A multimodal LLM with a SAM-based mask decoder localizes diffusion-edited regions better than traditional forensic methods on MagicBrush, CocoGLIDE, and a new BrushNet dataset.
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Most multimodal large language models (MLLMs) learn language-to-object grounding through causal language modeling where grounded objects are captured by bounding boxes as sequences of location tokens. This paradigm lacks pixel-level representations that are important for fine-grained visual understanding and diagnosis. In this work, 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, which then connects groundable phrases to unified grounding masks by retrieving and merging the entity masks. To train GROUNDHOG, we carefully curated M3G2, a grounded visual instruction tuning dataset with Multi-Modal Multi-Grained Grounding, by harvesting a collection of segmentation-grounded datasets with rich annotations. Our experimental results show that GROUNDHOG achieves superior performance on various language grounding tasks without task-specific fine-tuning, and significantly reduces object hallucination. GROUNDHOG also demonstrates better grounding towards complex forms of visual input and provides easy-to-understand diagnosis in failure cases.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM
A multimodal LLM with a SAM-based mask decoder localizes diffusion-edited regions better than traditional forensic methods on MagicBrush, CocoGLIDE, and a new BrushNet dataset.