An official website of the United States government
This paper presents a pixel-level predictive sampling method for image sensing and processing to reduce the computing overhead for power-limited image sensing systems. The predictive sampling method scans through rows and columns to identify the location and value of the critical pixels, which are the turning points in the row and column arrays. The prediction is performed using the value of prior pixels and a pre-defined error threshold. When the prediction is successful, the pixel is marked as a non-critical pixel and is skipped for recording and processing. Only the critical pixels are selected for further processing. We proposed reconstruction methods that recover the raw image from the selected critical pixels using interpolation. The experimental results show that the proposed method can reduce the data throughput by 72% with an error of 1.6% for sparse images. The convolutional neural network model applied with this method can achieve a similar detection accuracy in a standard method while only using 27.1% of data size.
more »
« less
Erroneous pixel prediction for semantic image segmentation
Abstract We consider semantic image segmentation. Our method is inspired by Bayesian deep learning which improves image segmentation accuracy by modeling the uncertainty of the network output. In contrast to uncertainty, our method directly learns to predict the erroneous pixels of a segmentation network, which is modeled as a binary classification problem. It can speed up training comparing to the Monte Carlo integration often used in Bayesian deep learning. It also allows us to train a branch to correct the labels of erroneous pixels. Our method consists of three stages: (i) predict pixel-wise error probability of the initial result, (ii) redetermine new labels for pixels with high error probability, and (iii) fuse the initial result and the redetermined result with respect to the error probability. We formulate the error-pixel prediction problem as a classification task and employ an error-prediction branch in the network to predict pixel-wise error probabilities. We also introduce a detail branch to focus the training process on the erroneous pixels. We have experimentally validated our method on the Cityscapes and ADE20K datasets. Our model can be easily added to various advanced segmentation networks to improve their performance. Taking DeepLabv3+ as an example, our network can achieve 82.88% of mIoU on Cityscapes testing dataset and 45.73% on ADE20K validation dataset, improving corresponding DeepLabv3+ results by 0.74% and 0.13% respectively.
more »
« less
- Award ID(s):
- 2018069
- PAR ID:
- 10346645
- Date Published:
- Journal Name:
- Computational Visual Media
- Volume:
- 8
- Issue:
- 1
- ISSN:
- 2096-0433
- Page Range / eLocation ID:
- 165 to 175
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Implicit neural representations (INR) have been recently proposed as deep learning (DL) based solutions for image compression. An image can be compressed by training an INR model with fewer weights than the number of image pixels to map the coordinates of the image to corresponding pixel values. While traditional training approaches for INRs are based on enforcing pixel-wise image consistency, we propose to further improve image quality by using a new structural regularizer. We present structural regularization for INR compression (SINCO) as a novel INR method for image compression. SINCO imposes structural consistency of the compressed images to the groundtruth by using a segmentation network to penalize the discrepancy of segmentation masks predicted from compressed images. We validate SINCO on brain MRI images by showing that it can achieve better performance than some recent INR methods.more » « less
-
null (Ed.)Abstract Deep neural networks (DNNs) have achieved state-of-the-art performance in many important domains, including medical diagnosis, security, and autonomous driving. In domains where safety is highly critical, an erroneous decision can result in serious consequences. While a perfect prediction accuracy is not always achievable, recent work on Bayesian deep networks shows that it is possible to know when DNNs are more likely to make mistakes. Knowing what DNNs do not know is desirable to increase the safety of deep learning technology in sensitive applications; Bayesian neural networks attempt to address this challenge. Traditional approaches are computationally intractable and do not scale well to large, complex neural network architectures. In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights. This method called Monte Carlo DropConnect (MC-DropConnect) gives us a tool to represent the model uncertainty with little change in the overall model structure or computational cost. We extensively validate the proposed algorithm on multiple network architectures and datasets for classification and semantic segmentation tasks. We also propose new metrics to quantify uncertainty estimates. This enables an objective comparison between MC-DropConnect and prior approaches. Our empirical results demonstrate that the proposed framework yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art.more » « less
-
Our method uses manipulation in video to learn to understand held-objects and hand-object contact. We train a system that takes a single RGB image and produces a pixel-embedding that can be used to answer grouping questions (do these two pixels go together) as well as hand-association questions (is this hand holding that pixel). Rather than painstakingly annotate segmentation masks, we observe people in realistic video data. We show that pairing epipolar geometry with modern optical flow produces simple and effective pseudo-labels for grouping. Given people segmentations, we can further associate pixels with hands to understand contact. Our system achieves competitive results on hand and hand-held object tasks.more » « less
-
Nuclei segmentation is a fundamental task in histopathological image analysis. Typically, such segmentation tasks require significant effort to manually generate pixel-wise annotations for fully supervised training. To alleviate the manual effort, in this paper we propose a novel approach using points only annotation. Two types of coarse labels with complementary information are derived from the points annotation, and are then utilized to train a deep neural network. The fully- connected conditional random field loss is utilized to further refine the model without introducing extra computational complexity during inference. Experimental results on two nuclei segmentation datasets reveal that the proposed method is able to achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods while requiring significantly less annotation effort. Our code is publicly available.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s41095-021-0235-7
