Jingyi Zhang, Jiaxing Huang, Shijian Lu, Xueying Jiang
We lifted 1 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| jingyi0000/bimem | — | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| CustomModel | Not yet run | jingyi0000/bimem/models/adaptation_modelv2.py pointer only (licence: NONE) · get_code("47426bcd4506168c") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Black-box unsupervised domain adaptation (UDA) learns with source predictions of target data without accessing either source data or source models during training, and it has clear superiority in data privacy and flexibility in target network selection. However, the source predictions of target data are often noisy and training with them is prone to learning collapses. We propose BiMem, a bidirectional memorization mechanism that learns to remember useful and representative information to correct noisy pseudo labels on the fly, leading to robust black-box UDA that can generalize across different visual recognition tasks. BiMem constructs three types of memory, including sensory memory, short-term memory, and long-term memory, which interact in a bi-directional manner for comprehensive and robust memorization of learnt features. It includes a forward memorization flow that identifies and stores useful features and a backward calibration flow that rectifies features' pseudo labels progressively. Extensive experiments show that BiMem achieves superior domain adaptation performance consistently across various visual recognition tasks such as image classification, semantic segmentation and object detection.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2308.13236")
get_code_for_paper("2308.13236")
have("2308.13236")
Connect an agent — have() is free.