Efficient Neural Network based Classification and Outlier Detection for
Image Moderation using Compressed Sensing and Group Testing
- URL: http://arxiv.org/abs/2305.07639v1
- Date: Fri, 12 May 2023 17:48:05 GMT
- Title: Efficient Neural Network based Classification and Outlier Detection for
Image Moderation using Compressed Sensing and Group Testing
- Authors: Sabyasachi Ghosh, Sanyam Saxena, Ajit Rajwade
- Abstract summary: We propose an approach which exploits this fact to reduce the overall computational cost of such engines.
We present the quantitative matrix-pooled neural network (QMPNN), which takes as input $n$ images.
We also present pooled deep outlier detection, which brings CS and group testing techniques to deep outlier detection.
- Score: 4.2455052426413085
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Popular social media platforms employ neural network based image moderation
engines to classify images uploaded on them as having potentially objectionable
content. Such moderation engines must answer a large number of queries with
heavy computational cost, even though the actual number of images with
objectionable content is usually a tiny fraction. Inspired by recent work on
Neural Group Testing, we propose an approach which exploits this fact to reduce
the overall computational cost of such engines using the technique of
Compressed Sensing (CS). We present the quantitative matrix-pooled neural
network (QMPNN), which takes as input $n$ images, and a $m \times n$ binary
pooling matrix with $m < n$, whose rows indicate $m$ pools of images i.e.
selections of $r$ images out of $n$. The QMPNN efficiently outputs the product
of this matrix with the unknown sparse binary vector indicating whether each
image is objectionable or not, i.e. it outputs the number of objectionable
images in each pool. For suitable matrices, this is decoded using CS decoding
algorithms to predict which images were objectionable. The computational cost
of running the QMPNN and the CS algorithms is significantly lower than the cost
of using a neural network with the same number of parameters separately on each
image to classify the images, which we demonstrate via extensive experiments.
Our technique is inherently resilient to moderate levels of errors in the
prediction from the QMPNN. Furthermore, we present pooled deep outlier
detection, which brings CS and group testing techniques to deep outlier
detection, to provide for the case when the objectionable images do not belong
to a set of pre-defined classes. This technique enables efficient automated
moderation of off-topic images shared on topical forums dedicated to sharing
images of a certain single class, many of which are currently human-moderated.
Related papers
- T-former: An Efficient Transformer for Image Inpainting [50.43302925662507]
A class of attention-based network architectures, called transformer, has shown significant performance on natural language processing fields.
In this paper, we design a novel attention linearly related to the resolution according to Taylor expansion, and based on this attention, a network called $T$-former is designed for image inpainting.
Experiments on several benchmark datasets demonstrate that our proposed method achieves state-of-the-art accuracy while maintaining a relatively low number of parameters and computational complexity.
arXiv Detail & Related papers (2023-05-12T04:10:42Z) - Machine learning based biomedical image processing for echocardiographic
images [0.0]
The proposed method uses K-Nearest Neighbor (KNN) algorithm for segmentation of medical images.
The trained neural network has been tested successfully on a group of echocardiographic images.
arXiv Detail & Related papers (2023-03-16T06:23:43Z) - Traditional Classification Neural Networks are Good Generators: They are
Competitive with DDPMs and GANs [104.72108627191041]
We show that conventional neural network classifiers can generate high-quality images comparable to state-of-the-art generative models.
We propose a mask-based reconstruction module to make semantic gradients-aware to synthesize plausible images.
We show that our method is also applicable to text-to-image generation by regarding image-text foundation models.
arXiv Detail & Related papers (2022-11-27T11:25:35Z) - Efficient Image Denoising by Low-Rank Singular Vector Approximations of Geodesics' Gramian Matrix [2.3499129784547654]
Noise contamination of images results in substandard expectations among the people.
Image denoising is an essential pre-processing step.
We present a manifold-based noise filtering method that mainly exploits a few prominent singular vectors of the geodesics' Gramian matrix.
arXiv Detail & Related papers (2022-09-27T01:03:36Z) - Deep ensembles in bioimage segmentation [74.01883650587321]
In this work, we propose an ensemble of convolutional neural networks (CNNs)
In ensemble methods, many different models are trained and then used for classification, the ensemble aggregates the outputs of the single classifiers.
The proposed ensemble is implemented by combining different backbone networks using the DeepLabV3+ and HarDNet environment.
arXiv Detail & Related papers (2021-12-24T05:54:21Z) - Image Compression with Recurrent Neural Network and Generalized Divisive
Normalization [3.0204520109309843]
Deep learning has gained huge attention from the research community and produced promising image reconstruction results.
Recent methods focused on developing deeper and more complex networks, which significantly increased network complexity.
In this paper, two effective novel blocks are developed: analysis and block synthesis that employs the convolution layer and Generalized Divisive Normalization (GDN) in the variable-rate encoder and decoder side.
arXiv Detail & Related papers (2021-09-05T05:31:55Z) - CNNs for JPEGs: A Study in Computational Cost [49.97673761305336]
Convolutional neural networks (CNNs) have achieved astonishing advances over the past decade.
CNNs are capable of learning robust representations of the data directly from the RGB pixels.
Deep learning methods capable of learning directly from the compressed domain have been gaining attention in recent years.
arXiv Detail & Related papers (2020-12-26T15:00:10Z) - Adversarial Robustness Across Representation Spaces [35.58913661509278]
Adversa robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time.
In this work we extend the setting to consider the problem of training of deep neural networks that can be made simultaneously robust to perturbations applied in multiple natural representation spaces.
arXiv Detail & Related papers (2020-12-01T19:55:58Z) - Efficient detection of adversarial images [2.6249027950824506]
Some or all pixel values of an image are modified by an external attacker, so that the change is almost invisible to the human eye.
This paper first proposes a novel pre-processing technique that facilitates the detection of such modified images.
An adaptive version of this algorithm is proposed where a random number of perturbations are chosen adaptively.
arXiv Detail & Related papers (2020-07-09T05:35:49Z) - Neural Sparse Representation for Image Restoration [116.72107034624344]
Inspired by the robustness and efficiency of sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks.
Our method structurally enforces sparsity constraints upon hidden neurons.
Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks.
arXiv Detail & Related papers (2020-06-08T05:15:17Z) - Computational optimization of convolutional neural networks using
separated filters architecture [69.73393478582027]
We consider a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing.
Use of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding.
arXiv Detail & Related papers (2020-02-18T17:42:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.