Vighnesh Birodkar, Zhichao Lu, Siyang Li, Vivek Rathod, Jonathan Google
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Instance segmentation models today are very accurate when trained on large annotated datasets, but collecting mask annotations at scale is prohibitively expensive. We address the partially supervised instance segmentation problem in which one can train on (significantly cheaper) bounding boxes for all categories but use masks only for a subset of categories. In this work, we focus on a popular family of models which apply differentiable cropping to a feature map and predict a mask based on the resulting crop. While many of these architectures perform similarly when trained in fully supervised mode, our main finding is that they can generalize to novel classes in dramatically different ways. We call this ability of mask-heads to generalize to unseen classes the strong mask generalization effect and show that without any specialty modules or losses, we can achieve state-of-the-art results in the partially supervised COCO instance segmentation benchmark. Finally, we demonstrate that our effect is general, holding across underlying detection methodologies (including anchor-based, anchor-free or no detector at all) and across different backbone networks. Code and pre-trained models are available at https://git.io/deepmac.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.00613")
get_code_for_paper("2104.00613")
have("2104.00613")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.00613.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.00613)
Connect an agent — have() is free.