We lifted 8 functions out of this paper's own repositories and ran 8 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 |
|---|---|---|
| zhangdoudou123/semfew | canonical | 8 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| window_partition | Ran | zhangdoudou123/semfew/model/swin_transformer.py pointer only (licence: NONE) · get_code("144d10b49baeb8a6") |
| conv1x1 | Ran | zhangdoudou123/semfew/model/res18.py pointer only (licence: NONE) · get_code("d9def42110729a85") |
| conv3x3 | Ran | zhangdoudou123/semfew/model/res12.py pointer only (licence: NONE) · get_code("fac5364e2f53c6db") |
| conv3x3 | Ran | zhangdoudou123/semfew/model/WRN28.py pointer only (licence: NONE) · get_code("00e569acd6b45ef0") |
| drop_path | Ran | zhangdoudou123/semfew/model/vision_transformer.py pointer only (licence: NONE) · get_code("55120f2026b56aa2") |
| loggers | Ran | zhangdoudou123/semfew/logger.py pointer only (licence: NONE) · get_code("eff73993564ab59b") |
| resnet18 | Ran | zhangdoudou123/semfew/model/resnet18.py pointer only (licence: NONE) · get_code("9668fcac8fe0b39d") |
| window_reverse | Ran | zhangdoudou123/semfew/model/swin_transformer.py pointer only (licence: NONE) · get_code("61bf152e6a42a184") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Learning from a limited amount of data, namely Few-Shot Learning, stands out as a challenging computer vision task. Several works exploit semantics and design complicated semantic fusion mechanisms to compensate for rare representative features within restricted data. However, relying on naive semantics such as class names introduces biases due to their brevity, while acquiring extensive semantics from external knowledge takes a huge time and effort. This limitation severely constrains the potential of semantics in Few-Shot Learning. In this paper, we design an automatic way called Semantic Evolution to generate high-quality semantics. The incorporation of high-quality semantics alleviates the need for complex network structures and learning algorithms used in previous works. Hence, we employ a simple two-layer network termed Semantic Alignment Network to transform semantics and visual features into robust class prototypes with rich discriminative features for few-shot classification. The experimental results show our framework outperforms all previous methods on six benchmarks, demonstrating a simple network with high-quality semantics can beat intricate multi-modal modules on few-shot classification tasks. Code is available at https://github.com/zhangdoudou123/SemFew.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.18649")
get_code_for_paper("2311.18649")
have("2311.18649")
Connect an agent — have() is free.