A purely sparse method for object detection in images. A fixed set of learned object proposals, total length of N, are used, thus eleiminating upto hundreds of thousands had designed candidate proposals.

Updated this blog site to use gatsby! Allows me to add many react components in pages and provide a more interactive experience.

Whether it’s diagnosing patients or driving cars, we want to know whether we can trust a person before assigning them a sensitive task. In the human world, we have different ways to establish and measure trustworthiness.

Image classification — the task of understanding the main content of an image — is easy for humans but hard for machines. In particular, it is challenging for convolution-free Transformers like DeiT...

Traditional computer vision models typically use a complex, partly handcrafted pipeline that relies on custom layers in order to localize objects in an image and then extract features.

Unsupervised image-to-image translation is an inherently ill-posed problem. This paper uses linear encoder-decoder architectures for unsupervised image to image translation.

Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such memorizing issue in the presence of annotation noise.

Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted to generate…

Those of us who see the great potential of artificial intelligence in radiology are eager to assure that AI systems work to the benefit of all of our patients...