Image quality assessment based label smoothing in deep neural network learning
For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in real application scenarios, while the practical issues regardi...
| Հիմնական հեղինակ: | |
|---|---|
| Այլ հեղինակներ: | |
| Ձևաչափ: | Research Report |
| Լեզու: | English |
| Հրապարակվել է: |
2018
|
| Խորագրեր: | |
| Առցանց հասանելիություն: | http://hdl.handle.net/10356/73386 |