Abstract: A synchronous rectification control system and method for a quasi-resonant flyback converter are provided. The control system includes a switching transistor voltage sampling circuit configured to sample an output terminal voltage of the switching transistor to obtain a sampled voltage of the switching transistor; a sampling calculation module configured to obtain a dead-time based on the sampled voltage of the switching transistor and a preset relationship, the preset relationship being a correspondence between the duration of the sampled voltage of the switching transistor being below a first preset value and the dead-time during an on-time of a switching cycle of the switching transistor, the dead-time being a time from when the switching transistor is turned off to when the synchronous rectification transistor is turned on; and a control module configured to receive the dead-time and control switching of the synchronous rectification transistor based on the dead-time.

Abstract: Method, apparatus, and non-transitory storage medium for end-to-end neural image compression using dependent scalar quantization with substitution, including receiving an input image; determining a substitute image based on the input image using a neural network based substitute feature generator; compressing the substitute image; quantizing the compressed substitute image to obtain a quantized representation of the input image with higher compression performance by using a first dependent scalar quantizer; and entropy encoding the substitute image using a neural network based encoder to generate a compressed representation of the quantized representation.

Abstract: Method, apparatus, and non-transitory storage medium for end-to-end neural image compression using dependent scalar quantization with substitution, including receiving an input image; determining a substitute image based on the input image using a neural network based substitute feature generator; compressing the substitute image; quantizing the compressed substitute image to obtain a quantized representation of the input image with higher compression performance by using a first dependent scalar quantizer; and entropy encoding the substitute image using a neural network based encoder to generate a compressed representation of the quantized representation.