Haifeng Zhao

Leilei Ma, Dengdi Sun, Lei Wang et al.

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on modeling label relationships with graph and understanding object regions using class activation maps (CAM). However, these methods ignore the complex intra- and inter-category relationships among specific semantic features, and CAM is prone to generate noisy information. To this end, we propose a novel semantic-aware dual contrastive learning framework that incorporates sample-to-sample contrastive learning (SSCL) as well as prototype-to-sample contrastive learning (PSCL). Specifically, we leverage semantic-aware representation learning to extract category-related local discriminative features and construct category prototypes. Then based on SSCL, label-level visual representations of the same category are aggregated together, and features belonging to distinct categories are separated. Meanwhile, we construct a novel PSCL module to narrow the distance between positive samples and category prototypes and push negative samples away from the corresponding category prototypes. Finally, the discriminative label-level features related to the image content are accurately captured by the joint training of the above three parts. Experiments on five challenging large-scale public datasets demonstrate that our proposed method is effective and outperforms the state-of-the-art methods. Code and supplementary materials are released on https://github.com/yu-gi-oh-leilei/SADCL.

Songsong Wu, Hao Tang, Xiao-Yuan Jing et al.

In this paper, we tackle the problem of synthesizing a ground-view panorama image conditioned on a top-view aerial image, which is a challenging problem due to the large gap between the two image domains with different view-points. Instead of learning cross-view mapping in a feedforward pass, we propose a novel adversarial feedback GAN framework named PanoGAN with two key components: an adversarial feedback module and a dual branch discrimination strategy. First, the aerial image is fed into the generator to produce a target panorama image and its associated segmentation map in favor of model training with layout semantics. Second, the feature responses of the discriminator encoded by our adversarial feedback module are fed back to the generator to refine the intermediate representations, so that the generation performance is continually improved through an iterative generation process. Third, to pursue high-fidelity and semantic consistency of the generated panorama image, we propose a pixel-segmentation alignment mechanism under the dual branch discrimiantion strategy to facilitate cooperation between the generator and the discriminator. Extensive experimental results on two challenging cross-view image datasets show that PanoGAN enables high-quality panorama image generation with more convincing details than state-of-the-art approaches. The source code and trained models are available at \url{https://github.com/sswuai/PanoGAN}.

Deyin Liu, Lin Wu, Haifeng Zhao et al.

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples that are crafted with imperceptible perturbations, i.e., a small change in an input image can induce a mis-classification, and thus threatens the reliability of deep learning based deployment systems. Adversarial training (AT) is often adopted to improve robustness through training a mixture of corrupted and clean data. However, most of AT based methods are ineffective in dealing with transferred adversarial examples which are generated to fool a wide spectrum of defense models, and thus cannot satisfy the generalization requirement raised in real-world scenarios. Moreover, adversarially training a defense model in general cannot produce interpretable predictions towards the inputs with perturbations, whilst a highly interpretable robust model is required by different domain experts to understand the behaviour of a DNN. In this work, we propose a novel approach based on Jacobian norm and Selective Input Gradient Regularization (J-SIGR), which suggests the linearized robustness through Jacobian normalization and also regularizes the perturbation-based saliency maps to imitate the model's interpretable predictions. As such, we achieve both the improved defense and high interpretability of DNNs. Finally, we evaluate our method across different architectures against powerful adversarial attacks. Experiments demonstrate that the proposed J-SIGR confers improved robustness against transferred adversarial attacks, and we also show that the predictions from the neural network are easy to interpret.

Sachith Seneviratne, Jasper S. Wijnands, Kerry Nice et al.

Analysis of overhead imagery using computer vision is a problem that has received considerable attention in academic literature. Most techniques that operate in this space are both highly specialised and require expensive manual annotation of large datasets. These problems are addressed here through the development of a more generic framework, incorporating advances in representation learning which allows for more flexibility in analysing new categories of imagery with limited labeled data. First, a robust representation of an unlabeled aerial imagery dataset was created based on the momentum contrast mechanism. This was subsequently specialised for different tasks by building accurate classifiers with as few as 200 labeled images. The successful low-level detection of urban infrastructure evolution over a 10-year period from 60 million unlabeled images, exemplifies the substantial potential of our approach to advance quantitative urban research.

Leilei Ma, Hongxing Xie, Lei Wang et al.

