Diffusion models have emerged as state-of-the-art generative methods, particularly excelling in conditional tasks such as prompt-driven image synthesis. While recent research emphasizes the pivotal role of noise seeds in enhancing text-image alignment and generating human-preferred outputs,these works predominantly rely on random Gaussian noise or heuristic local adjustments, , overlooking the potential of global optimization trategies to systematically improve generation quality. To bridge this gap, we propose Seed Optimization based on Evolution (SOE), a hybrid framework that integrates global evolutionary search with local semantic refinement. The global evolutionary stage conducts seed selection by jointly optimizing text-image alignment (via CLIP-Score) and human preference estimation (via ImageReward), while the local stage employs diffusion inversion to inject conditional semantics into the noise seed. Together, these components constitute a model-agnostic, training-free optimization framework for conditional diffusion models. Extensive experiments across various diffusion models demonstrate that SOE consistently improves semantic fidelity and visual quality, highlighting its generalizability and potential as a plug-and-play enhancement for generative diffusion pipelines.

Transfer-based adversarial attacks involve generating adversarial point clouds in surrogate models and transferring them to other models to assess 3D model robustness. However, current methods rely too much on surrogate model parameters, limiting transferability. In this work, we use Shapley value to identify positive and negative features, guiding optimization of adversarial noise in feature space. To effectively mislead the 3D classifier, we factorize the adversarial noise into positive and negative noise, with the former keeping the features of the adversarial point cloud close to the negative features, and the latter and the adversarial noise moving it away from the positive features. Finally, a novel adversarial point cloud attack method with Adversarial Noise Factorization is proposed, which is abbreviated asANF. ANF simultaneously optimizes the adversarial noise and its positive and negative noise in the feature space, only relying on partial network parameters, which significantly reduces the reliance on the surrogate model and improves the transferability of the adversarial point cloud. Experiments on well-recognized benchmark datasets show that the transferability of adversarial point clouds generated by ANF could be improved by more than 26.7$\%$on average over state-of-the-art transfer-based adversarial attack methods.

Multimodal change detection (MCD) aims to detect changed areas between the bi-temporal multimodal images such as the RGB, panchromatic (PAN), multispectral (MS), and synthetic aperture radar (SAR) images, which has attracted attention in recent years. However, existing deep learning-based methods for MCD tasks still face several heterogeneity factors, the first one is the spatial resolution differences in multimodal data, which leads to the semantic gap between multimodal features. To solve this problem, we propose the heterogeneous collaborative fusion (HCF) module to integrate the multimodal features with spatial gaps. The other one is the consistency and dissimilarity between multimodal data, which lead to unequal detection contributions. To address this dilemma, we propose the heterogeneous adaptive fusion (HAF) module to fuse multimodal decision-making jointly. In this study, we proposed a heterogeneous fusion network for MCD (HF-MCD) with the HCF and the HAF module. We validate the proposed method on four public available MCD datasets. Extensive experimental results have demonstrated the superior performance of HF-MCD over the state-of-the-art methods.

Deploying state-of-the-art object detectors on resource-limited devices presents significant challenges. Knowledge distillation is an efficient and streamlined lightweight technique to improve the accuracy of compact detectors. However, its effectiveness is limited by the redundancy of different types of semantics on the feature map and the closure of same level’s feature distillation. To alleviate this problem, we propose Decoupled and Interactive Distillation, an effective and versatile method to improve knowledge distillation in some complex object detection tasks. The method has two key components. A knowledge decoupled module captures category awareness and localization awareness features. A multi-level feature interaction distillation can aggregate feature distillations from shallow to deep levels, facilitating the collaboration between feature transfers at different levels. The relevant experiments in traffic-related, 3D, rotated object detection have verified the effectiveness of the proposed method, particularly in challenging scenes.

