Fine-grained image analysis is widely recognized as highly challenging, since distinguishing individual differences within a certain category, species, or type often depends on tiny, subtle patterns. However, learning fine-grained semantic categories from these subtle part patterns is inherently fragile, as they can easily be overwhelmed by the dominant patterns resting in the coarse-category information. Therefore, how to enhance the relation between the fine-grained semantics and these subtle patterns is the key. To push this frontier, a novel semantic-part alignment (SPA) learning scheme is proposed in this paper. Its general idea is to firstly measure the relevance of each part to the fine-grained semantics, and then regularize the fine-grained visual representation learning. Specifically, it consists of three key components, namely, joint semantic-part modeling, semantic-part set modeling, and optimal semantic-part transport. The joint semantic-part modeling associates each part in an image with the fine-grained semantics in a latent space. Then, the optimal semantic-part transport component is devised to enhance the relation between fine-grained semantic embeddings and the discriminative part embeddings. Notably, the proposed SPA is plug-in-and-play, easy-to-implement, and insensitive to the latent embedding dimension and loss weight. Experiments show the proposed method can substantially boost performance on multiple fine-grained image analysis tasks across various baselines.

Domain generalization aims to learn a representation from the source domain, which can be generalized to arbitrary unseen target domains. A fundamental challenge for visual domain generalization is the domain gap caused by the dramatic style variation whereas the image content is stable. The realm of selective state space, exemplified by VMamba, demonstrates its global receptive field in representing the content. However, the way exploiting the domain-invariant property for selective state space is rarely explored. In this paper, we propose a novel Flow Factorized State Space model, dubbed as DGFamba, for visual domain generalization. To maintain domain consistency, we innovatively map the style-augmented and the original state embeddings by flow factorization. In this latent flow space, each state embedding from a certain style is specified by a latent probability path. By aligning these probability paths in the latent space, the state embeddings are able to represent the same content distribution regardless of the style differences. Extensive experiments conducted on various visual domain generalization settings show its state-of-the-art performance.

Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains when only trained on the source domain data. Compared with generic domain generalization, FGDG is particularly challenging in that the fine-grained category can be only discerned by some subtle and tiny patterns. Such patterns are particularly fragile under the cross-domain style shifts caused by illumination, color and etc. To push this frontier, this paper presents a novel Hyperbolic State Space Hallucination (HSSH) method. It consists of two key components, namely, state space hallucination (SSH) and hyperbolic manifold consistency (HMC). SSH enriches the style diversity for the state embeddings by firstly extrapolating and then hallucinating the source images. Then, the pre- and post- style hallucinate state embeddings are projected into the hyperbolic manifold. The hyperbolic state space models the high-order statistics, and allows a better discernment of the fine-grained patterns. Finally, the hyperbolic distance is minimized, so that the impact of style variation on fine-grained patterns can be eliminated. Experiments on three FGDG benchmarks demonstrate its state-of-the-art performance.

Night-time scene segmentation is a critical yet challenging task in the real-world applications, primarily due to the complicated lighting conditions. However, existing methods lack sufficient generalization ability to unseen nighttime scenes with varying illumination. In light of this issue, we focus on investigating generalizable paradigms for night-time scene segmentation and propose an efficient fine-tuning scheme, dubbed NightAdapter, alleviating the domain gap across various scenes. Interestingly, different properties embedded in the day-time and night-time features can be characterized by the bands after discrete sine transform, which can be categorized into illumination-sensitive/-insensitive bands. Hence, our NightAdapter is powered by two appealing designs: (1) Illumination-Insensitive Band Adaptation that provides a foundation for understanding the prior, enhancing the robustness to illumination shifts; (2) Illumination-Sensitive Band Adaptation that fine-tunes the randomized frequency bands, mitigating the domain gap between the day-time and various night-time scenes. As a consequence, illumination-insensitive enhancement improves the domain invariance, while illumination-sensitive diminution strengthens the domain shift between different scenes. NightAdapter yields significant improvements over the state-of-the-art methods under various day-to-night, night-to-night, and in-domain night segmentation experiments. Source code is available at https://github.com/BiQiWHU/NightAdapter.

Image restoration is a fundamental task in computer vision and machine learning, which learns a mapping between the clear images and the degraded images under various conditions (e.g., blur, low-light, haze). Yet, most existing image restoration methods are highly restricted by the requirement of degraded and clear image pairs, which limits the generalization and feasibility to enormous real-world scenarios without paired images. To address this bottleneck, we propose a Degradation-aware Dynamic Schr\"{o}dinger Bridge (DDSB) for unpaired image restoration. Its general idea is to learn a Schr\"{o}dinger Bridge between clear and degraded image distribution, while at the same time emphasizing the physical degradation priors to reduce the accumulation of errors during the restoration process. A Degradation-aware Optimal Transport (DOT) learning scheme is accordingly devised. Training a degradation model to learn the inverse restoration process is particularly challenging, as it must be applicable across different stages of the iterative restoration process. A Dynamic Transport with Consistency (DTC) learning objective is further proposed to reduce the loss of image details in the early iterations and therefore refine the degradation model. Extensive experiments on multiple image degradation tasks show its state-of-the-art performance over the prior arts.

