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.
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1802.05766")
get_code_for_paper("1802.05766")
have("1802.05766")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1802.05766.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1802.05766)
Connect an agent — have() is free.