An official website of the United States government
Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, however, millions of weights in the form of thousands of convolutional filters in CNNs make them difficult for human interpretation or understanding in science. In this article, we introduce a greedy structural compression scheme to obtain smaller and more interpretable CNNs, while achieving close to original accuracy. The compression is based on pruning filters with the least contribution to the classification accuracy or the lowest Classification Accuracy Reduction (CAR) importance index. We demonstrate the interpretability of CAR-compressed CNNs by showing that our algorithm prunes filters with visually redundant functionalities such as color filters. These compressed networks are easier to interpret because they retain the filter diversity of uncompressed networks with an order of magnitude fewer filters. Finally, a variant of CAR is introduced to quantify the importance of each image category to each CNN filter. Specifically, the most and the least important class labels are shown to be meaningful interpretations of each filter.
more »
« less
Plasmonic color filter array based visible light spectroscopy
Abstract Compared with traditional Fabry–Perot optical filters, plasmonic color filters could greatly remedy the complexity and reduce the cost of manufacturing. In this paper we present end-to-end demonstration of visible light spectroscopy based on highly selective plasmonic color filter array based on resonant grating structure. The spectra of 6 assorted samples were measured using an array of 20 narrowband color filters and detected signals were used to reconstruct original spectra by using new unmixing algorithm and by solving least squares problem with smoothing regularization. The original spectra were reconstructed with less than 0.137 root mean squared error. This works shows promise towards fully integrating plasmonic color filter array in imagers used in hyperspectral cameras.
more »
« less
- Award ID(s):
- 1707506
- PAR ID:
- 10380156
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 11
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract We report a novel approach for realizing tunable/reconfigurable terahertz (THz) mesh filters on the basis of micromachined mesa‐array structures. In this approach, different filter patterns are generated virtually using photogenerated free carriers in a semiconducting mesa‐array structure to achieve superior tunability and reconfigurability. Micromachined mesa‐array structures enable the formation of high fidelity, optically generated mesh filter structures for THz frequencies. To evaluate the proposed filter designs, the optically patterned spatial modulation properties of mesa‐array structures were first evaluated. Reconfigurable mesh filter prototypes were then designed and simulated using silicon mesa arrays with 50 × 50 μm2square mesa unit cells. Simulations show that reconfigurable bandpass filters (BPFs) operating in the frequency range of 108–489 GHz with insertion losses of 0.82–1.13 dB can be achieved. By employing smaller unit cells, the frequency tuning range and filtering performance can be further improved. In addition to BPFs, other filter functionalities can also be realized utilizing the proposed approach. The wide tuning range and reconfigurability of the mesh filters demonstrate that the proposed approach is promising for developing tunable/reconfigurable circuits and components for advanced THz sensing, imaging, and communications.more » « less
-
We have designed a new filter pack array to measure angular variations in x-ray spectra during a single shot. The filter pack was composed of repeating identical columns of aluminum and copper filters of varying thicknesses. These columns were located at different positions to measure the spectrum at each corresponding angle. This array was utilized in an experiment to measure the energy evolution of betatron x rays in a laser wakefield accelerator by curving the wakefield with a transverse density gradient, streaking the x rays across the array in front of an x-ray charge-coupled device (CCD) camera. After subtracting the background and “flattening” the image to remove spatial nonuniformities, a critical energy was calculated for each position that produced the best agreement with the measured signal. There was a clear change in critical energy with angle, shedding light on the dynamics of the electrons that traveled through the accelerator. These angles correspond to distinct emission times, covering a timescale of tens of picoseconds. The filter pack was capable of recovering these angular details without the impact of errors introduced by shot-to-shot variability.more » « less
-
We present Sparse Numerical Array-Based Range Filters (SNARF), a learned range filter that efficiently supports range queries for numerical data. SNARF creates a model of the data distribution to map the keys into a bit array which is stored in a compressed form. The model along with the compressed bit array which constitutes SNARF are used to answer membership queries. We evaluate SNARF on multiple synthetic and real-world datasets as a stand-alone filter and by integrating it into RocksDB. For range queries, SNARF provides up to 50x better false positive rate than state-of-the-art range filters, such as SuRF and Rosetta, with the same space usage. We also evaluate SNARF in RocksDB as a filter replacement for filtering requests before they access on-disk data structures. For RocksDB, SNARF can improve the execution time of the system up to 10x compared to SuRF and Rosetta for certain read-only workloads.more » « less
-
This paper introduces a new image smoothing filter based on a feed-forward convolutional neural network (CNN) in presence of impulse noise. This smoothing filter integrates a very deep architecture, a regularization method, and a batch normalization process. This fully integrated approach yields an effectively denoised and smoothed image yielding a high similarity measure with the original noise free image. Specific structural metrics are used to assess the denoising process and how effective was the removal of the impulse noise. This CNN model can also deal with other noise levels not seen during the training phase. The proposed CNN model is constructed through a 20-layer network using 400 images from the Berkeley Segmentation Dataset (BSD) in the training phase. Results are obtained using the standard testing set of 8 natural images not seen in the training phase. The merits of this proposed method are weighed in terms of high similarity measure and structural metrics that conform to the original image and compare favorably to the different results obtained using state-of-art denoising filters.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1038/s41598-021-03092-3
