•Using a Bayesian classifier reparameterization for classifier uncertainty analysis.•A label augmentation strategy models the distribution for label uncertainty.•Our strategies significantly improve ...the backbones under different SGG tasks.
As a challenging task in computer vision, Scene graph generation (SGG) aims to model the underlying semantic relationships among objects in a given image for scene understanding. Due to the increasing scale and subjectivity, the annotations of existing SGG benchmarks inevitably suffer from some uncertainty issues, resulting in the models hardly learning the relationships comprehensively. In this work, we address the uncertainty from the perspectives of both classifier parameters and relationship labels. On one hand, we handle the classifier uncertainty via learning a Bayesian classifier reparameterization, of which the weights are sampled from a latent space spanned with a prior distribution. On the other hand, we assume that each relationship label is sampled from a latent label space and mitigate the label uncertainty via estimating the latent relationship distribution. As a result, the distribution of the classifier parameters are comprehensively learned under the supervision of the estimated relationship labels, thus improving the model’s generalization ability. Experimental results on the popular benchmark demonstrate that the proposed strategies significantly improve different baseline models on different SGG tasks.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The rapid development of deep learning has opened a new door to the exploration of topology optimization methods. The combination of deep learning and topology optimization has become one of the ...hottest research fields at the moment. Different from most existing work, this paper conducts an in-depth study on the method of directly using neural networks (NN) to carry out topology optimization. Inspired by the idea from the field of “Inverting Representation of Image” and “Physics-Informed Neural Network”, a topology optimization via neural reparameterization framework (TONR) that can solve various topology optimization problems is formed. The core idea of TONR is Reparameterization, which means the update of the design variables (pseudo-density) in the conventional topology optimization method is transformed into the update of the NN’s parameters. The sensitivity analysis in the conventional topology optimization method is realized by automatic differentiation technology. With the update of NN’s parameters, the density field is optimized. Some strategies for dealing with design constraints, determining NN’s initial parameters, and accelerating training are proposed in the paper. In addition, the solution of the multi-constrained topology optimization problem is also embedded in the TONR framework. Numerical examples show that TONR can stably obtain optimized structures for different optimization problems, including the stress-constrained problem, structural natural frequency optimization problems, compliant mechanism design problems, heat conduction system design problems, and the optimization problem of hyperelastic structures. Compared with the existing methods that combine deep learning with topology optimization, TONR does not need to construct a dataset in advance and does not suffer from structural disconnection. The structures obtained by TONR can be comparable to the conventional methods.
•This paper conducts an in-depth exploration of the method that directly executes TO using the NN itself.•In TONR, the update of the design variables in the conventional-TO is transformed into the update of the NN’s parameters.•TONR can solve various optimization problems.•The performance of the optimized structures obtained by TONR can be comparable to that of the conventional method.•TONR employs automatic differentiation to handle differential operators.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
As an emerging and popular technique for boosting CNNs, structural reparameterization (SR) decouples the training and inference structures to alter the training dynamics and achieve cost-free ...improvement of a given network. Existing SR methods often prioritize network expressiveness enhancement but have yet to investigate approaches to mitigate significant bias and non-robustness of model prediction due to over-reliance on training data distribution and image noise. To this end, inspired by the effective strength of implicit regularization on the problem, this paper introduces an extra balanced implicit regularization mechanism into SR techniques to enhance the generalization of a given network for the first time. Specifically, we propose a novel SR module named DR-Block, which is used to complicate each convolutional layer of a given CNN during training. It draws on the advantages of deep matrix factorization with the regularization effect and further improves singular value dynamics by introducing batch normalization and dense connections to alleviate network degradation. At inference time, DR-Block can be equivalently reparameterized back into a single convolution for deployment. Furthermore, we empirically demonstrate the role of each design in DR-Block and explicitly reveal its inherent mechanism, which lies in enhancing the movement of large singular values while countering the attenuation of small ones. This helps enhance the interpretability of SR techniques. Experiments illustrate that DR-Block is an impressive alternative for a regular convolution layer of any structure and outperforms the existing SR methods in improving mainstream network architectures on various visual tasks. The code will be available online.
