mlsanityData to 7 Oct 2026

Referring Expression Comprehension for Small Objects

arXiv 2510.03701 ↗First posted 4 Oct 2025cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Referring expression comprehension (REC) aims to localize the target object described by a natural language expression. Recent advances in vision-language learning have led to significant performance improvements in REC tasks. However, localizing extremely small objects remains a considerable challenge despite its importance in real-world applications such as autonomous driving. To address this issue, we introduce a novel dataset and method for REC targeting small objects. First, we present the small object REC (SOREC) dataset, which consists of 100,000 pairs of referring expressions and corresponding bounding boxes for small objects in driving scenarios. Second, we propose the progressive-iterative zooming adapter (PIZA), an adapter module for parameter-efficient fine-tuning that enables models to progressively zoom in and localize small objects. In a series of experiments, we apply PIZA to GroundingDINO and demonstrate a significant improvement in accuracy on the SOREC dataset. Our dataset, codes and pre-trained models are publicly available on the project page.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 79 of its 95 references that are in the map. First posted on arXiv 4 Oct 2025.

Builds on

79 of 95 references.

References · 79

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2017Mask R-CNNcited by 7,259
  10. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  11. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  12. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
38 more
  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2015Fast R-CNNcited by 2,930
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  5. 2022Visual Prompt Tuningcited by 1,674
  6. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  7. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,352
  8. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  9. 2021Grounded Language-Image Pre-trainingcited by 1,147
  10. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  11. 2016Modeling Context in Referring Expressionscited by 1,054
  12. 2019How Can We Know What Language Models Know?cited by 953
  13. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 897
  14. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  15. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 742
  16. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 714
  17. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  18. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  19. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  20. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  21. 2018MAttNet: Modular Attention Network for Referring Expression Comprehensioncited by 427
  22. 2022Prompt-aligned Gradient for Prompt Tuningcited by 339
  23. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 330
  24. 2023Visual-Language Prompt Tuning with Knowledge-guided Context Optimizationcited by 307
  25. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  26. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  27. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  28. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  29. 2020Detection and Tracking Meet Drones Challengecited by 261
  30. 2016Modeling Context Between Objects for Referring Expression Understandingcited by 250
  31. 2022Prompt Distribution Learningcited by 235
  32. 2020Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentationcited by 204
  33. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  34. 2019A Fast and Accurate One-Stage Approach to Visual Groundingcited by 194
  35. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  36. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  37. 2023QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Modelscited by 154
  38. 2022FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformercited by 133

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025Towards Cross-View Point Correspondence in Vision-Language Modelscited by 12
  2. 2026Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checkercited by 0
  3. 2026FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMscited by 0
  4. 2026GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagerycited by 0
  5. 2026A-PAIR: A Benchmark and Identity-Consistent Grounding Framework for Air-Ground Cross-View Referring Person Detectioncited by 0
  6. 2026EviRover: Reinforcing Agentic Perception Beyond a Glancecited by 0