In the past few years, in the context of fully-supervised semantic segmentation, several losses -- such as cross-entropy and dice -- have emerged as de facto standards to supervise neural networks. The Dice loss is an interesting case, as it comes from the relaxation of the popular Dice coefficient; one of the main evaluation metric in medical imaging applications. In this paper, we first study theoretically the gradient of the dice loss, showing that concretely it is a weighted negative of the ground truth, with a very small dynamic range. This enables us, in the second part of this paper, to mimic the supervision of the dice loss, through a simple element-wise multiplication of the network output with a negative of the ground truth. This rather surprising result sheds light on the practical supervision performed by the dice loss during gradient descent. This can help the practitioner to understand and interpret results while guiding researchers when designing new losses.
相關內容
Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather conditions. GridFormer is designed in a grid structure using a residual dense transformer block, and it introduces two core designs. First, it uses an enhanced attention mechanism in the transformer layer. The mechanism includes stages of the sampler and compact self-attention to improve efficiency, and a local enhancement stage to strengthen local information. Second, we introduce a residual dense transformer block (RDTB) as the final GridFormer layer. This design further improves the network's ability to learn effective features from both preceding and current local features. The GridFormer framework achieves state-of-the-art results on five diverse image restoration tasks in adverse weather conditions, including image deraining, dehazing, deraining & dehazing, desnowing, and multi-weather restoration. The source code and pre-trained models will be released.
We discuss how to implement backjumping (or intelligent backtracking) in Prolog by using the built-ins throw/1 and catch/3. We show that it is impossible in a general case, contrary to a claim that ``backjumping is exception handling". We provide two solutions. One works for binary programs; in a general case it imposes a restriction on where backjumping may originate. The other restricts the class of backjump targets. We also discuss implementing backjumping by using backtracking and the Prolog database. Additionally, we explain the semantics of Prolog exception handling in the presence of coroutining.
Analog compute-in-memory (CIM) systems are promising for deep neural network (DNN) inference acceleration due to their energy efficiency and high throughput. However, as the use of DNNs expands, protecting user input privacy has become increasingly important. In this paper, we identify a potential security vulnerability wherein an adversary can reconstruct the user's private input data from a power side-channel attack, under proper data acquisition and pre-processing, even without knowledge of the DNN model. We further demonstrate a machine learning-based attack approach using a generative adversarial network (GAN) to enhance the data reconstruction. Our results show that the attack methodology is effective in reconstructing user inputs from analog CIM accelerator power leakage, even at large noise levels and after countermeasures are applied. Specifically, we demonstrate the efficacy of our approach on an example of U-Net inference chip for brain tumor detection, and show the original magnetic resonance imaging (MRI) medical images can be successfully reconstructed even at a noise-level of 20% standard deviation of the maximum power signal value. Our study highlights a potential security vulnerability in analog CIM accelerators and raises awareness of using GAN to breach user privacy in such systems.
Towards higher-order accurate mass lumping in explicit isogeometric analysis for structural dynamics
We present a mass lumping approach based on an isogeometric Petrov-Galerkin method that preserves higher-order spatial accuracy in explicit dynamics calculations irrespective of the polynomial degree of the spline approximation. To discretize the test function space, our method uses an approximate dual basis, whose functions are smooth, have local support and satisfy approximate bi-orthogonality with respect to a trial space of B-splines. The resulting mass matrix is ``close'' to the identity matrix. Specifically, a lumped version of this mass matrix preserves all relevant polynomials when utilized in a Galerkin projection. Consequently, the mass matrix can be lumped (via row-sum lumping) without compromising spatial accuracy in explicit dynamics calculations. We address the imposition of Dirichlet boundary conditions and the preservation of approximate bi-orthogonality under geometric mappings. In addition, we establish a link between the exact dual and approximate dual basis functions via an iterative algorithm that improves the approximate dual basis towards exact bi-orthogonality. We demonstrate the performance of our higher-order accurate mass lumping approach via convergence studies and spectral analyses of discretized beam, plate and shell models.
Despite remarkable performance on a variety of tasks, many properties of deep neural networks are not yet theoretically understood. One such mystery is the depth degeneracy phenomenon: the deeper you make your network, the closer your network is to a constant function on initialization. In this paper, we examine the evolution of the angle between two inputs to a ReLU neural network as a function of the number of layers. By using combinatorial expansions, we find precise formulas for how fast this angle goes to zero as depth increases. These formulas capture microscopic fluctuations that are not visible in the popular framework of infinite width limits, and leads to qualitatively different predictions. We validate our theoretical results with Monte Carlo experiments and show that our results accurately approximate finite network behaviour. The formulas are given in terms of the mixed moments of correlated Gaussians passed through the ReLU function. We also find a surprising combinatorial connection between these mixed moments and the Bessel numbers that allows us to explicitly evaluate these moments.
Structured variational autoencoders (SVAEs) combine probabilistic graphical model priors on latent variables, deep neural networks to link latent variables to observed data, and structure-exploiting algorithms for approximate posterior inference. These models are particularly appealing for sequential data, where the prior can capture temporal dependencies. However, despite their conceptual elegance, SVAEs have proven difficult to implement, and more general approaches have been favored in practice. Here, we revisit SVAEs using modern machine learning tools and demonstrate their advantages over more general alternatives in terms of both accuracy and efficiency. First, we develop a modern implementation for hardware acceleration, parallelization, and automatic differentiation of the message passing algorithms at the core of the SVAE. Second, we show that by exploiting structure in the prior, the SVAE learns more accurate models and posterior distributions, which translate into improved performance on prediction tasks. Third, we show how the SVAE can naturally handle missing data, and we leverage this ability to develop a novel, self-supervised training approach. Altogether, these results show that the time is ripe to revisit structured variational autoencoders.
Navigating to destinations using human speech instructions is essential for autonomous mobile robots operating in the real world. Although robots can take different paths toward the same goal, the shortest path is not always optimal. A desired approach is to flexibly accommodate waypoint specifications, planning a better alternative path, even with detours. Furthermore, robots require real-time inference capabilities. Spatial representations include semantic, topological, and metric levels, each capturing different aspects of the environment. This study aims to realize a hierarchical spatial representation by a topometric semantic map and path planning with speech instructions, including waypoints. We propose SpCoTMHP, a hierarchical path-planning method that utilizes multimodal spatial concepts, incorporating place connectivity. This approach provides a novel integrated probabilistic generative model and fast approximate inference, with interaction among the hierarchy levels. A formulation based on control as probabilistic inference theoretically supports the proposed path planning. Navigation experiments using speech instruction with a waypoint demonstrated the performance improvement of path planning, WN-SPL by 0.589, and reduced computation time by 7.14 sec compared to conventional methods. Hierarchical spatial representations offer a mutually understandable form for humans and robots, enabling language-based navigation tasks.
Integrating renewable energy into the power grid while balancing supply and demand is a complex issue, given its intermittent nature. Demand side management (DSM) offers solutions to this challenge. We propose a new method for DSM, in particular the problem of controlling a large population of electrical devices to follow a desired consumption signal. We model it as a finite horizon Markovian mean field control problem. We develop a new algorithm, MD-MFC, which provides theoretical guarantees for convex and Lipschitz objective functions. What distinguishes MD-MFC from the existing load control literature is its effectiveness in directly solving the target tracking problem without resorting to regularization techniques on the main problem. A non-standard Bregman divergence on a mirror descent scheme allows dynamic programming to be used to obtain simple closed-form solutions. In addition, we show that general mean-field game algorithms can be applied to this problem, which expands the possibilities for addressing load control problems. We illustrate our claims with experiments on a realistic data set.
We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and zero or few-shot learning. We formulate unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are shared across different modalities via distillation. Further, we introduce the concept of loss function evolution by using an evolutionary search algorithm to automatically find optimal combination of loss functions capturing many (self-supervised) tasks and modalities. Thirdly, we propose an unsupervised representation evaluation metric using distribution matching to a large unlabeled dataset as a prior constraint, based on Zipf's law. This unsupervised constraint, which is not guided by any labeling, produces similar results to weakly-supervised, task-specific ones. The proposed unsupervised representation learning results in a single RGB network and outperforms previous methods. Notably, it is also more effective than several label-based methods (e.g., ImageNet), with the exception of large, fully labeled video datasets.
In this paper, we focus on three problems in deep learning based medical image segmentation. Firstly, U-net, as a popular model for medical image segmentation, is difficult to train when convolutional layers increase even though a deeper network usually has a better generalization ability because of more learnable parameters. Secondly, the exponential ReLU (ELU), as an alternative of ReLU, is not much different from ReLU when the network of interest gets deep. Thirdly, the Dice loss, as one of the pervasive loss functions for medical image segmentation, is not effective when the prediction is close to ground truth and will cause oscillation during training. To address the aforementioned three problems, we propose and validate a deeper network that can fit medical image datasets that are usually small in the sample size. Meanwhile, we propose a new loss function to accelerate the learning process and a combination of different activation functions to improve the network performance. Our experimental results suggest that our network is comparable or superior to state-of-the-art methods.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191