Blog

[ICIP2020 to appear] - The Good, the Bad, and the Ugly: Neural Networks Straight from JPEG

In this paper, entitled "The Good, the Bad, and the Ugly: Neural Networks Straight from JPEG", we investigate whether the spatial resolution and JPEG quality affects the performance of CNNs fed with DCT coefficients. More specifically, we studied several aspects of a state-of-the-art CNN recently proposed by Gueguen et al. [1], which is a modified version of the ResNet-50 architecture [2]. Despite the speed-up obtained by partially decoding JPEG images, their architectural changes raised the computation complexity and the number of parameters of the network. To alleviate these drawbacks, we propose a Frequency Band Selection (FBS) technique to select the most relevant DCT coefficients before feeding them to the network. A comparison among the original ResNet-50 network [2], the modified ResNet-50 network proposed by Gueguen et al. [1], and our improved version with FBS is presented below. Original ResNet-50 network [2] ResNet-50 using DCT as input [1]...

Read more ...

GIBIS at the Academic Orientation Week

Today was held a presentation of the GIBIS in the context of the Academic Orientation Week. Two sessions were organized: the first, from 17:15 to 18:30; and second, from 21:45 to 22:30. They were attended by the professors Jurandy Almeida, Fabio Faria and Claudio Shida, and by the students Lucas Lellis, Anderson Faria and Leonardo Duarte. We extend a warm thank you to everyone who was present to know a little bit about our work.

Read more ...