Deep neural networks have advanced chromosome classification, a critical procedure in karyotyping for disease diagnosis. However, training an effective DNN requires clean and reliable data, whereas real-world clinical chromosome data often contain label errors and outliers, which degrade DNN performance and limit their clinical applicability. In this work, we propose a Noise-Tolerance Automatic Cleaning framework, named NoTAC, to address potential labeling errors and outliers to enhance the performance of chromosome classification. The framework consists of two branches: KaryoCleanse for label noise detection and KaryoDrift for outlier identification. First, it identifies potential label errors by leveraging the DNN's self-confidence, estimating the latent label distribution, and ranking probabilities to prune mislabeled data. Second, it scores out-of-distribution samples based on the average K-nearest neighbor distances, enabling the identification and removal of outlier data. We conducted comprehensive comparative experiments against state-of-the-art noise-handling methods on a real-world R-band bone marrow chromosome dataset. Our results demonstrate that NoTAC achieves superior performance with an accuracy of 93.99%, which represents a 6.25% relative improvement over the baseline and outperforms the best competing method by 0.92% . Furthermore, our qualitative analysis of NoTAC revealed reliable data issues in a real-world R-band bone marrow chromosome dataset, offering insights into how these issues impair DNN prediction capabilities. These findings demonstrate NoTAC's potential to enhance both the performance and reliability of DNNs in practical medical datasets. The proposed method has also been applied to assist clinical karyotype diagnosis.

Many existing adversarial attacks generate -norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes. Towards visual imperceptibility, some recent works explore unrestricted attacks without -norm constraints, yet lacking transferability of attacking black-box models. In this work, we propose a novel imperceptible and transferable attack by leveraging both the generative and discriminative power of diffusion models. Specifically, instead of direct manipulation in pixel space, we craft perturbations in the latent space of diffusion models. Combined with well-designed content-preserving structures, we can generate human-insensitive perturbations embedded with semantic clues. For better transferability, we further "deceive" the diffusion model which can be viewed as an implicit recognition surrogate, by distracting its attention away from the target regions. To our knowledge, our proposed method, DiffAttack, is the first that introduces diffusion models into the adversarial attack field. Extensive experiments conducted across diverse model architectures (CNNs, Transformers, and MLPs), datasets (ImageNet, CUB-200, and Standford Cars), and defense mechanisms underscore the superiority of our attack over existing methods such as iterative attacks, GAN-based attacks, and ensemble attacks. Furthermore, we provide a comprehensive discussion on future research avenues in diffusion-based adversarial attacks, aiming to chart a course for this burgeoning field.

Foundation models have attracted significant attention for their impressive generalizability across diverse downstream tasks. However, they are demonstrated to exhibit great limitations in representing high-frequency components and fine-grained details. In many medical imaging tasks, precise representation of such information is crucial due to the inherently intricate anatomical structures, sub-visual features, and complex boundaries involved. Consequently, the limited representation of prevalent foundation models can result in considerable performance degradation or even failure in these tasks. To address these challenges, we propose a novel pretraining strategy for both 2D images and 3D volumes, named Frequency-advanced Representation Autoencoder (Frepa). Through high-frequency masking and low-frequency perturbation combined with embedding consistency learning, Frepa encourages the encoder to effectively represent and preserve high-frequency components in the image embeddings. Additionally, we introduce an innovative histogram-equalized image masking strategy, extending the Masked Autoencoder approach beyond ViT to other architectures such as Swin-Transformer and convolutional networks. We develop Frepa across nine medical modalities and validate it on 32 downstream tasks for both 2D images and 3D volumes. Without fine-tuning, Frepa can outperform other self-supervised pretraining methods and, in some cases, even surpasses task-specific foundation models. This improvement is particularly significant for tasks involving fine-grained details, such as achieving up to a +15% increase in dice score for retina vessel segmentation and a +8% increase in IoU for lung tumor detection. Further experiment quantitatively reveals that Frepa enables superior high-frequency representations and preservation in the embeddings, underscoring its potential for developing more generalized and universal medical image foundation models.

We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training expenses and often struggle with generalization to unseen images. To this end, we introduce a fully modularized framework inspired by human behavior. Leveraging the reasoning capabilities of recent foundation models in language and vision, our approach comprises three main stages. Initially, we employ a pretrained vision-language model (VLM) to generate descriptions for the composite image. Subsequently, these descriptions guide the foreground harmonization direction of a text-to-image generative model (T2I). We refine text embeddings for enhanced representation of imaging conditions and employ self-attention and edge maps for structure preservation. Following each harmonization iteration, an evaluator determines whether to conclude or modify the harmonization direction. The resulting framework, mirroring human behavior, achieves harmonious results without the need for extensive training. We present compelling visual results across diverse scenes and objects, along with quantitative comparisons validating the effectiveness of our approach.

