Signal Processing
By Nirode Mohanty. 2013
3,700 citations recorded by the source corpus.
learnable upsampling strategy DUpsampling is utilized to replace the commonly used bilinear interpolation to improve the segmentation accuracy. We deploy detailed experiments on three publicly available datasets, named NWPU_YRCC_EX, NWPU_YRCC2, and Alberta River Ice Segmentation Dataset. The experimental results demonstrate that our method achieves state-of-the-art performance with competing methods, on the NWPU_YRCC_EX dataset, we can achieve the segmentation speed as 90.84FPS and the segmentation accuracy as 90.770 % mIoU, which also illustrates the good leverage between accuracy and speed. Our code is available at https://github.com/nwpulab113/FastICENet ©
Subfields: Computer Networks and Communications, Speech & Audio
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Networks and Communications
- Mariya Ishteva
- S. Van Huffel
- Pierre-Antoine Absil
- Bernhard Schölkopf
- Thomas B. Berrett
- Hodjat Shirmard
- T. Chen
- Raphael Suter
In Speech & Audio
- Sepp Hochreiter
- J. Urgen Schmidhuber
- A. Hero
- Koby Todros
- Richard J. Samworth
- Thomas B. Berrett
- Hodjat Shirmard
- T. Chen
Citations in the corpus
- A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation (2020, methodology): “Similarly, the non-linear ICA community recently shifted to non-iid data types exploiting time dependent or grouped observations (Hyvarinen and Morioka, 2016; Hyvarinen et al., 2019; Gresele et al., 2019) We focus our study on the setting where factors of variations are not observable at all, that i”
- Flexibly Fair Representation Learning by Disentanglement (2019, background): “The search of independent latent components that explain observed data has long been a focus on the probabilistic modeling community (Comon, 1994; Hyv¨arinen & Oja, 2000; Bach & Jordan, 2002).”
- On the Transfer of Disentangled Representations in Realistic Settings (2020, background): “Ideas related to disentangling the factors of variation date back to the non-linear ICA literature (Comon, 1994; Hyv¨arinen and Pajunen, 1999; Bach and Jordan, 2002; Jutten and Karhunen, 2003; Hyvarinen and Morioka, 2016; Hyvarinen et al., 2019; Gresele et al., 2019).”
- Weakly-Supervised Disentanglement Without Compromises (2020, background): “It has roots in the independent component analysis (ICA) literature, where the goal is to unmix independent non-Gaussian sources of a d-dimensional signal (Comon, 1994).”
- On the Fairness of Disentangled Representations (2019, background): “Ideas related to disentangling the factors of variations have a long tradition in machine learning, dating back to the non-linear ICA literature [17, 3, 46, 42, 43, 44, 32].”
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (2018, methodology): “The lack of almost any identifiability result in nonlinear ICA has been a main bottleneck for the utility of the approach (Hyvarinen et al., 2018) and partially motivated alternative machine learning approaches (Desjardins et al., 2012; Schmidhuber, 1992; Cohen & Welling, 2015).”
- Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness (2018, methodology): “Others used techniques to encourage statistical independence between the different components in Z , e.g., FactorVAE (Kim & Mnih, 2018) or β -TCVAE (Chen et al., 2018), similar to independent component analysis (e.g. Comon, 1994).”
- Isolating Sources of Disentanglement in VAEs (2018, background): “In a similar vein, non-linear independent component analysis [36, 37, 38] studies the problem of inverting a generative process assuming independent latent factors.”
- Disentangling Factors of Variation Using Few Labels (2019, background): “We conclude that the semi-supervised loss improves the training and transfer better to different metrics 0.84 0.86 0.88 0.90 0.92 0.94 0.96 V a lu e Metric = BetaVAE Score 0.60 0.65 0.70 0.75 0.80 0.85 0.90 0.95 Metric = FactorVAE Score 0.10 0.15 0.20 0.25 0.30 0.35 0.40 0.45 Metric = MIG 0.15 0.20 ”
- Unsupervised Model Selection for Variational Disentangled Representation Learning (2019, neutral): “This theoretical result is not surprising and has been known for a while in the ICA literature (Comon, 1994), however what is surprising is that disentangling VAEs appear to work in practice.”
- How Does BERT Answer Questions?: A Layer-Wise Analysis of Transformer Representations (2019, methodology): “the vectors into two-dimensional space. To that end we apply T-distributed Stochastic Neighbor Embedding (t-SNE) [35], Principal Component Analysis (PCA) [10] and Independent Component Analysis (ICA) [3] to vectors in each layer. As the results of PCA reveal the most distinct clusters for our data, ”
- Natural Gradient Works Eciently in Learning (methodology): “Such a loss function is obtained by the maximum entropy method (Bell and Sejnowski, 1995), independent component analysis (Common, 1994) or by the statistical likelihood method.”
- A review of machine learning in processing remote sensing data for mineral exploration (2021, methodology): “Shirmard et al. (2020) applied PCA, ICA, MNF and compared their efficiency for mapping different alteration types using ASTER data.”
- Disentanglement through Nonlinear ICA with General Incompressible-flow Networks (GIN) (2020, background): “The theory of identifiability in linear independent component analysis (ICA) (Comon, 1994) tells us when this is possible, if we restrict the model to a linear transformation, but until recently there was no corresponding theory for the highly nonlinear models needed to manipulate complex data.”
- Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style (2021, background): “(3) Our setting for modelling data augmentation differs from that commonly assumed in (multi-view) disentanglement and ICA in that we do not assume that the latent factors z = (c, s) are mutually (or conditionally) independent, i.e., we allow for arbitrary (non-factorised) marginals pz in (2).6 Caus”
- On the best low multilinear rank approximation of higher-order tensors (2010, background): “The tensor corresponding to S can be made as diagonal as possible (in a least squares sense) under orthogonal transformations [ 12 , 24, 56, 10], or the original tensor can be decomposed in a minimal number of rank-1 terms (CANDECOMP/PARAFAC) [13, 37, 9, 25, 17], on which orthogonal [50] or symmetry”
- Modeling multivariable hydrological series: Principal component analysis or independent component analysis? (2007, background): “and H(ygauss) is similarly defined as the entropy of a Gaussian variable ygauss of the same covariance matrix as y [ Comon, 1994 ].”