We lifted 5 functions out of this paper's own repositories and ran 4 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 |
|---|---|---|
| sheqi/Continual_Learning_CV | pwc_unofficial | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| conv1x1 | Ran | sheqi/Continual_Learning_CV/backbones/resnet.py code served (permissive licence) · get_code("d9def42110729a85") |
| conv3x3 | Ran | sheqi/Continual_Learning_CV/backbones/resnet.py code served (permissive licence) · get_code("160bb14bd76201b4") |
| get_multitask_experiment | Ran | sheqi/Continual_Learning_CV/data.py code served (permissive licence) · get_code("046c51a013eb21a5") |
| linearExcitability | Ran | sheqi/Continual_Learning_CV/excitability_modules.py code served (permissive licence) · get_code("a99bc1039b57a869") |
| resnet18 | Not yet run | sheqi/Continual_Learning_CV/backbones/resnet.py code served (permissive licence) · get_code("e6fd4d30c58afef7") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks. Fully retraining models each time a new task becomes available is infeasible due to computational, storage and sometimes privacy issues, while naïve incremental strategies have been shown to suffer from catastrophic forgetting. It is crucial for the robots to operate continuously under open-set and detrimental conditions with adaptive visual perceptual systems, where lifelong learning is a fundamental capability. However, very few datasets and benchmarks are available to evaluate and compare emerging techniques. To fill this gap, we provide a new lifelong robotic vision dataset ("OpenLORIS-Object") collected via RGB-D cameras. The dataset embeds the challenges faced by a robot in the real-life application and provides new benchmarks for validating lifelong object recognition algorithms. Moreover, we have provided a testbed of $9$ state-of-the-art lifelong learning algorithms. Each of them involves $48$ tasks with $4$ evaluation metrics over the OpenLORIS-Object dataset. The results demonstrate that the object recognition task in the ever-changing difficulty environments is far from being solved and the bottlenecks are at the forward/backward transfer designs. Our dataset and benchmark are publicly available at at \href{https://lifelong-robotic-vision.github.io/dataset/object}{\underline{https://lifelong-robotic-vision.github.io/dataset/object}}.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1911.06487")
get_code_for_paper("1911.06487")
have("1911.06487")
Connect an agent — have() is free.