Research map / Vision-language and multimodal / Multimodal LLMs
MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes
Jin Zhang, Ruiheng Zhang, Zhe Cao, Kaizheng Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces MMCSBench, a fine-grained benchmark for evaluating large vision-language models on camouflaged scene understanding, motivated by the limited generalization of discriminative camouflaged object detection methods.
Problem
Camouflaged object detection methods follow discriminative segmentation paradigms, rely on predefined training categories, and struggle to generalize to unseen camouflaged objects; collecting camouflage imagery is also labor-intensive.
Approach
A benchmark for assessing LVLMs on camouflage scenes at fine granularity, as an alternative to discriminative segmentation that depends on predefined categories. Details beyond the abstract are not available.
Experimental setup
Benchmarks: MMCSBench
Closest papers by meaning
- MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios (AAAI 2025 · similarity 0.93)
- Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and Visual Analysis Strategy (ECCV 2024 · similarity 0.90)
- Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes (ICCV 2025 · similarity 0.90)
- Training-Free Open-Vocabulary Camouflaged Object Segmentation via Fine-Grained Object Binding and Adaptive Hybrid Prompt (CVPR 2026 · similarity 0.89)
- Shift the Lens: Environment-Aware Unsupervised Camouflaged Object Detection (CVPR 2025 · similarity 0.89)
- Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation (ICLR 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
