SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

• URL: http://arxiv.org/abs/2503.08625v1
• Date: Tue, 11 Mar 2025 17:08:54 GMT
• Title: SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
• Authors: Muzhi Zhu, Yuzhuo Tian, Hao Chen, Chunluan Zhou, Qingpei Guo, Yang Liu, Ming Yang, Chunhua Shen,
• Abstract summary: 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.
• Score: 52.57696897619189
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While MLLMs have demonstrated adequate image understanding capabilities, they still struggle with pixel-level comprehension, limiting their practical applications. Current evaluation tasks like VQA and visual grounding remain too coarse to assess fine-grained pixel comprehension accurately. Though segmentation is foundational for pixel-level understanding, existing methods often require MLLMs to generate implicit tokens, decoded through external pixel decoders. This approach disrupts the MLLM's text output space, potentially compromising language capabilities and reducing flexibility and extensibility, while failing to reflect the model's intrinsic pixel-level understanding. Thus, we introduce the Human-Like Mask Annotation Task (HLMAT), a new paradigm where MLLMs mimic human annotators using interactive segmentation tools. Modeling segmentation as a multi-step Markov Decision Process, HLMAT enables MLLMs to iteratively generate text-based click points, achieving high-quality masks without architectural changes or implicit tokens. Through this setup, we develop SegAgent, a model fine-tuned on human-like annotation trajectories, which achieves performance comparable to state-of-the-art (SOTA) methods and supports additional tasks like mask refinement and annotation filtering. HLMAT provides a protocol for assessing fine-grained pixel understanding in MLLMs and introduces a vision-centric, multi-step decision-making task that facilitates exploration of MLLMs' visual reasoning abilities. Our adaptations of policy improvement method StaR and PRM-guided tree search further enhance model robustness in complex segmentation tasks, laying a foundation for future advancements in fine-grained visual perception and multi-step decision-making for MLLMs.

Related papers

• GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing [22.729750410621826]
  GeoPix is a RS MLLM that extends image understanding capabilities to the pixel level.<n>To facilitate the segmentation of multi-scale objects in RS imagery, a class-wise learnable memory module is integrated into the mask predictor.<n>To address the absence of large-scale datasets for training pixel-level RS MLLMs, we construct the GeoPixInstruct dataset.
  arXiv  Detail & Related papers  (2025-01-12T14:45:27Z)
• Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy [37.471419716572086]
  There is a significant gap in instruction-following capabilities between Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) We propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap.
  arXiv  Detail & Related papers  (2024-11-23T05:03:32Z)
• 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)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language.<n>This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok)<n>SeTok groups visual features into semantic units via a dynamic clustering algorithm.<n>The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.
  arXiv  Detail & Related papers  (2024-06-07T17:55:43Z)
• 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)
• 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)
• PixelLM: Pixel Reasoning with Large Multimodal Model [110.500792765109]
  PixelLM is an effective and efficient LMM for pixel-level reasoning and understanding. It produces masks from the hidden embeddings of the codebook tokens, which encode detailed target-relevant information. PixelLM excels across various pixel-level image reasoning and understanding tasks, outperforming well-established methods in multiple benchmarks.
  arXiv  Detail & Related papers  (2023-12-04T03:05:59Z)
• Perceptual MAE for Image Manipulation Localization: A High-level Vision Learner Focusing on Low-level Features [33.37376410890546]
  We propose a method to enhance the Masked Autoencoder (MAE) by incorporating high-resolution inputs and a perceptual loss supervision module. Based on such an interpretation, we propose a method to enhance the Masked Autoencoder (MAE) by incorporating high-resolution inputs and a perceptual loss supervision module.
  arXiv  Detail & Related papers  (2023-10-10T11:14:29Z)

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.