The reliability and robustness of 3D object detection play an instrumental role in the practical deployment of autonomous driving systems. Despite previous research indicating that adversarial examples can negatively affect 3D object detection models, leading to misinterpretations of the environment, these models still maintain the capability to detect the majority of objects within adversarially manipulated point clouds. To further probe into the adversarial robustness of these models, we propose an effective adversarial attack method named IoU-S attack in this paper. We meticulously formulate the adversarial loss to adversely affect the decision-making behavior (such as localization, etc.) of 3D object detection, thereby compromising its ability to accurately interpret the environment. Owing to the significant relevance of this adversarial loss to 3D object detection tasks, we have integrated the IoU-S attack into three attack paradigms: point cloud perturbation, detachment, and attachment. Comprehensive experiments on the widely accepted nuScenes dataset illustrate that the IoU-S attack outperforms existing attack methods in both white-box and black-box scenarios (https://github.com/haichen-ber/IoU-S-Attack). It reinforces its potential to serve as a valuable method in understanding and enhancing the robustness of 3D object detection models against adversarial attacks.

Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much high dimension, which brings huge computational costs when generating adversarial videos. This is especially serious for the query-based black-box attacks where gradient estimation for the threat models is usually utilized, and high dimensions will lead to a large number of queries. To mitigate this issue, we propose to simultaneously eliminate the temporal and spatial redundancy within the video to achieve an effective and efficient gradient estimation on the reduced searching space, and thus query number could decrease. To implement this idea, we design the novel Adversarial spatial-temporal Focus (AstFocus) attack on videos, which performs attacks on the simultaneously focused key frames and key regions from the inter-frames and intra-frames in the video. AstFocus attack is based on the cooperative Multi-Agent Reinforcement Learning (MARL) framework. One agent is responsible for selecting key frames, and another agent is responsible for selecting key regions. These two agents are jointly trained by the common rewards received from the black-box threat models to perform a cooperative prediction. By continuously querying, the reduced searching space composed of key frames and key regions is becoming precise, and the whole query number becomes less than that on the original video. Extensive experiments on four mainstream video recognition models and three widely used action recognition datasets demonstrate that the proposed AstFocus attack outperforms the SOTA methods, which is prevenient in fooling rate, query number, time, and perturbation magnitude at the same time.

More and more deep neural network models have been deployed in real-time video systems. However, it is proved that deep models are susceptible to the crafted adversarial examples. The adversarial examples are imperceptible and can make the normal deep models misclassify them. Although there exist a few works aiming at the adversarial examples of video recognition in the black-box attack mode, most of them need large perturbations or hundreds of thousands of queries. There are still lack of effective adversarial methods to produce adversarial videos with small perturbations and limited query numbers at the same time.

Infrared remote-sensing images have irreplaceable value in military and civilian research, such as remote surveillance and military reconnaissance. However, under the conditions of complex scenes, infrared ship detection still faces great challenges. Most importantly, because of the limited hardware resource, the spaceborne satellites usually have weak computational processing ability, which makes the traditional convolution neural network (CNN)-based detection algorithms difficult to show their power. In terms of the above facts, this article proposes a high-performance but low-computation and storage-efficient ship detection algorithm to adapt the severe spaceborne environment. Overall, our method contains the following technical steps: 1) we first present a novel iterative precise segmentation of land and sea algorithm to preprocess the complex and diverse remote-sensing scenes; 2) the multivariate Gaussian distribution is then selected to extract the ship target candidate regions to guarantee the detection recall; 3) we adopt the optical panchromatic data to assist the limited infrared data training; and 4) the cascade decision of multisource features including global and local cues is next utilized to gradually eliminate false alarms. Due to the high efficiency, the proposed method can implement well on the hardware platform of DSP and field-programmable gate array (FPGA) architecture. We conduct a series of experiments and compare with the state-of-the-art object detection algorithms. Experimental results show that our method has fewer parameters but can achieve strong detection robustness against the noise, cloud and reef interfere, which verifies the effectiveness of the proposed method.

Clustering is an important unsupervised machine learning method which has played an important role in various fields. Density-based clustering methods are capable of dealing with clusters of different sizes and shapes. As suggested by Alex Rodriguez et al. in a paper published in Science in 2014, the 2D decision graph of the estimated density value versus the minimum distance from the points with higher density values for all the data points can be used to identify the cluster centroids. However, there lack automatic methods for the determination of the cluster centroids from the decision graph. In this work, a novel statistic-based method is designed to identify the cluster centroids automatically from the decision graph. So the number of clusters is also automatically determined. Experiments on several synthetic and real-world datasets show the superiority of the proposed method in centroid identification from the datasets with various distributions and dimensionalities. Furthermore, it is also shown that the proposed method can be effectively applied to image segmentation. Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.