Papers
Topics
Authors
Recent
Search
2000 character limit reached

SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models

Published 20 Mar 2024 in cs.CV | (2403.13263v1)

Abstract: Recent trends in Large Vision LLMs (LVLMs) research have been increasingly focusing on advancing beyond general image understanding towards more nuanced, object-level referential comprehension. In this paper, we present and delve into the self-consistency capability of LVLMs, a crucial aspect that reflects the models' ability to both generate informative captions for specific objects and subsequently utilize these captions to accurately re-identify the objects in a closed-loop process. This capability significantly mirrors the precision and reliability of fine-grained visual-language understanding. Our findings reveal that the self-consistency level of existing LVLMs falls short of expectations, posing limitations on their practical applicability and potential. To address this gap, we introduce a novel fine-tuning paradigm named Self-Consistency Tuning (SC-Tune). It features the synergistic learning of a cyclic describer-locator system. This paradigm is not only data-efficient but also exhibits generalizability across multiple LVLMs. Through extensive experiments, we demonstrate that SC-Tune significantly elevates performance across a spectrum of object-level vision-language benchmarks and maintains competitive or improved performance on image-level vision-language benchmarks. Both our model and code will be publicly available at https://github.com/ivattyue/SC-Tune.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Nocaps: Novel object captioning at scale. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8948–8957, 2019.
  2. Qwen technical report. arXiv preprint arXiv:2309.16609, 2023a.
  3. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966, 2023b.
  4. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862, 2022.
  5. Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, pages 65–72, 2005.
  6. Disclip: Open-vocabulary referring expression generation. arXiv preprint arXiv:2305.19108, 2023.
  7. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  8. Position-enhanced visual instruction tuning for multimodal large language models. arXiv preprint arXiv:2308.13437, 2023a.
  9. Minigpt-v2: Large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478, 2023b.
  10. Shikra: Unleashing multimodal llm’s referential dialogue magic. arXiv preprint arXiv:2306.15195, 2023c.
  11. Pix2seq: A language modeling framework for object detection. arXiv preprint arXiv:2109.10852, 2021.
  12. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https://vicuna. lmsys. org (accessed 14 April 2023), 2023.
  13. Instructblip: Towards general-purpose vision-language models with instruction tuning, 2023.
  14. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  15. Eva: Exploring the limits of masked visual representation learning at scale. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19358–19369, 2023.
  16. Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6904–6913, 2017.
  17. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
  18. Gqa: A new dataset for real-world visual reasoning and compositional question answering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6700–6709, 2019.
  19. Openclip, 2021. If you use this software, please cite it as below.
  20. Referitgame: Referring to objects in photographs of natural scenes. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 787–798, 2014.
  21. Openimages: A public dataset for large-scale multi-label and multi-class image classification. Dataset available from https://github.com/openimages, 2017.
  22. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision, 123:32–73, 2017.
  23. Rlaif: Scaling reinforcement learning from human feedback with ai feedback. arXiv preprint arXiv:2309.00267, 2023a.
  24. Aligning text-to-image models using human feedback. arXiv preprint arXiv:2302.12192, 2023b.
  25. Visual instruction tuning, 2023a.
  26. Second thoughts are best: Learning to re-align with human values from text edits. Advances in Neural Information Processing Systems, 35:181–196, 2022.
  27. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499, 2023b.
  28. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
  29. Unified-io: A unified model for vision, language, and multi-modal tasks. arXiv preprint arXiv:2206.08916, 2022.
  30. Point and ask: Incorporating pointing into visual question answering. arXiv preprint arXiv:2011.13681, 2020.
  31. Human-level control through deep reinforcement learning. nature, 518(7540):529–533, 2015.
  32. Modeling context between objects for referring expression understanding. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 792–807. Springer, 2016.
  33. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332, 2021.
  34. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744, 2022a.
  35. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744, 2022b.
  36. Kosmos-2: Grounding multimodal large language models to the world. ArXiv, abs/2306, 2023.
  37. Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In Proceedings of the IEEE international conference on computer vision, pages 2641–2649, 2015.
  38. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1):5485–5551, 2020.
  39. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017.
  40. Objects365: A large-scale, high-quality dataset for object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8430–8439, 2019.
  41. Learning to summarize with human feedback. Advances in Neural Information Processing Systems, 33:3008–3021, 2020.
  42. A proposal-free one-stage framework for referring expression comprehension and generation via dense cross-attention. IEEE Transactions on Multimedia, 25:2446–2458, 2023.
  43. Reinforcement learning: An introduction. MIT press, 2018.
  44. Generating easy-to-understand referring expressions for target identifications. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5794–5803, 2019.
  45. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023a.
  46. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023b.
  47. Cider: Consensus-based image description evaluation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4566–4575, 2015.
  48. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In International Conference on Machine Learning, pages 23318–23340. PMLR, 2022.
  49. One-peace: Exploring one general representation model toward unlimited modalities. arXiv preprint arXiv:2305.11172, 2023a.
  50. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. arXiv preprint arXiv:2305.11175, 2023b.
  51. Clip-vg: Self-paced curriculum adapting of clip for visual grounding. IEEE Transactions on Multimedia, 2023.
  52. Imagereward: Learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977, 2023.
  53. Universal instance perception as object discovery and retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 15325–15336, 2023.
  54. Improving visual grounding with visual-linguistic verification and iterative reasoning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9499–9508, 2022.
  55. Modeling context in referring expressions. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, pages 69–85. Springer, 2016.
  56. A joint speaker-listener-reinforcer model for referring expressions. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3521–3529, 2017.
  57. Gpt4roi: Instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601, 2023.
  58. Seqtr: A simple yet universal network for visual grounding. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXV, pages 598–615. Springer, 2022.
  59. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592, 2023.
  60. Visual7w: Grounded question answering in images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4995–5004, 2016.
Citations (6)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free