Fundamental machine learning theory shows that different samples contribute unequally to both the learning and testing processes. Recent studies on deep neural networks (DNNs) suggest that such sample differences are rooted in the distribution of intrinsic pattern information, namely sample regularity. Motivated by recent discoveries in network memorization and generalization, we propose a pair of sample regularity measures with a formulation-consistent representation for both processes. Specifically, the cumulative binary training/generalizing loss (CBTL/CBGL), the cumulative number of correct classifications of the training/test sample within the training phase, is proposed to quantify the stability in the memorization-generalization process, while forgetting/mal-generalizing events (ForEvents/MgEvents), i.e., the misclassification of previously learned or generalized samples, are utilized to represent the uncertainty of sample regularity with respect to optimization dynamics. The effectiveness and robustness of the proposed approaches for mini-batch stochastic gradient descent (SGD) optimization are validated through sample-wise analyses. Further training/test sample selection applications show that the proposed measures, which share the unified computing procedure, could benefit both tasks.

The active contour model is a comprehensive research technique used for salient object detection. Most active contour models of saliency detection are developed in the context of natural scenes, and their role with synthetic and medical images is not well investigated. Existing active contour models perform efficiently in many complexities but facing challenges on synthetic and medical images due to the limited time like, precise automatic fitted contour and expensive initialization computational cost. Our intention is detecting automatic boundary of the object without re-initialization which further in evolution drive to extract salient object. For this, we propose a simple novel derivative of a numerical solution scheme, using fast Fourier transformation (FFT) in active contour (Snake) differential equations that has two major enhancements, namely it completely avoids the approximation of expansive spatial derivatives finite differences, and the regularization scheme can be generally extended more. Second, FFT is significantly faster compared to the traditional solution in spatial domain. Finally, this model practiced Fourier-force function to fit curves naturally and extract salient objects from the background. Compared with the state-of-the-art methods, the proposed method achieves at least a 3% increase of accuracy on three diverse set of images. Moreover, it runs very fast, and the average running time of the proposed methods is about one twelfth of the baseline.

In recent years, visual 3D Semantic Scene Completion (SSC) has emerged as a critical perception task for autonomous driving due to its ability to infer complete 3D scene layouts and semantics from single 2D images. However, in real-world traffic scenarios, a significant portion of the scene remains occluded or outside the camera's field of view - a fundamental challenge that existing monocular SSC methods fail to address adequately. To overcome these limitations, we propose Creating the Future SSC (CF-SSC), a novel temporal SSC framework that leverages pseudo-future frame prediction to expand the model's effective perceptual range. Our approach combines poses and depths to establish accurate 3D correspondences, enabling geometrically-consistent fusion of past, present, and predicted future frames in 3D space. Unlike conventional methods that rely on simple feature stacking, our 3D-aware architecture achieves more robust scene completion by explicitly modeling spatial-temporal relationships. Comprehensive experiments on SemanticKITTI [1] and SSCBench-KITTI-360 [2], [3] benchmarks demonstrate state-of-the-art performance, validating the effectiveness of our approach, highlighting our method's ability to improve occlusion reasoning and 3D scene completion accuracy.

The combination of active contour models (ACMs) for both contour and salient object detection is an attractive approach for researchers in image segmentation. Existing active contour models fail when improper initialization is performed. We propose a novel active contour model with salience detection in the complex domain to address this issue. First, the input image is converted to the complex domain. The complex transformation gives salience cue. In addition, it is well suited for cyclic objects and it speeds up the iteration of the active contour. During the process, we utilize a low-pass filter that lets the low spatial frequencies pass, while attenuating, or completely blocking, the high spatial frequencies to reduce the random noise connected with favorable or higher frequencies. Furthermore, the model introduces a force function in the complex domain that dynamically shrinks a contour when it is outside of the object of interest and expands it when the contour is inside the object. Comprehensive tests on both synthetic images and natural images show that our proposed algorithm produces accurate salience results that are close to the ground truth. At the same time, it eliminates re-initialization and, thus, reduces the execution time.