2results about How to "Avoid problems such as loss" patented technology

The application provides a baffle, an expansion card containing the baffle and an electronic device. The expansion card is suitable for a case of the electronic device and includes a circuit board and the baffle. The baffle includes a baffle part and an assembling part. The baffle part is fixed to the circuit board. The assembling part is detachably clamped to the baffle part and is suitable for being combined with the case, so that the expansion card is assembled to the electronic device through the assembling part.

This invention proposes a domain-adaptive method for dehazing coal mine dust and fog images with partial parameter sharing. The method includes: constructing a coal mine dust and fog image dataset; building a domain-adaptive dehazing network framework with partial parameter sharing; supervised training of a loss function for synthetic dust and fog images; enhancement of real dust and fog images followed by unsupervised adversarial training; designing an enhancement module for real dust and fog images followed by supervised training; and obtaining the dehazed coal mine dust and fog images. The method provided by this invention effectively alleviates the problem of poor generalization ability of deep networks trained on synthetic data on real coal mine dust and fog images, thus improving the visual effect of the images.