Trevor Darrell, Xudong Wang, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Kazuki Kozuka
We lifted 4 functions out of this paper's own repositories and ran 2 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.
| Repository | Role | Ran |
|---|---|---|
| berkeley-hipie/hipie | canonical | 2 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| get_images_color_similarity | Ran | berkeley-hipie/hipie/projects/HIPIE/hipie/hipie_img.py code served (permissive licence) · get_code("3a4a70eddd103b6f") |
| unfold_wo_center | Ran | berkeley-hipie/hipie/projects/HIPIE/hipie/hipie_img.py code served (permissive licence) · get_code("6bc62d34967e2917") |
| convert_grounding_to_od_logits | Not yet run | berkeley-hipie/hipie/projects/HIPIE/hipie/hipie_img.py code served (permissive licence) · get_code("133372f6b12b6ba0") |
| vote | Not yet run | berkeley-hipie/hipie/projects/HIPIE/hipie/demo_lib/demo_utils.py code served (permissive licence) · get_code("0d78867cbc2d1619") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple levels of granularity, introducing inherent segmentation ambiguity. Unlike existing methods that typically sidestep this ambiguity and treat it as an external factor, our approach actively incorporates a hierarchical representation encompassing different semantic-levels into the learning process. We also propose a decoupled text-image fusion mechanism and representation learning modules for both "things" and "stuff". 1 Additionally, we systematically examine the differences that exist in the textual and visual features between these types of categories. Our resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework. Benchmarked on over 40 datasets, e.g., ADE20K, COCO, Pascal-VOC Part, RefCOCO/RefCOCOg, ODinW and SeginW, HIPIE achieves the state-of-the-art results at various levels of image comprehension, including semantic-level (e.g., semantic segmentation), instance-level (e.g., panoptic/referring segmentation and object detection), as well as part-level (e.g., part/subpart segmentation) tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2307.00764")
get_code_for_paper("2307.00764")
have("2307.00764")
Connect an agent — have() is free.