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with missing labels, leveraging VLP prompt-tuning technology. However, they usually cannot match text and vision features well, due to complicated semantics gaps and missing labels in a multi-label image. To tackle this challenge, we propose $\textbf{T}$ext-$\textbf{R}$egion $\textbf{M}$atching for optimizing $\textbf{M}$ulti-$\textbf{L}$abel prompt tuning, namely TRM-ML, a novel method for enhancing meaningful cross-modal matching. Compared to existing methods, we advocate exploring the information of category-aware regions rather than the entire image or pixels, which contributes to bridging the semantic gap between textual and visual representations in a one-to-one matching manner. Concurrently, we further introduce multimodal contrastive learning to narrow the semantic gap between textual and visual modalities and establish intra-class and inter-class relationships. Additionally, to deal with missing labels, we propose a multimodal category prototype that leverages intra- and inter-category semantic relationships to estimate unknown labels, facilitating pseudo-label generation. Extensive experiments on the MS-COCO, PASCAL VOC, Visual Genome, NUS-WIDE, and CUB-200-211 benchmark datasets demonstrate that our proposed framework outperforms the state-of-the-art methods by a significant margin. Our code is available here: https://github.com/yu-gi-oh-leilei/TRM-ML.

Bo Cheng, Jueqing Lu, Yuan Tian et al.

Semi-supervised learning (SSL) has garnered significant attention due to its ability to leverage limited labeled data and a large amount of unlabeled data to improve model generalization performance. Recent approaches achieve impressive successes by combining ideas from both consistency regularization and pseudo-labeling. However, these methods tend to underperform in the more realistic situations with relatively scarce labeled data. We argue that this issue arises because existing methods rely solely on the model's confidence, making them challenging to accurately assess the model's state and identify unlabeled examples contributing to the training phase when supervision information is limited, especially during the early stages of model training. In this paper, we propose a novel SSL model called CGMatch, which, for the first time, incorporates a new metric known as Count-Gap (CG). We demonstrate that CG is effective in discovering unlabeled examples beneficial for model training. Along with confidence, a commonly used metric in SSL, we propose a fine-grained dynamic selection (FDS) strategy. This strategy dynamically divides the unlabeled dataset into three subsets with different characteristics: easy-to-learn set, ambiguous set, and hard-to-learn set. By selective filtering subsets, and applying corresponding regularization with selected subsets, we mitigate the negative impact of incorrect pseudo-labels on model optimization and generalization. Extensive experimental results on several common SSL benchmarks indicate the effectiveness of CGMatch especially when the labeled data are particularly limited. Source code is available at https://github.com/BoCheng-96/CGMatch.

Haifeng Zhao, Lixiang Jiang, Leilei Ma et al.

Medical images from different healthcare centers exhibit varied data distributions, posing significant challenges for adapting lung nodule detection due to the domain shift between training and application phases. Traditional unsupervised domain adaptive detection methods often struggle with this shift, leading to suboptimal outcomes. To overcome these challenges, we introduce a novel domain adaptive approach for lung nodule detection that leverages mean teacher self-training and contrastive learning. First, we propose a hierarchical contrastive learning strategy to refine nodule representations and enhance the distinction between nodules and background. Second, we introduce a nodule-level domain-invariant feature learning (NDL) module to capture domain-invariant features through adversarial learning across different domains. Additionally, we propose a new annotated dataset of X-ray images to aid in advancing lung nodule detection research. Extensive experiments conducted on multiple X-ray datasets demonstrate the efficacy of our approach in mitigating domain shift impacts.

Haifeng Zhao, Yuguang Jin, Leilei Ma

Significant advancements have been made in single label incremental learning (SLCIL),yet the more practical and challenging multi label class incremental learning (MLCIL) remains understudied. Recently,visual language models such as CLIP have achieved good results in classification tasks. However,directly using CLIP to solve MLCIL issue can lead to catastrophic forgetting. To tackle this issue, we integrate an improved data replay mechanism and prompt loss to curb knowledge forgetting. Specifically,our model enhances the prompt information to better adapt to multi-label classification tasks and employs confidence-based replay strategy to select representative samples. Moreover, the prompt loss significantly reduces the model's forgetting of previous knowledge. Experimental results demonstrate that our method has substantially improved the performance of MLCIL tasks across multiple benchmark datasets,validating its effectiveness.

LeiLei Ma, Shuo Xu, MingKun Xie et al.