Multimodal learning significantly benefits cancer survival prediction, especially the integration of pathological images and genomic data. Despite advantages of multimodal learning for cancer survival prediction, massive redundancy in multimodal data prevents it from extracting discriminative and compact information: (1) An extensive amount of intra-modal task-unrelated information blurs discriminability, especially for gigapixel whole slide images (WSIs) with many patches in pathology and thousands of pathways in genomic data, leading to an "intra-modal redundancy" issue. (2) Duplicated information among modalities dominates the representation of multimodal data, which makes modality-specific information prone to being ignored, resulting in an "inter-modal redundancy" issue. To address these, we propose a new framework, Prototypical Information Bottlenecking and Disentangling (PIBD), consisting of Prototypical Information Bottleneck (PIB) module for intra-modal redundancy and Prototypical Information Disentanglement (PID) module for inter-modal redundancy. Specifically, a variant of information bottleneck, PIB, is proposed to model prototypes approximating a bunch of instances for different risk levels, which can be used for selection of discriminative instances within modality. PID module decouples entangled multimodal data into compact distinct components: modality-common and modality-specific knowledge, under the guidance of the joint prototypical distribution. Extensive experiments on five cancer benchmark datasets demonstrated our superiority over other methods. The code is released.

High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing. However, due to the high memory costs, existing dense pixel-to-pixel harmonization methods are mainly focusing on processing low-resolution (LR) images. Some recent works resort to combining with color-to-color transformations but are either limited to certain resolutions or heavily depend on hand-crafted image filters. In this work, we explore leveraging the implicit neural representation (INR) and propose a novel image Harmonization method based on Implicit neural Networks (HINet), which to the best of our knowledge, is the first dense pixel-to-pixel method applicable to HR images without any hand-crafted filter design. Inspired by the Retinex theory, we decouple the MLPs into two parts to respectively capture the content and environment of composite images. A Low-Resolution Image Prior (LRIP) network is designed to alleviate the Boundary Inconsistency problem, and we also propose new designs for the training and inference process. Extensive experiments have demonstrated the effectiveness of our method compared with state-of-the-art methods. Furthermore, some interesting and practical applications of the proposed method are explored. Our code is available at https://github.com/WindVChen/INR-Harmonization.

In contrast to digital image adversarial attacks, adversarial patch attacks involve physical operations that project crafted perturbations into real-world scenarios. During the digital-to-physical transition, adversarial patches inevitably undergo information distortion. Existing approaches focus on data augmentation and printer color gamut regularization to improve the generalization of adversarial patches to the physical world. However, these efforts overlook a critical issue within the adversarial patch crafting pipeline—namely, the significant disparity between the appearance of adversarial patches during the digital optimization phase and their manifestation in the physical world. This unexplored concern, termed “Digital-to-Physical Visual Inconsistency", introduces inconsistent objectives between the digital and physical realms, potentially skewing optimization directions for adversarial patches. To tackle this challenge, we propose a novel harmonization-based adversarial patch attack. Our approach involves the design of a self-supervised harmonization method, seamlessly integrated into the adversarial patch generation pipeline. This integration aligns the appearance of adversarial patches overlaid on digital images with the imaging environment of the background, ensuring a consistent optimization direction with the primary physical attack goal. We validate our method through extensive testing on the aerial object detection task. To enhance the controllability of environmental factors for method evaluation, we construct a dataset of 3D simulated scenarios using a graphics rendering engine. Extensive experiments on these scenarios demonstrate the efficacy of our approach. Our code and dataset are publicly accessible at https://github.com/WindVChen/VCO-AP.

Big urban trajectory exploration extracts insights from trajectories. It has many smart-city applications, e.g., traffic jam detection, taxi movement pattern analysis. The challenges of big urban trajectory data exploration are: (i) the data analysts probably do not have experience or knowledge on issuing their analysis tasks by SQL-like queries or analysis operations accurately; and (ii) big urban trajectory data is naturally complex, e.g., unpredictability, interrelation, etc. In this work, we architect and implement a visualization-assisted big urban trajectory data exploration system (Vaiet) to address these chanllenges. Vaiet includes three layers, from data collection to results visualization. We devise novel visualization views in Vaiet to support interactive big urban trajectory exploratory analysis. We demonstrate the effectiveness of Vaiet by the real world applications.