Hi, this is Jieming at NUS. I’m documenting my learning notes in this blog.
I’m currently a research engineer intern in SenseTime in Singapore and actively learning Backend Development knowledge.
PRML | Probability Distributions
Chapter 2 Probability Distributions Chapter Structure Exponential family distribution： Exponential family distribution has a fixed formed conjugate prior. Bernoulli distribution Conjugate Prior: Beta distribution One binary experiment: toss a coin Binomial distribution Conjugate Prior: Beta distribution N binary experiments: toss a coin many times Multinomial distribution Conjugate Prior: Dirichlet distribution Multiple value experiments: like throw the dice Gaussian Distribution Conjugate Prior of Mean: Gaussain distribution Conjugate Prior of Variance: Inverse Gamma distribution...
Enhancement | Exposure Correction
Background Similarity measurement(PSNR and SSIM) PSNR Peak signal-to-noise ratio (PSNR) is to check the similarity of differences. The definition starts from the mean squared error. $$ MSE = \frac{1}{c\cdot h\cdot w}\sum(I_1-I_2)^2 $$ where $I_1$ and $I_2$ are two images, $h$ and $w$ are the height and width of images, $c$ is the numbers of channels. Then PSNR is expressed as $$ PSNR = 10\cdot \log_{10} \left(\frac{MAX_I^2}{MSE}\right) $$ where the $MAX_I$...
Object detection | Overview
bounding box ground truth 4 number to decide a bounding box $$ (x_{left-up}, y_{left-up},x_{right-down}, y_{right-down})\ (x_{left-up}, y_{left-up},width, height) $$ for drawing, another kind $$ (x_{center}, y_{center}, width, height) $$ Dataset every row represent a object File_name, object_class, bounding box(4 value) COCO dataset 80 object class, 330K picture, 1.5M objects anchor box A lot of anchor-box-based algorithm. a series of predictive box. predict whether every anchor box has interested object if yes, predict the offset between anchor box and bounding box Every anchor box is a training sample....