Modeling label correlations has always played a pivotal role in multi-label image classification (MLC), attracting significant attention from researchers. However, recent studies have overemphasized co-occurrence relationships among labels, which can lead to overfitting risk on this overemphasis, resulting in suboptimal models. To tackle this problem, we advocate for balancing correlative and discriminative relationships among labels to mitigate the risk of overfitting and enhance model performance. To this end, we propose the Multi-Label Visual Prompt Tuning framework, a novel and parameter-efficient method that groups classes into multiple class subsets according to label co-occurrence and mutual exclusivity relationships, and then models them respectively to balance the two relationships. In this work, since each group contains multiple classes, multiple prompt tokens are adopted within Vision Transformer (ViT) to capture the correlation or discriminative label relationship within each group, and effectively learn correlation or discriminative representations for class subsets. On the other hand, each group contains multiple group-aware visual representations that may correspond to multiple classes, and the mixture of experts (MoE) model can cleverly assign them from the group-aware to the label-aware, adaptively obtaining label-aware representation, which is more conducive to classification. Experiments on multiple benchmark datasets show that our proposed approach achieves competitive results and outperforms SOTA methods on multiple pre-trained models.

Xue Han, Haodong Yao, Fei Zhan et al.

X-ray absorption spectroscopy (XAS) is a powerful technique to probe the electronic and structural properties of materials. With the rapid growth in both the volume and complexity of XAS datasets driven by advancements in synchrotron radiation facilities, there is an increasing demand for advanced computational tools capable of efficiently analyzing large-scale data. To address these needs, we introduce XASDAML,a flexible, machine learning based framework that integrates the entire data-processing workflow-including dataset construction for spectra and structural descriptors, data filtering, ML modeling, prediction, and model evaluation-into a unified platform. Additionally, it supports comprehensive statistical analysis, leveraging methods such as principal component analysis and clustering to reveal potential patterns and relationships within large datasets. Each module operates independently, allowing users to modify or upgrade modules in response to evolving research needs or technological advances. Moreover, the platform provides a user-friendly interface via Jupyter Notebook, making it accessible to researchers at varying levels of expertise. The versatility and effectiveness of XASDAML are exemplified by its application to a copper dataset, where it efficiently manages large and complex data, supports both supervised and unsupervised machine learning models, provides comprehensive statistics for structural descriptors, generates spectral plots, and accurately predicts coordination numbers and bond lengths. Furthermore, the platform streamlining the integration of XAS with machine learning and lowering the barriers to entry for new users.

Huanli Zhuo, Leilei Ma, Haifeng Zhao et al.

Although SAM-based single-source domain generalization models for medical image segmentation can mitigate the impact of domain shift on the model in cross-domain scenarios, these models still face two major challenges. First, the segmentation of SAM is highly dependent on domain-specific expert-annotated prompts, which prevents SAM from achieving fully automated medical image segmentation and therefore limits its application in clinical settings. Second, providing poor prompts (such as bounding boxes that are too small or too large) to the SAM prompt encoder can mislead SAM into generating incorrect mask results. Therefore, we propose the FA-SAM, a single-source domain generalization framework for medical image segmentation that achieves fully automated SAM. FA-SAM introduces two key innovations: an Auto-prompted Generation Model (AGM) branch equipped with a Shallow Feature Uncertainty Modeling (SUFM) module, and an Image-Prompt Embedding Fusion (IPEF) module integrated into the SAM mask decoder. Specifically, AGM models the uncertainty distribution of shallow features through the SUFM module to generate bounding box prompts for the target domain, enabling fully automated segmentation with SAM. The IPEF module integrates multiscale information from SAM image embeddings and prompt embeddings to capture global and local details of the target object, enabling SAM to mitigate the impact of poor prompts. Extensive experiments on publicly available prostate and fundus vessel datasets validate the effectiveness of FA-SAM and highlight its potential to address the above challenges.

Haifeng Zhao, Yufei Zhang, Leilei Ma et al.

Radiology report generation represents a significant application within medical AI, and has achieved impressive results. Concurrently, large language models (LLMs) have demonstrated remarkable performance across various domains. However, empirical validation indicates that general LLMs tend to focus more on linguistic fluency rather than clinical effectiveness, and lack the ability to effectively capture the relationship between X-ray images and their corresponding texts, thus resulting in poor clinical practicability. To address these challenges, we propose Optimal Transport-Driven Radiology Report Generation (OTDRG), a novel framework that leverages Optimal Transport (OT) to align image features with disease labels extracted from reports, effectively bridging the cross-modal gap. The core component of OTDRG is Alignment \& Fine-Tuning, where OT utilizes results from the encoding of label features and image visual features to minimize cross-modal distances, then integrating image and text features for LLMs fine-tuning. Additionally, we design a novel disease prediction module to predict disease labels contained in X-ray images during validation and testing. Evaluated on the MIMIC-CXR and IU X-Ray datasets, OTDRG achieves state-of-the-art performance in both natural language generation (NLG) and clinical efficacy (CE) metrics, delivering reports that are not only linguistically coherent but also clinically accurate.

