Spatial stratified heterogeneity refers to the pattern variation of the target phenomenon across different regions. Current measures mainly quantify spatially stratified heterogeneity in terms of the consistency between strata and the target variable and neglect the complexity of stratification, whereas complex stratification may lead to overfitting and an overestimated degree of heterogeneity. To address this issue, this paper enhances the relative-entropy-based spatial stratified heterogeneity measure to unit explanatory power using the entropy of the stratification. The proposed method first quantifies the stratification complexity using the minimum theoretical number of bits for encoding it, then characterizes the degree of heterogeneity per bit, i.e., unit explanatory power, by the quotient of the relative-entropy-based measure and the stratification complexity. Additionally, this paper develops two visualization tools for interpreting and comparing unit explanatory power and reveals the relation among spatial stratified heterogeneity, stratification complexity, and the log-likelihood function. Finally, we conduct experiments on both illustrative and real-life data sets to show the advantages of the unit explanatory power over traditional spatial stratified heterogeneity measures. The code for computing unit explanatory power has been released athttps://github.com/crafly/ssh_with_gran.

Dataset distillation (DD) condenses key information from large-scale datasets into smaller synthetic datasets, reducing storage and computational costs for training networks. However, most recent research has primarily focused on image classification tasks, with limited exploration in detection and segmentation. Two key challenges remain: (i) Task Optimization Heterogeneity, where existing methods focus on class-level information but fail to address the diverse needs of detection and segmentation, and (ii) Inflexible Image Generation, where current generation methods rely on global updates for single-class targets and lack localized optimization for specific object regions. To address these challenges, we propose UniDD, a universal dataset distillation framework built on a task-driven diffusion model for diverse DD tasks, as shown in Fig. 1. Our approach operates in two stages: Universal Task Knowledge Mining, which captures task-relevant information through task-specific proxy model training, and Universal Task-Driven Diffusion, where these proxies guide the diffusion process to generate task-specific synthetic images. Extensive experiments across ImageNet-1K, Pascal VOC, and MS COCO demonstrate that UniDD consistently outperforms state-of-the-art methods. In particular, on ImageNet-1K with IPC-10, UniDD surpasses previous diffusion-based methods by 6.1%, while also reducing deployment costs.

Existing multi-label knowledge distillation methods simply use regression or single-label classification methods without fully exploiting the essence of multi-label classification, resulting in student models’ inadequate performance and poor functional similarity to teacher models. In this paper, we reinterpret multi-label classification as multiple intra-class ranking tasks, with each class corresponding to a ranking task. Furthermore, we define the knowledge of multi-label classification models as the ranking of intra-class samples. On the one hand, we propose to evaluate the functional similarity between multi-label classification models with Kendall’s tau and rank-biased overlap, which are common metrics for evaluating ranking similarity. On the other hand, we propose a new functionally similar multi-label knowledge distillation method called FSD, which enables student models to learn the ranking of intra-class samples from teacher models. Finally, experimental results validate that FSD outperforms existing methods, especially for functional similarity. Specifically, we achieve a mAP of 73.38% and a mKDT of 0.686 on COCO, which are 2.22% and 0.19 better than existing methods, respectively.

Video-text retrieval has widespread applications in economic and security domains, making it crucial to evaluate its robustness through adversarial attack. However, the existing research in this field is inadequate. In this paper, we first introduce adversarial attack to this task. By leveraging the concept of metric learning, we propose novel attack methods Cross-modal Dual Level Contrastive Attack (CDCA) and Cross-modal Rank Pairing Attack (CRPA). In the white-box scenario, CDCA utilizes the distribution of head and tail examples in the retrieval list to form positive and negative example sets, employing both coarse and fine-grained features. In the black-box scenario, CRPA employs the rank difference in retrieval list as example pairs and utilizes the Rank Difference Loss (RDL) as the attack objective function. Experiments validate the superiority of our methods. Furthermore, we contribute a benchmark, which lays a foundation for understanding the vulnerability of multi-modal models.

Positive and Unlabeled (PU) learning, a binary classification model trained with only positive and unlabeled data, generally suffers from overfitted risk estimation due to inconsistent data distributions. To address this, we introduce a pseudo-supervised PU learning framework (PSPU), in which we train the PU model first, use it to gather confident samples for the pseudo supervision, and then apply these supervision to correct the PU model’s weights by leveraging non-PU objectives. We also incorporate an additional consistency loss to mitigate noisy sample effects. Our PSPU outperforms recent PU learning methods significantly on MNIST, CIFAR-10, CIFAR-100 in both balanced and imbalanced settings, and enjoys competitive performance on MVTecAD for industrial anomaly detection.

Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship between two objects in an image, often neglecting world knowledge and lacking general language capabilities. In this paper, we propose a Large Language-and-Vision Assistant for Visual Spatial Description, named LLaVA-VSD, which is designed for the classification, description, and open-ended description of visual spatial relationships. Specifically, the model first constructs a visual spatial instruction-following dataset using given figure-caption pairs for the three tasks. It then employs LoRA to fine-tune a Large Language and Vision Assistant for VSD, which has 13 billion parameters and supports high-resolution images. Finally, a large language model is used to refine the generated sentences, enhancing their diversity and accuracy. LLaVA-VSD demonstrates excellent multimodal conversational capabilities and can follow open-ended instructions to assist with inquiries about object relationships in images.

This paper proposes spatial distribution pattern-based subpixel mapping (SPMS) as a novel subpixel mapping (SPM) strategy. It separately considers spatial distribution patterns of different types of geographical objects. Initially, it classifies geographical objects into areal, linear, and point patterns according to their spatially geometric characteristics. For the different patterns, SPMS uses the vectorial boundary-based SPM algorithm with the spatial dependence assumption to deal with areal objects, the linear template matching-based SPM algorithm for linear objects, and the spatial pattern consistency matching-based SPM algorithm for point objects. The three patterns are integrated to generate a subpixel map. An artificially created image and two remotely sensed images were used to evaluate the performance of SPMS. The results were compared with a traditional hard classifier and seven existing SPM methods. The experimental results demonstrated that SPMS performed better than the hard classification and traditional SPM methods, particularly when dealing with linear and point objects.