Ceramic Cracks Segmentation with Deep Learning

Semantic Segmentation with Deep Learning

We present a deep convolutional neural network approach for producing semantic segmentations. First, we generalize the architecture of the successful Alexnet network [7] to directly predict coarse segmentations. Second, we produce full resolution segmentations by re-ranking a diverse set of plausible segmentation proposals generated from a recent state of the art approach [9].

Semantic Part Segmentation with Deep Learning

In this work we address the task of segmenting an object into its parts, or semantic part segmentation. We start by adapting a state-of-the-art semantic segmentation system to this task, and show that a combination of a fully-convolutional Deep CNN system coupled with Dense CRF labelling provides excellent results for a broad range of object categories. Still, this approach remains agnostic to ...

Deepcrop: Directed Object Segmentation with Deep Learning

• The project presented several challenges: understanding DeepMask, learning to program in Torch, and the sheer amount of compute power these models require (3 AWS GPU instances were used for a total of $1000 AWS credit granted by Amazon for this project) • Overall I consider the project successful, since DeepCropV1 provided interesting results as to the limitations of DeepMask and DeepCropV2 w...

New Theory Cracks Open the Black Box of Deep Learning

Melanoma detection with a deep learning model

Background: Skin cancer is one of the most common forms of cancer in the world and melanoma is the deadliest type of skin cancer. Both melanoma and melanocytic nevi begin in melanocytes (cells that produce melanin). However, melanocytic nevi are benign whereas melanoma is malignant. This work proposes a deep learning model for classification of these two lesions.    Methods: In this analytic s...