We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| yxiwang/atp | canonical | 1 of 1 |
| copy not recorded | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| calc_grad_magnitude | Ran | this paper's copy was not recorded; identical code first harvested from usr922/fst pointer only · get_code("be78c4e9ca31118d") |
| convert_to_train_id | Ran | yxiwang/atp/tools/convert_datasets/gta.py code served (permissive licence) · get_code("91a6e5fa8152a0f0") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property protection. However, a number of feature alignment techniques in prior domain adaptation methods are not feasible in this challenging problem setting. Thereby, we resort to probing inherent domain-invariant feature learning and propose a curriculum-style self-training approach for source-free domain adaptive semantic segmentation. In particular, we introduce a curriculum-style entropy minimization method to explore the implicit knowledge from the source model, which fits the trained source model to the target data using certain information from easy-to-hard predictions. We then train the segmentation network by the proposed complementary curriculum-style self-training, which utilizes the negative and positive pseudo labels following the curriculum-learning manner. Although negative pseudo-labels with high uncertainty cannot be identified with the correct labels, they can definitely indicate absent classes. Moreover, we employ an information propagation scheme to further reduce the intra-domain discrepancy within the target domain, which could act as a standard post-processing method for the domain adaptation field. Furthermore, we extend the proposed method to a more challenging black-box source model scenario where only the source model's predictions are available. Extensive experiments validate that our method yields state-of-the-art performance on source-free semantic segmentation tasks for both synthetic-to-real and adverse conditions datasets. The code and corresponding trained models are released at \url{https://github.com/yxiwang/ATP}.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.11653")
get_code_for_paper("2106.11653")
have("2106.11653")
Connect an agent — have() is free.