Shiwei Zhou, Xin Liu, Haifeng Zhao et al.

In semi-supervised medical image segmentation, the poor quality of unlabeled data and the uncertainty in the model's predictions lead to models that inevitably produce erroneous pseudo-labels. These errors accumulate throughout model training, thereby weakening the model's performance. We found that these erroneous pseudo-labels are typically concentrated in high-uncertainty regions. Traditional methods improve performance by directly discarding pseudo-labels in these regions, which can also result in neglecting potentially valuable training data. To alleviate this problem, we propose a bidirectional uncertainty-aware region learning strategy to fully utilize the precise supervision provided by labeled data and stabilize the training of unlabeled data. Specifically, in the training labeled data, we focus on high-uncertainty regions, using precise label information to guide the model's learning in potentially uncontrollable areas. Meanwhile, in the training of unlabeled data, we concentrate on low-uncertainty regions to reduce the interference of erroneous pseudo-labels on the model. Through this bidirectional learning strategy, the model's overall performance has significantly improved. Extensive experiments show that our proposed method achieves significant performance improvement on different medical image segmentation tasks.

Jasper S. Wijnands, Haifeng Zhao, Kerry A. Nice et al.

The World Health Organization has listed the design of safer intersections as a key intervention to reduce global road trauma. This article presents the first study to systematically analyze the design of all intersections in a large country, based on aerial imagery and deep learning. Approximately 900,000 satellite images were downloaded for all intersections in Australia and customized computer vision techniques emphasized the road infrastructure. A deep autoencoder extracted high-level features, including the intersection's type, size, shape, lane markings, and complexity, which were used to cluster similar designs. An Australian telematics data set linked infrastructure design to driving behaviors captured during 66 million kilometers of driving. This showed more frequent hard acceleration events (per vehicle) at four- than three-way intersections, relatively low hard deceleration frequencies at T-intersections, and consistently low average speeds on roundabouts. Overall, domain-specific feature extraction enabled the identification of infrastructure improvements that could result in safer driving behaviors, potentially reducing road trauma.

Kerry A. Nice, Jasper S. Wijnands, Ariane Middel et al.

Computer vision techniques enable automated detection of sky pixels in outdoor imagery. In urban climate, sky detection is an important first step in gathering information about urban morphology and sky view factors. However, obtaining accurate results remains challenging and becomes even more complex using imagery captured under a variety of lighting and weather conditions. To address this problem, we present a new sky pixel detection system demonstrated to produce accurate results using a wide range of outdoor imagery types. Images are processed using a selection of mean-shift segmentation, K-means clustering, and Sobel filters to mark sky pixels in the scene. The algorithm for a specific image is chosen by a convolutional neural network, trained with 25,000 images from the Skyfinder data set, reaching 82% accuracy for the top three classes. This selection step allows the sky marking to follow an adaptive process and to use different techniques and parameters to best suit a particular image. An evaluation of fourteen different techniques and parameter sets shows that no single technique can perform with high accuracy across varied Skyfinder and Google Street View data sets. However, by using our adaptive process, large increases in accuracy are observed. The resulting system is shown to perform better than other published techniques.

Jasper S. Wijnands, Kerry A. Nice, Jason Thompson et al.

Deep learning using neural networks has provided advances in image style transfer, merging the content of one image (e.g., a photo) with the style of another (e.g., a painting). Our research shows this concept can be extended to analyse the design of streetscapes in relation to health and wellbeing outcomes. An Australian population health survey (n=34,000) was used to identify the spatial distribution of health and wellbeing outcomes, including general health and social capital. For each outcome, the most and least desirable locations formed two domains. Streetscape design was sampled using around 80,000 Google Street View images per domain. Generative adversarial networks translated these images from one domain to the other, preserving the main structure of the input image, but transforming the `style' from locations where self-reported health was bad to locations where it was good. These translations indicate that areas in Melbourne with good general health are characterised by sufficient green space and compactness of the urban environment, whilst streetscape imagery related to high social capital contained more and wider footpaths, fewer fences and more grass. Beyond identifying relationships, the method is a first step towards computer-generated design interventions that have the potential to improve population health and wellbeing.