Adaptive Neural Layer for Globally Filtered Segmentation

by   Viktor Shipitsin, et al.

This study is motivated by typical images taken during ultrasonic examinations in the clinic. Their grainy appearance, low resolution, and poor contrast demand an eye of a very qualified expert to discern targets and to spot pathologies. Training a segmentation model on such data is frequently accompanied by excessive pre-processing and image adjustments, with an accumulation of the localization error emerging due to the digital post-filtering artifacts and due to the annotation uncertainty. Each patient case generally requires an individually tuned frequency filter to obtain optimal image contrast and to optimize the segmentation quality. Thus, we aspired to invent an adaptive global frequency-filtering neural layer to "learn" optimal frequency filter for each image together with the weights of the segmentation network itself. Specifically, our model receives the source image in the spatial domain, automatically selects the necessary frequencies from the frequency domain, and transmits the inverse-transform image to the convolutional neural network for concurrent segmentation. In our experiments, such "learnable" filters boosted typical U-Net segmentation performance by 10 and made the training of other popular models (DenseNet and ResNet) almost twice faster. In our experiments, this trait holds both for two public datasets with ultrasonic images (breast and nerves), and for natural images (Caltech birds).


page 3

page 4

page 5

page 9


Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters

Semantic segmentation on driving-scene images is vital for autonomous dr...

Frequency Dropout: Feature-Level Regularization via Randomized Filtering

Deep convolutional neural networks have shown remarkable performance on ...

aura-net : robust segmentation of phase-contrast microscopy images with few annotations

We present AURA-net, a convolutional neural network (CNN) for the segmen...

Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints

Breast cancer is one of the most serious disease affects women's health....

Exploring Frequency Domain Interpretation of Convolutional Neural Networks

Many existing interpretation methods of convolutional neural networks (C...

Frequency Disentangled Learning for Segmentation of Midbrain Structures from Quantitative Susceptibility Mapping Data

One often lacks sufficient annotated samples for training deep segmentat...

Multidimensional Digital Filters for Point-Target Detection in Cluttered Infrared Scenes

A 3-D spatiotemporal prediction-error filter (PEF), is used to enhance f...

Please sign up or login with your details

Forgot password? Click here to reset