Qiang Zhai

Yao Du, Qiang Zhai, Weihang Dai et al.

Ordinal regression is a fundamental problem within the field of computer vision, with customised well-trained models on specific tasks. While pre-trained vision-language models (VLMs) have exhibited impressive performance on various vision tasks, their potential for ordinal regression has received less exploration. In this study, we first investigate CLIP's potential for ordinal regression, from which we expect the model could generalise to different ordinal regression tasks and scenarios. Unfortunately, vanilla CLIP fails on this task, since current VLMs have a well-documented limitation of encapsulating compositional concepts such as number sense. We propose a simple yet effective method called NumCLIP to improve the quantitative understanding of VLMs. We disassemble the exact image to number-specific text matching problem into coarse classification and fine prediction stages. We discretize and phrase each numerical bin with common language concept to better leverage the available pre-trained alignment in CLIP. To consider the inherent continuous property of ordinal regression, we propose a novel fine-grained cross-modal ranking-based regularisation loss specifically designed to keep both semantic and ordinal alignment in CLIP's feature space. Experimental results on three general ordinal regression tasks demonstrate the effectiveness of NumCLIP, with 10% and 3.83% accuracy improvement on historical image dating and image aesthetics assessment task, respectively. Code is publicly available at https://github.com/xmed-lab/NumCLIP.

Jianwei Zhao, Xin Li, Fan Yang et al.

Detecting objects seamlessly blended into their surroundings represents a complex task for both human cognitive capabilities and advanced artificial intelligence algorithms. Currently, the majority of methodologies for detecting camouflaged objects mainly focus on utilizing discriminative models with various unique designs. However, it has been observed that generative models, such as Stable Diffusion, possess stronger capabilities for understanding various objects in complex environments; Yet their potential for the cognition and detection of camouflaged objects has not been extensively explored. In this study, we present a novel denoising diffusion model, namely FocusDiffuser, to investigate how generative models can enhance the detection and interpretation of camouflaged objects. We believe that the secret to spotting camouflaged objects lies in catching the subtle nuances in details. Consequently, our FocusDiffuser innovatively integrates specialized enhancements, notably the Boundary-Driven LookUp (BDLU) module and Cyclic Positioning (CP) module, to elevate standard diffusion models, significantly boosting the detail-oriented analytical capabilities. Our experiments demonstrate that FocusDiffuser, from a generative perspective, effectively addresses the challenge of camouflaged object detection, surpassing leading models on benchmarks like CAMO, COD10K and NC4K.

Jianwei Zhao, Qiang Zhai, Pengbo Zhao et al.

Geolocation is a fundamental component of route planning and navigation for unmanned vehicles, but GNSS-based geolocation fails under denial-of-service conditions. Cross-view geo-localization (CVGL), which aims to estimate the geographical location of the ground-level camera by matching against enormous geo-tagged aerial (\emph{e.g.}, satellite) images, has received lots of attention but remains extremely challenging due to the drastic appearance differences across aerial-ground views. In existing methods, global representations of different views are extracted primarily using Siamese-like architectures, but their interactive benefits are seldom taken into account. In this paper, we present a novel approach using cross-view knowledge generative techniques in combination with transformers, namely mutual generative transformer learning (MGTL), for CVGL. Specifically, by taking the initial representations produced by the backbone network, MGTL develops two separate generative sub-modules -- one for aerial-aware knowledge generation from ground-view semantics and vice versa -- and fully exploits the entirely mutual benefits through the attention mechanism. Moreover, to better capture the co-visual relationships between aerial and ground views, we introduce a cascaded attention masking algorithm to further boost accuracy. Extensive experiments on challenging public benchmarks, \emph{i.e.}, {CVACT} and {CVUSA}, demonstrate the effectiveness of the proposed method which sets new records compared with the existing state-of-the-art models.

Haoming Chen, Xiaohui Zhong, Qiang Zhai et al.

Accurate nowcasting of convective clouds from satellite imagery is essential for mitigating the impacts of meteorological disasters, especially in developing countries and remote regions with limited ground-based observations. Recent advances in deep learning have shown promise in video prediction; however, existing models frequently produce blurry results and exhibit reduced accuracy when forecasting physical fields. Here, we introduce SATcast, a diffusion model that leverages a cascade architecture and multimodal inputs for nowcasting cloud fields in satellite imagery. SATcast incorporates physical fields predicted by FuXi, a deep-learning weather model, alongside past satellite observations as conditional inputs to generate high-quality future cloud fields. Through comprehensive evaluation, SATcast outperforms conventional methods on multiple metrics, demonstrating its superior accuracy and robustness. Ablation studies underscore the importance of its multimodal design and the cascade architecture in achieving reliable predictions. Notably, SATcast maintains predictive skill for up to 24 hours, underscoring its potential for operational nowcasting applications.

Jianwei Zhao, Xin Li, Fan Yang et al.

Whole Slide Image (WSI) classification poses unique challenges due to the vast image size and numerous non-informative regions, which introduce noise and cause data imbalance during feature aggregation. To address these issues, we propose MExD, an Expert-Infused Diffusion Model that combines the strengths of a Mixture-of-Experts (MoE) mechanism with a diffusion model for enhanced classification. MExD balances patch feature distribution through a novel MoE-based aggregator that selectively emphasizes relevant information, effectively filtering noise, addressing data imbalance, and extracting essential features. These features are then integrated via a diffusion-based generative process to directly yield the class distribution for the WSI. Moving beyond conventional discriminative approaches, MExD represents the first generative strategy in WSI classification, capturing fine-grained details for robust and precise results. Our MExD is validated on three widely-used benchmarks-Camelyon16, TCGA-NSCLC, and BRACS consistently achieving state-of-the-art performance in both binary and multi-class tasks.

Qiang Zhai, Xin Li, Fan Yang et al.

Automatically detecting/segmenting object(s) that blend in with their surroundings is difficult for current models. A major challenge is that the intrinsic similarities between such foreground objects and background surroundings make the features extracted by deep model indistinguishable. To overcome this challenge, an ideal model should be able to seek valuable, extra clues from the given scene and incorporate them into a joint learning framework for representation co-enhancement. With this inspiration, we design a novel Mutual Graph Learning (MGL) model, which generalizes the idea of conventional mutual learning from regular grids to the graph domain. Specifically, MGL decouples an image into two task-specific feature maps -- one for roughly locating the target and the other for accurately capturing its boundary details -- and fully exploits the mutual benefits by recurrently reasoning their high-order relations through graphs. Importantly, in contrast to most mutual learning approaches that use a shared function to model all between-task interactions, MGL is equipped with typed functions for handling different complementary relations to maximize information interactions. Experiments on challenging datasets, including CHAMELEON, CAMO and COD10K, demonstrate the effectiveness of our MGL with superior performance to existing state-of-the-art methods.

Qiang Zhai

With the maturity of Artificial Intelligence (AI) technology, Large Scale Visual Geo-Localization (LSVGL) is increasingly important in urban computing, where the task is to accurately and efficiently recognize the geo-location of a given query image. The main challenge of LSVGL faced by many experiments due to the appearance of real-word places may differ in various ways. While perspective deviation almost inevitably exists between training images and query images because of the arbitrary perspective. To cope with this situation, in this paper, we in-depth analyze the limitation of triplet loss which is the most commonly used metric learning loss in state-of-the-art LSVGL framework, and propose a new QUInTuplet Loss (QUITLoss) by embedding all the potential positive samples to the primitive triplet loss. Extensive experiments have been conducted to verify the effectiveness of the proposed approach and the results demonstrate that our new loss can enhance various LSVGL methods.