Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues

• URL: http://arxiv.org/abs/2604.24036v2
• Date: Wed, 29 Apr 2026 06:30:21 GMT
• Title: Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues
• Abstract summary: Crowded scenes entail visual challenges, which impair object semantics and degrade grounding performance.<n>We propose a novel method that overcomes such constraints by leveraging Language-Guided Semantic Cues (LGSCs)
• Score: 58.21371989991432
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Multimodal Large Language Models (MLLMs) have enhanced grounding capabilities in general scenes, their robustness in crowded scenes remains underexplored. Crowded scenes entail visual challenges (i.e., occlusion and small objects), which impair object semantics and degrade grounding performance. In contrast, language expressions are immune to such degradation and preserve object semantics. In light of these observations, we propose a novel method that overcomes such constraints by leveraging Language-Guided Semantic Cues (LGSCs). Specifically, our approach introduces a Semantic Cue Extractor (SCE) to derive semantic cues of objects from the visual pipeline of an MLLM. We then guide these cues using corresponding text embeddings to produce LGSCs as linguistic semantic priors. Subsequently, they are reintegrated into the original visual pipeline to refine object semantics. Extensive experiments and analyses demonstrate that incorporating LGSCs into an MLLM effectively improves grounding accuracy in crowded scenes.

Related papers

• Semantic Manipulation Localization [18.942761820082705]
  We introduce semantic manipulation, a new task that focuses on localizing subtle semantic edits that significantly change image interpretation.<n>Based on this task, we propose TRACE, an end-to-end framework that models semantic sensitivity through three components: semantic anchoring, perturbation sensing, and semantic-constrained reasoning.<n>Extensive experiments show that TRACE consistently outperforms existing IML methods on our benchmark and produces more complete, compact, and semantically coherent localization results.
  arXiv  Detail & Related papers  (2026-04-11T09:53:09Z)
• FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning [62.11389260206383]
  textscFineRS is a two-stage MLLM-based reinforcement learning framework for segmenting extremely small objects.<n>We present textscFineRS-4k, a new dataset for evaluating MLLMs on attribute-level reasoning and pixel-level segmentation on subtle, small-scale targets.
  arXiv  Detail & Related papers  (2025-10-24T10:14:17Z)
• AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding [79.43306110124875]
  AlignVLM is a vision-text alignment method that maps visual features to a weighted average of text embeddings.<n>Our experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods.
  arXiv  Detail & Related papers  (2025-02-03T13:34:51Z)
• EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models [80.00303150568696]
  We propose a novel Multimodal Large Language Models (MLLM) that empowers comprehension of arbitrary referring visual prompts with less training efforts than existing approaches. Our approach embeds referring visual prompts as spatial concepts conveying specific spatial areas comprehensible to the MLLM. We also propose a Geometry-Agnostic Learning paradigm (GAL) to further disentangle the MLLM's region-level comprehension with the specific formats of referring visual prompts.
  arXiv  Detail & Related papers  (2024-09-25T08:22:00Z)
• OLIVE: Object Level In-Context Visual Embeddings [8.168219870640318]
  We propose a novel method to prompt large language models with in-context visual object vectors. This eliminates the necessity of fusing a lengthy array of image patch features and significantly speeds up training. Our experiments reveal that our method achieves competitive referring object classification and captioning performance.
  arXiv  Detail & Related papers  (2024-06-02T21:36:31Z)
• Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation [114.72734384299476]
  We propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. We leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Our approach significantly boosts the capacity of segmentation models for unseen classes.
  arXiv  Detail & Related papers  (2024-03-13T11:23:55Z)
• Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception [63.03288425612792]
  We propose bfAnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references. Our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.
  arXiv  Detail & Related papers  (2024-03-05T13:45:46Z)
• GROUNDHOG: Grounding Large Language Models to Holistic Segmentation [22.347590874621865]
  We introduce GROUNDHOG, an MLLM developed by grounding Large Language Models to holistic segmentation. GROUNDHOG incorporates a masked feature extractor and converts extracted features into visual entity tokens for the MLLM backbone. Our experimental results show that GROUNDHOG achieves superior performance on various language grounding tasks without task-specific fine-tuning.
  arXiv  Detail & Related papers  (2024-02-26T18:59:33Z)
• Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning [32.178931149612644]
  In-context learning enables language models to adapt to downstream data or incorporate tasks by few samples as demonstrations within the prompts. However, the performance of in-context learning can be unstable depending on the quality, format, or order of demonstrations. We propose a novel approach "vocabulary-defined semantics"
  arXiv  Detail & Related papers  (2024-01-29T14:29:48Z)

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.