•Modeling the uncertainty of attention modules.•Improving the generalization ability of attention models.•Mitigating the degradation issue that appears in the reparameterized attention.•Improving the ...image classification performance of different attention models on different datasets consistently.
The attention mechanism has been widely explored for neural networks as it could effectively model the interdependencies among channels, spatial positions, and frames. A neural network with attention modules has uncertainties in its parameters, but training the models deterministically hardly captures the uncertainties. Modeling the parameters’ uncertainty of the attention module could facilitate flexibly capturing the representative patterns, thus promoting the generalization of the models. In this work, we propose a novel reparameterized attention strategy by modeling the uncertainty of the parameters in the attention module and performing uncertainty-aware optimization. Instead of learning deterministic parameters for the attention modules, our strategy learns variational posterior distributions. The experimental results show that our strategy could consistently improve different models’ accuracy and reduce the generalization gap without extra computation.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Latent Dirichlet allocation model (LDA) has been widely used in topic modeling. Recent works have shown the effectiveness of integrating neural network mechanisms with this generative model for ...learning text representation. However, one of the significant setbacks of LDA is that it is based on a Dirichlet prior that has a restrictive covariance structure. All its variables are considered to be negatively correlated, which makes the model restrictive. In a practical sense, topics can be positively or negatively correlated. To address this problem, we proposed a generalized Dirichlet variational autoencoder (GD-VAE) for topic modeling. The Generalized Dirichlet (GD) distribution has a more general covariance structure than the Dirichlet distribution because it takes into account both positively and negatively correlated topics in the corpus. Our proposed model leverages rejection sampling variational inference using a reparameterization trick for effective training. GD-VAE compares favorably to recent works on topic models on several benchmark corpora. Experiments show that accounting for topics’ positive and negative correlations results in better performance. We further validate the superiority of our proposed framework on two image data sets. GD-VAE demonstrates its significance as an integral part of a classification architecture. For reproducibility and further research purposes, code for this work can be found at https://github.com/hormone03/GD-VAE.
•We propose GD-VAE to capture correlations and learn complex distributions.•We show that capturing all correlations leads to improved performance in GD-VAE.•We address training instability by introducing a weighted objective function.•The comprehensive experiments show that GD-VAE outperformed state-of-the-art models.•We demonstrate the effectiveness of GD-VAE on data augmentation with image data sets.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
In the context of medical image segmentation, the segmentation of polyps holds significant importance for early cancer screening and preoperative planning. Polyp images encapsulate substantial ...semantic information, including the main body of the colon, internal wall folds, and the polyp itself. These components exhibit numerous similar features, while the characteristics of polyps vary significantly in different locations. This paper proposes an improved U-Net neural network model designed to address the issue of unbalanced segmentation accuracy and generalization capability in existing models. The incorporation of a reparameterization module as the backbone network integrates multiscale features while adopting a training-prediction model separation pattern ensures the accuracy of the model. To avoid compromising global spatial information and simultaneously enhance the global perceptual capability, we employ a convolutional block attention module to compensate for the feature loss generated by skip connections. Additionally, we devise a loss computation method specific to this model, named CDLoss, to achieve more effective gradient optimization and enhance the model’s ability to segment polyp boundaries. Our model undergoes comprehensive validation on the Kavirs-SEG and CVC-ClinicDB datasets. The segmentation Intersection over Union (IoU) and Dice values reach 96.56% and 98.16%, respectively. The generalization capability achieves 98.57% and 97.33% in CVC-ClinicDB, surpassing other current state-of-the-art polyp image segmentation models.
