Wei Wu, Bo Li, Yu Qiao, Yali Wang, Yiru Wang, Weihao Gan, Jiaxi Wu, Hanqing Li, Mengzhe He
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.
Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instancelevel annotations in the target domain. Existing approaches mainly focus on either of these two difficulties, even though they are closely coupled in cross domain object detection. To solve this problem, we propose a novel Target-perceived Dual-branch Distillation (TDD) framework. By integrating detection branches of both source and target domains in a unified teacher-student learning scheme, it can reduce domain shift and generate reliable supervision effectively. In particular, we first introduce a distinct Target Proposal Perceiver between two domains. It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative crossattention. Afterwards, we design a concise Dual Branch Self Distillation strategy for model training, which can progressively integrate complementary object knowledge from different domains via self-distillation in two branches. Finally, we conduct extensive experiments on a number of widely-used scenarios in cross domain object detection. The results show that our TDD significantly outperforms the state-of-the-art methods on all the benchmarks. The codes and models will be released afterwards.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.01291")
get_code_for_paper("2205.01291")
have("2205.01291")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.01291.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.01291)
Connect an agent — have() is free.