PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding

• URL: http://arxiv.org/abs/2505.20759v2
• Date: Sun, 15 Jun 2025 23:23:25 GMT
• Title: PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding
• Authors: Ansel Blume, Jeonghwan Kim, Hyeonjeong Ha, Elen Chatikyan, Xiaomeng Jin, Khanh Duy Nguyen, Nanyun Peng, Kai-Wei Chang, Derek Hoiem, Heng Ji,
• Abstract summary: We introduce PARTONOMY, an LMM benchmark designed for pixel-level part grounding.<n>We train several part-centric LMMs and propose PLUM, a novel segmenting LMM that uses span tagging instead of segmentation tokens.<n>Our work opens up new avenues towards enabling fine-grained grounded visual understanding in LMMs.
• Score: 114.47739645594204
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Real-world objects are composed of distinctive, object-specific parts. Identifying these parts is key to performing fine-grained, compositional reasoning-yet, large multimodal models (LMMs) struggle to perform this seemingly straightforward task. In this work, we introduce PARTONOMY, an LMM benchmark designed for pixel-level part grounding. We construct PARTONOMY from existing part datasets and our own rigorously annotated set of images, encompassing 862 part labels and 534 object labels for evaluation. Unlike existing datasets that simply ask models to identify generic parts, PARTONOMY uses specialized concepts (e.g., agricultural airplane), and challenges models to compare objects' parts, consider part-whole relationships, and justify textual predictions with visual segmentations. Our experiments demonstrate significant limitations in state-of-the-art LMMs (e.g., LISA-13B achieves only 5.9% gIoU), highlighting a critical gap in their part grounding abilities. We note that existing segmentation-enabled LMMs (segmenting LMMs) have two key architectural shortcomings: they use special [SEG] tokens not seen during pretraining which induce distribution shift, and they discard predicted segmentations instead of using past predictions to guide future ones. To address these deficiencies, we train several part-centric LMMs and propose PLUM, a novel segmenting LMM that uses span tagging instead of segmentation tokens and that conditions on prior predictions in a feedback loop. We find that pretrained PLUM outperforms existing segmenting LMMs on reasoning segmentation, VQA, and visual hallucination benchmarks. In addition, PLUM finetuned on our proposed Explanatory Part Segmentation task is competitive with segmenting LMMs trained on significantly more segmentation data. Our work opens up new avenues towards enabling fine-grained, grounded visual understanding in LMMs.

Related papers

• LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance [56.474856189865946]
  Large multi-modal models (LMMs) struggle with inaccurate segmentation and hallucinated comprehension.<n>We propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation.<n>LIRA achieves state-of-the-art performance in both segmentation and comprehension tasks.
  arXiv  Detail & Related papers  (2025-07-08T07:46:26Z)
• 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)
• ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model [75.750699619993]
  We propose ROSE, a Revolutionary Open-set dense SEgmentation LMM, which enables dense mask prediction and open-category generation.<n>Our method treats each image patch as an independent region of interest candidate, enabling the model to predict both dense and sparse masks simultaneously.
  arXiv  Detail & Related papers  (2024-11-29T07:00:18Z)
• Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model [19.861556031795725]
  We introduce a Multi-Granularity Large Multimodal Model (MGLMM) MGLMM is capable of seamlessly adjusting the granularity of Captioning (SegCap) following user instructions. It excels at tackling more than eight downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-20T11:13:31Z)
• F-LMM: Grounding Frozen Large Multimodal Models [53.8059045627934]
  We present F-LMM -- grounding frozen off-the-shelf LMMs in human-AI conversations.<n>It is based on the fact that word-pixel correspondences conducive to visual grounding inherently exist in the attention mechanism of well-trained LMMs.<n>It achieves competitive performance on referring expression segmentation and panoptic narrative grounding benchmarks.
  arXiv  Detail & Related papers  (2024-06-09T15:14:26Z)
• PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model [49.80313655590392]
  PSALM is a powerful extension of the Large Multi-modal Model (LMM) to address the segmentation task challenges. It incorporates a mask decoder and a well-designed input schema to handle a variety of segmentation tasks. The flexible design of PSALM supports joint training across multiple datasets and tasks, leading to improved performance and task generalization.
  arXiv  Detail & Related papers  (2024-03-21T17:50:47Z)
• Compositional Chain-of-Thought Prompting for Large Multimodal Models [46.721769077885966]
  Compositional Chain-of-Thought (CCoT) is a novel zero-shot Chain-of-Thought prompting method. We first generate an SG using the Large Language Model (LLM) and then use that SG in the prompt to produce a response. We find that the proposed CCoT approach not only improves LMM performance but also improves the performance of several popular LMMs on general multimodal benchmarks.
  arXiv  Detail & Related papers  (2023-11-27T22:23:27Z)

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.