ロード中...
Mitigation of Effects of Occlusion on Object Recognition with Deep Neural Networks through Low-Level Image Completion
Heavily occluded objects are more difficult for classification algorithms to identify correctly than unoccluded objects. This effect is rare and thus hard to measure with datasets like ImageNet and PASCAL VOC, however, owing to biases in human-generated image pose selection. We introduce a dataset t...
保存先:
| 出版年: | Comput Intell Neurosci |
|---|---|
| 主要な著者: | , |
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
Hindawi Publishing Corporation
2016
|
| 主題: | |
| オンライン･アクセス: | https://ncbi.nlm.nih.gov/pmc/articles/PMC4908250/ https://ncbi.nlm.nih.gov/pubmed/27340396 https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1155/2016/6425257 |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|