasets.
  arXiv  Detail & Related papers  (2023-09-26T15:13:09Z)
• Beyond One-to-One: Rethinking the Referring Image Segmentation [117.53010476628029]
  Referring image segmentation aims to segment the target object referred by a natural language expression. We propose a Dual Multi-Modal Interaction (DMMI) Network, which contains two decoder branches. In the text-to-image decoder, text embedding is utilized to query the visual feature and localize the corresponding target. Meanwhile, the image-to-text decoder is implemented to reconstruct the erased entity-phrase conditioned on the visual feature.
  arXiv  Detail & Related papers  (2023-08-26T11:39:22Z)
• Referring Image Matting [85.77905619102802]
  We introduce a new task named Referring Image Matting (RIM) in this paper. RIM aims to extract the meticulous alpha matte of the specific object that best matches the given natural language description. RefMatte consists of 230 object categories, 47,500 images, 118,749 expression-region entities, and 474,996 expressions.
  arXiv  Detail & Related papers  (2022-06-10T14:44:43Z)
• ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity [16.550790981646276]
  Current approaches combine the features of each of the two elements of the query into a single representation. Our work aims at shedding new light on the task by looking at it through the prism of two familiar and related frameworks: text-to-image and image-to-image retrieval.
  arXiv  Detail & Related papers  (2022-03-15T17:29:20Z)
• Tasks Integrated Networks: Joint Detection and Retrieval for Image Search [99.49021025124405]
  In many real-world searching scenarios (e.g., video surveillance), the objects are seldom accurately detected or annotated. We first introduce an end-to-end Integrated Net (I-Net), which has three merits. We further propose an improved I-Net, called DC-I-Net, which makes two new contributions.
  arXiv  Detail & Related papers  (2020-09-03T03:57:50Z)
• Compact Deep Aggregation for Set Retrieval [87.52470995031997]
  We focus on retrieving images containing multiple faces from a large scale dataset of images. Here the set consists of the face descriptors in each image, and given a query for multiple identities, the goal is then to retrieve, in order, images which contain all the identities. We show that this compact descriptor has minimal loss of discriminability up to two faces per image, and degrades slowly after that.
  arXiv  Detail & Related papers  (2020-03-26T08:43:15Z)

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.