Nanning Zheng, Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Hongbin Sun, Jian Sun
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.
The Feature Pyramid Network (FPN) presents a remarkable approach to alleviate the scale variance in object representation by performing instance-level assignments. Nevertheless, this strategy ignores the distinct characteristics of different sub-regions in an instance. To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation. Moreover, we design a spatial gate with the new activation function to reduce computational complexity dramatically through spatially sparse convolutions. Extensive experiments demonstrate the effectiveness and efficiency of the proposed method on several state-of-the-art detection benchmarks. Code is available at https://github.com/StevenGrove/DynamicHead.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.03519")
get_code_for_paper("2012.03519")
have("2012.03519")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.03519.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.03519)
Connect an agent — have() is free.