Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GROUNDHOG: Grounding Large Language Models to Holistic Segmentation

About

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.

Yichi Zhang, Ziqiao Ma, Xiaofeng Gao, Suhaila Shakiah, Qiaozi Gao, Joyce Chai• 2024

Related benchmarks

TaskDatasetResultRank
Referring Expression SegmentationRefCOCO (testA)
cIoU79.9
257
Referring Expression SegmentationRefCOCO+ (testA)
cIoU75
230
Referring Expression SegmentationRefCOCO+ (val)
cIoU70.5
223
Referring Expression SegmentationRefCOCO (testB)
cIoU75.7
213
Referring Expression SegmentationRefCOCO (val)
cIoU78.5
212
Referring Expression SegmentationRefCOCO+ (testB)
cIoU64.9
210
Reasoning SegmentationReasonSeg (val)
gIoU56.2
193
Referring Expression SegmentationRefCOCOg (val)
cIoU74.1
129
Referring Expression SegmentationRefCOCOg (test)
cIoU74.6
118
Referring Expression SegmentationRefCOCOg (val (U))--
89
Showing 10 of 12 rows

Other info

Follow for update