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.
Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degradation in unusual scenes. Unfortunately, different datasets often use incompatible labels. For instance, the Cityscapes road class subsumes all driving surfaces, while Vistas defines separate classes for road markings, manholes etc. We address this challenge by proposing a principled method for seamless learning on datasets with overlapping classes based on partial labels and probabilistic loss. Our method achieves competitive within-dataset and cross-dataset generalization, as well as ability to learn visual concepts which are not separately labeled in any of the training datasets. Experiments reveal competitive or state-of-the-art performance on two multi-domain dataset collections and on the WildDash 2 benchmark.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.11224")
get_code_for_paper("2108.11224")
have("2108.11224")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.11224.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.11224)
Connect an agent — have() is free.