SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.07704 · 2023

Ferret: Refer and Ground Anything Anywhere at Any Granularity

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
apple/ml-ferret canonical 3 of 3
copy not recorded — 4 of 5
FunctionStatusWhere it lives
are_phrases_similar Ran this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only · get_code("d515c6ab54f0598c")
decode_bbox_from_caption Ran this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only · get_code("3b23c33aca6cdead")
generate_mask_for_feature Ran this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only · get_code("974d957b09ee69d2")
point_sample Ran apple/ml-ferret/ferret/model/ferret_arch.py
pointer only (licence: NOASSERTION) · get_code("55e4e4a151814912")
rand_sample Ran apple/ml-ferret/ferret/model/ferret_arch.py
pointer only (licence: NOASSERTION) · get_code("490cd3fba7ed0f15")
rand_sample_repeat Ran apple/ml-ferret/ferret/model/ferret_arch.py
pointer only (licence: NOASSERTION) · get_code("7f94db7c29cc4f44")
resize_bbox Ran this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only · get_code("5a8ea802e3fdbf73")
draw_box Not yet run this paper's copy was not recorded; identical code first harvested from apple/ml-ferret
pointer only · get_code("a449641f4bef63f1")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions. To unify referring and grounding in the LLM paradigm, Ferret employs a novel and powerful hybrid region representation that integrates discrete coordinates and continuous features jointly to represent a region in the image. To extract the continuous features of versatile regions, we propose a spatial-aware visual sampler, adept at handling varying sparsity across different shapes. Consequently, Ferret can accept diverse region inputs, such as points, bounding boxes, and free-form shapes. To bolster the desired capability of Ferret, we curate GRIT, a comprehensive refer-and-ground instruction tuning dataset including 1.1M samples that contain rich hierarchical spatial knowledge, with 95K hard negative data to promote model robustness. The resulting model not only achieves superior performance in classical referring and grounding tasks, but also greatly outperforms existing MLLMs in region-based and localization-demanded multimodal chatting. Our evaluations also reveal a significantly improved capability of describing image details and a remarkable alleviation in object hallucination. Code and data will be available at https://github.com/apple/ml-ferret

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.07704")
get_code_for_paper("2310.07704")
have("2310.07704")

Connect an agent — have() is free.