Pith. sign in

REVIEW 6 cited by

Effects of Degradations on Deep Neural Network Architectures

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.10108 v6 pith:EBSZOQEB submitted 2018-07-26 cs.CV eess.IV

Prasun Roy , Subhankar Ghosh , Saumik Bhattacharya , Umapada Pal This is my paper · ORCID
classification cs.CVeess.IV
keywords architecturesdeepgaussianimagenoiseblurclassificationmodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep convolutional neural networks (CNN) have massively influenced recent advances in large-scale image classification. More recently, a dynamic routing algorithm with capsules (groups of neurons) has shown state-of-the-art recognition performance. However, the behavior of such networks in the presence of a degrading signal (noise) is mostly unexplored. An analytical study on different network architectures toward noise robustness is essential for selecting the appropriate model in a specific application scenario. This paper presents an extensive performance analysis of six deep architectures for image classification on six most common image degradation models. In this study, we have compared VGG-16, VGG-19, ResNet-50, Inception-v3, MobileNet and CapsuleNet architectures on Gaussian white, Gaussian color, salt-and-pepper, Gaussian blur, motion blur and JPEG compression noise models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Data-free distillation from non-transferable teachers fails because synthesized samples drift toward the OOD domain; ATEsc separates ID-like from OOD-like samples via adversarial robustness and improves distillation.

  2. SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A new benchmark shows that camera capture settings and lighting systematically change the performance of image classifiers, object detectors, and VQA models, and that common vision datasets are biased toward narrow ex...

  3. Identifying Bias in Deep Neural Networks Using Image Transforms

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A method that applies Fourier, wavelet, and median filter transforms to full images to detect whether a CNN's accuracy is driven by dataset background bias rather than object features.

  4. DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A federated learning method combining model-fusion pruning with representation regularization reports modest accuracy gains on two benchmarks while compressing models for heterogeneous devices.

  5. A Possible Reason for why Data-Driven Beats Theory-Driven Computer Vision

    cs.CV 2019-08 conditional novelty 5.0 of 10

    Deep learning may have beaten classical computer vision partly because benchmarks used camera settings outside the classical algorithms' operating ranges.

  6. Robust Federated Learning on Edge Devices with Domain Heterogeneity

    cs.LG 2025-05 conditional novelty 4.0 of 10

    FedAPC augments data, averages the augmented features into local class prototypes, and aligns local features with global prototypes; it reports small average accuracy gains over FedAvg, MOON, and FedProto on Digits an...

Pith tools