Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder

• URL: http://arxiv.org/abs/2508.04107v3
• Date: Tue, 19 Aug 2025 08:35:04 GMT
• Title: Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
• Authors: Jingchao Wang, Zhijian Wu, Dingjiang Huang, Yefeng Zheng, Hong Wang,
• Abstract summary: We propose a novel framework that exploits the inherent visual detail features encoded in the MLLM vision encoder without introducing an extra visual encoder.<n>Besides, we propose a detail-enhanced and semantic-consistent feature fusion module (DSFF) that fully integrates the detail-related visual feature with the semantic-related feature output by the large language model (LLM) of MLLM.<n>Our method generally surpasses both SAM-based and SAM-free competitors, striking a better balance between performance and cost.
• Score: 18.236863512276187
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reference Expression Segmentation (RES) aims to segment image regions specified by referring expressions and has become popular with the rise of multimodal large models (MLLMs). While MLLMs excel in semantic understanding, their token-generation paradigm struggles with pixel-level dense prediction. Existing RES methods either couple MLLMs with the parameter-heavy Segment Anything Model (SAM) with 632M network parameters or adopt SAM-free lightweight pipelines that sacrifice accuracy. To address the trade-off between performance and cost, we specifically propose MLLMSeg, a novel framework that fully exploits the inherent visual detail features encoded in the MLLM vision encoder without introducing an extra visual encoder. Besides, we propose a detail-enhanced and semantic-consistent feature fusion module (DSFF) that fully integrates the detail-related visual feature with the semantic-related feature output by the large language model (LLM) of MLLM. Finally, we establish a light-weight mask decoder with only 34M network parameters that optimally leverages detailed spatial features from the visual encoder and semantic features from the LLM to achieve precise mask prediction. Extensive experiments demonstrate that our method generally surpasses both SAM-based and SAM-free competitors, striking a better balance between performance and cost. Code is available at https://github.com/jcwang0602/MLLMSeg.

Related papers

• Segmentation as A Plug-and-Play Capability for Frozen Multimodal LLMs [9.6979217203587]
  We introduce LENS (Leveraging kEypoiNts for MLLMs'), a novel plug-and-play solution.<n>LENS attaches a lightweight, trainable head to a completely frozen MLLM.<n>It achieves segmentation performance competitive with or superior to that of retraining-based methods.
  arXiv  Detail & Related papers  (2025-10-19T10:21:01Z)
• MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval [50.062817677022586]
  Zero-Shot Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens.<n>We propose MLLM-Guided VLM Fine-Tuning with Joint Inference (MVFT-JI) to construct two complementary training tasks using only unlabeled images.
  arXiv  Detail & Related papers  (2025-05-26T08:56:59Z)
• Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM [21.967692616735196]
  multimodal large language models (MLLMs) have emerged as a key approach in achieving artificial general intelligence.<n>We propose an object-centric visual tokenizer based on Slot Attention specifically for MLLMs.<n>This work is the first demonstration of the feasibility of object-centric slot attention performed with MLLMs and in-the-wild natural images.
  arXiv  Detail & Related papers  (2025-05-23T10:43:45Z)
• SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories [52.57696897619189]
  We introduce the Human-Like Mask Modeling Task (HLMAT), a new paradigm where MLLMs mimic human annotators using interactive segmentation tools.<n>HLMAT enables MLLMs to iteratively generate text-based click points, achieving high-quality masks without architectural changes or implicit tokens.<n>HLMAT provides a protocol for assessing fine-grained pixel understanding in MLLMs and introduces a vision-centric, multi-step decision-making task.
  arXiv  Detail & Related papers  (2025-03-11T17:08:54Z)
• PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures [5.513631883813244]
  We propose a framework that textbfPre-textbfIntegratestextbfPrompt information into the visual encoding process using existingmodules of MLLMs. Our model maintains excellent generation even when half of the visual tokens are reduced.
  arXiv  Detail & Related papers  (2024-10-30T15:05:17Z)
• Dense Connector for MLLMs [89.50595155217108]
  We introduce the Dense Connector - a plug-and-play vision-language connector that significantly enhances existing MLLMs. Building on this, we also propose the Efficient Dense Connector, which achieves performance comparable to LLaVA-v1.5 with only 25% of the visual tokens. Our model, trained solely on images, showcases remarkable zero-shot capabilities in video understanding as well.
  arXiv  Detail & Related papers  (2024-05-22T16:25:03Z)
• MAS-SAM: Segment Any Marine Animal with Aggregated Features [55.91291540810978]
  We propose a novel feature learning framework named MAS-SAM for marine animal segmentation. Our method enables to extract richer marine information from global contextual cues to fine-grained local details.
  arXiv  Detail & Related papers  (2024-04-24T07:38:14Z)
• 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)
• From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models [36.41816380074965]
  We investigate the effectiveness of different vision encoders within Large Language Models (MLLMs) Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. We propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging.
  arXiv  Detail & Related papers  (2023-10-13T02:41:55Z)
• CLIP Is Also a Good Teacher: A New Learning Framework for Inductive Zero-shot Semantic Segmentation [6.181169909576527]
  Generalized Zero-shot Semantic aims to segment both seen and unseen categories only under the supervision of the seen ones. Existing methods adopt the large-scale Vision Language Models (VLMs) which obtain outstanding zero-shot performance. We propose CLIP-ZSS (Zero-shot Semantic), a training framework that enables any image encoder designed for closed-set segmentation applied in zero-shot and open-vocabulary tasks.
  arXiv  Detail & Related papers  (2023-10-03T09:33:47Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)

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.