Bonjour

In the previous blog, I have discussed YOLACT, a common instance segmentation architecture and my grudges against it and its variants. In this blog, I will introduce another architecture, which I believe a more efficient design. This is namely SOLO. [Read More]

Recently, I reluctantly had a task involving image segmentation. Why reluctance? As a deep learning engineer, I don’t really believe in the power of this branch since convolutional network doesn’t work well in pixel level (I think!!!). Anyways, I give it a try and now I want to share with... [Read More]

In the age when vision technology thrive remarkably, Computer Vision and its application become more and more rife, particularly in retail industry where a host of issues remains unsolved. In AWL Vietnam, we are concentrating on developing a system detecting wrongdoings and analyzing customers’s behaviours. One of the concrete pillar... [Read More]

In my post a year ago, I did discuss about a deep learning technique called DeepRanking. Its core is the triplet loss, which helps to minimize the distance between images in the same group and maximize the ones from different categories . At the moment, I’m working in a project... [Read More]

In the most recent post, I talked about some famous clustering algorithms and they work well in reality. However, we the data scientists don’t really like these methods because of one thing: they are deterministic and nothing in data science have that deterministic, especially in unsupervised learning: we don’t have... [Read More]