•The reparameterization module helps balance the model’s extraction of detailed and broad features.•The skip-connected CBAM addresses semantic gaps in multiscale polyp features, enhancing RCNU-Net’s polyp segmentation with richer content.•The CDLoss function merges pixel-level classification accuracy and target overlap measurement to enhance model generalization.•Experimental results demonstrate the superiority of this model over previous research in polyp segmentation.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Physics-based differentiable rendering is becoming increasingly crucial for tasks in inverse rendering and machine learning pipelines. To address discontinuities caused by geometric boundaries and ...occlusion, two classes of methods have been proposed: 1) the edge-sampling methods that directly sample light paths at the scene discontinuity boundaries, which require nontrivial data structures and precomputation to select the edges, and 2) the reparameterization methods that avoid discontinuity sampling but are currently limited to hemispherical integrals and unidirectional path tracing. We introduce a new mathematical formulation that enjoys the benefits of both classes of methods. Unlike previous reparameterization work that focused on hemispherical integral, we derive the reparameterization in the path space. As a result, to estimate derivatives using our formulation, we can apply advanced Monte Carlo rendering methods, such as bidirectional path tracing, while avoiding explicit sampling of discontinuity boundaries. We show differentiable rendering and inverse rendering results to demonstrate the effectiveness of our method.
Sparse reparameterization in Deep Neural Networks (DNNs) aims to achieve a better tradeoff between the network parameter count and performance. Recently, the lottery ticket hypothesis suppose that ...excellent sub-networks (“winning tickets”) exist in dense randomly-initialized networks. These sparse sub-networks trained from scratch are able to reach the performance of their dense counterparts. Compared with Iterative Magnitude Pruning that relies on pruning strategies, the Continuous Sparsification algorithm learns the “winning tickets” with gradient-based methods, achieving better performance. In this paper, we propose Layer-wise Continuous Sparsification (LCS) scheme for finding sparse sub-networks, in which the parameterized relaxation of step functions used to remove network parameters in each layer is integrated into the DNN loss as an optimization objective. LCS utilizes a family of sigmoid functions to asynchronously filter important per-layer weights throughout training, yielding sparser and better sub-networks. Experiments show that our method surpasses state-of-the-art methods for sparse reparameterization. Additionally, the proposed method can be utilized as a regularization technique to further improve the accuracy of dense networks11Our code is publicly available at https://github.com/RiyaoDong/LCS..
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
A rational translational surface is a typical modeling surface used in computer-aided design and the architecture industry. In this study, we determine whether a given algebraic surface implicitly ...defined as V is a rational translational surface or not. This problem is reduced to finding the rational parameterizations of two space curves. More important, our discussions are constructive, and thus if V is translational, we provide a parametric representation of V of the form P(t1,t2)=P1(t1)+P2(t2).
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Given a properly parameterized rational Bézier curve of irreducible degree, it is well-known that its control polygon is uniquely defined. We prove that this property is peculiar to the Bézier model. ...In the rational form associated with any other normalized polynomial basis, Moebius reparameterizations change the control polygon, so the same segment admits different polygons. This feature stems from identifying a remarkable algebraic property of Bernstein polynomials, namely that they provide the only normalized eigenbasis of the linear map, transforming homogeneous control points, that a Moebius reparameterization with fixed endpoints defines. Indeed, preserving the affine control polygon boils down to stretching the homogeneous points, i.e., a map with a diagonal matrix. Our result carries over to the alternative representation of rational curves using trigonometric polynomials so that, once again, the control polygon associated with the corresponding normalized B-basis is the only one enjoying uniqueness.
•The uniqueness of the rational polygon is peculiar to the rational Bézier form.•This uniqueness applies to properly parameterized curves of irreducible degree.•Only in Bézier form Moebius reparametrizations do not affect the control polygon.•The Bernstein basis provides the eigenbasis of the map the reparametrization defines.•The uniqueness extends to the rational trigonometric form in the normalized B-basis.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP