Crowd counting is a challenging task due to the influence of various factors, such as scene transformation, complex crowd distribution, uneven illumination, and occlusion. To overcome such problems, scale-adaptive convolutional neural network (SaCNN) used a convolutional neural network to obtain high-quality crowd density map estimation and integrate the density map to get the estimated headcount. To obtain better performance on crowd counting, an improved crowd counting method based on SaCNN was proposed in this paper. The spread parameter, i.e., the standard variance, of geometry-adaptive Gaussian kernel used in SaCNN was optimized to generate a higher quality ground truth density map for training. The absolute count loss with weight 4e-5 was used to jointly optimize with the density map loss to improve the network generalization ability for crowd scenes with few pedestrians. Also, a random cropping method was applied to improve the diversity of training samples to enhance network generalization ability. The experimental results upon ShanghaiTech public dataset showed that the proposed method can obtain more accurate and more robust results on crowd counting than those of SaCNN. INDEX TERMS Crowd counting, convolutional neural network, scale-adaptive convolutional neural network (SaCNN), density map, scale-adaptive, absolute count loss.
Convolutional neural network-based methods are attracting increasing attention in steganalysis. However, steganalysis for content-adaptive image steganography in the spatial domain is still a difficult problem. In this paper, a new convolutional neural network-based steganalysis approach was proposed with two contributions. 1) By adding more convolutional layers in the lower part of the model, we proposed a new arrangement of convolutional layers and pooling layers, which can process the local information better than the existing CNN models in steganalysis. 2) By adding the global average pooling layer before the softmax layer instead of using global average pooling before the fully connected layer, the global average pooling was placed in a better position for steganalysis. Two state-of-the-art steganographic algorithms in the spatial domain, namely, WOW and S-UNIWARD, were used to evaluate the effectiveness of our model. The experimental results on BOSSbase showed that the proposed CNN could obtain better steganalysis performance than YeNet across all tested algorithms when the payloads were 0.2, 0.3, and 0.4 bpp.
This paper addresses the complex issue of resource-constrained scheduling, an NP-hard problem that spans critical areas including chip design and high-performance computing. Traditional scheduling methods often stumble over scalability and applicability challenges. We propose a novel approach using a differentiable combinatorial scheduling framework, utilizing Gumbel-Softmax differentiable sampling technique. This new technical allows for a fully differentiable formulation of linear programming (LP) based scheduling, extending its application to a broader range of LP formulations. To encode inequality constraints for scheduling tasks, we introduce constrained Gumbel Trick, which adeptly encodes arbitrary inequality constraints. Consequently, our method facilitates an efficient and scalable scheduling via gradient descent without the need for training data. Comparative evaluations on both synthetic and real-world benchmarks highlight our capability to significantly improve the optimization efficiency of scheduling, surpassing state-of-the-art solutions offered by commercial and open-source solvers such as CPLEX, Gurobi, and CP-SAT in the majority of the designs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.