Domain generalization aims to train models that perform robustly on unseen target domains without access to target data. The realm of vision-language foundation model has opened a new venue owing to its inherent out-of-distribution generalization capability. However, the static alignment to class-level textual anchors remains insufficient to handle the dramatic distribution discrepancy from diverse domain-specific visual features. In this work, we propose a novel cross-domain Schrödinger Bridge (SB) method, namely SBGen, to handle this challenge, which explicitly formulates the stochastic semantic evolution, to gain better generalization to unseen domains. Technically, the proposed \texttt{SBGen} consists of three key components: (1) \emph{text-guided domain-aware feature selection} to isolate semantically aligned image tokens; (2) \emph{stochastic cross-domain evolution} to simulate the SB dynamics via a learnable time-conditioned drift; and (3) \emph{stochastic domain-agnostic interpolation} to construct semantically grounded feature trajectories. Empirically, \texttt{SBGen} achieves state-of-the-art performance on domain generalization in both classification and segmentation. This work highlights the importance of modeling domain shifts as structured stochastic processes grounded in semantic alignment.

Medical images are usually collected from multiple clinical centers with various types of scanners. When confronted with such significant cross-domain distribution discrepancy, a deep network tends to capture similar patterns by multiple channels, while different cross-domain patterns are also allowed to rest in the same channel. Such channel redundancy limits the expressive capability of a representation, resulting in less preferable generalization ability. To address this fundamental yet challenging issue, we propose a novel decoupled feature as query (DFQ) framework for domain generalized medical image representation learning. Its general idea is to leverage the channel-wise decoupled deep features as queries. Particularly, a deep instance whitening transform with restricted isometry is proposed, which enforces each channel orthogonal to the rest channels after decoupling. Besides, the long-range dependency between decoupled deep and shallow features is implicitly constrained to minimize channel redundancy throughout training. Extensive experiments show its state-of-the-art performance on three medical domain generalization tasks with four modalities.

High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g., species, brands) by self-supervised learning becomes a feasible solution. However, recent investigations find that existing self-supervised learning methods are less qualified to represent fine-grained categories. The bottleneck lies in that the pre-trained class-agnostic representation is built from every patch-wise embedding, while fine-grained categories are only determined by several key patches of an image. In this paper, we propose a Cross-level Multi-instance Distillation (CMD) framework to tackle this challenge. Our key idea is to consider the importance of each image patch in determining the fine-grained representation by multiple instance learning. To comprehensively learn the relation between informative patches and fine-grained semantics, the multi-instance knowledge distillation is implemented on both the region/image crop pairs from the teacher and student net, and the region-image crops inside the teacher / student net, which we term as intra-level multi-instance distillation and inter-level multi-instance distillation. Extensive experiments on several commonly used datasets, including CUB-200-2011, Stanford Cars and FGVC Aircraft, demonstrate that the proposed method outperforms the contemporary methods by up to 10.14% and existing state-of-the-art self-supervised learning approaches by up to 19.78% on both top-1 accuracy and Rank-1 retrieval metric. Source code is available at https://github.com/BiQiWHU/CMD.

Domain generalized medical image segmentation requires models to learn from multiple source domains and generalize well to arbitrary unseen target domain. Such a task is both technically challenging and clinically practical, due to the domain shift problem (i.e., images are collected from different hospitals and scanners). Existing methods focused on either learning shape-invariant representation or reaching consensus among the source domains. An ideal generalized representation is supposed to show similar pattern responses within the same channel for cross-domain images. However, to deal with the significant distribution discrepancy, the network tends to capture similar patterns by multiple channels, while different cross-domain patterns are also allowed to rest in the same channel. To address this issue, we propose to leverage channel-wise decoupled deep features as queries. With the aid of cross-attention mechanism, the long-range dependency between deep and shallow features can be fully mined via self-attention and then guides the learning of generalized representation. Besides, a relaxed deep whitening transformation is proposed to learn channel-wise decoupled features in a feasible way. The proposed decoupled fea- ture query (DFQ) scheme can be seamlessly integrate into the Transformer segmentation model in an end-to-end manner. Extensive experiments show its state-of-the-art performance, notably outperforming the runner-up by 1.31% and 1.98% with DSC metric on generalized fundus and prostate benchmarks, respectively. Source code is available at https://github.com/BiQiWHU/DFQ.

The rapid development of intelligent systems for eye disease diagnosis decreases the risk of people suffering from vision impairment. However, the superior discrimination ability of existing retinal disease diagnosis methods heavily relies on the large-scale high-quality annotations. In this work, we adapt the self-supervised technique for fundus image classification with the merits of bypassing the over-dependence of labeled data. Unlike most current self-supervised approaches, which only learn global pre-text representations from view-level, our method further incorporates the region-level representations into the learning process, since the pathological changes in fundus images are usually subtle and scattered. Specifically, we propose a novel self-supervised cross-level consistency learning scheme (S2C2L), which leverages both view-level and region-level representations of a vision Transformer to improve the robustness of extracted self-supervised representation. A diagnosis perception module (DPM) is constructed to enhance the activation of local pathological regions from both region and view levels, and a cross-level consistency loss is dedicated to align the representations from both levels. Extensive experiments on iChallenge-AMD, LAG and APTOS2019 datasets validate the state-of-the-art performance of our method for three common eye diseases.

The rapid development of Vision Foundation Model (VFM) brings inherent out-domain generalization for a variety of down-stream tasks. Among them, domain generalized semantic segmentation (DGSS) holds unique challenges as the cross-domain images share common pixel-wise content information but vary greatly in terms of the style. In this paper, we present a novel Spectral-dEcomposed Token (SET) learning framework to advance the frontier. Delving into further than existing fine-tuning token & frozen backbone paradigm, the proposed SET especially focuses on the way learning style-invariant features from these learnable tokens. Particularly, the frozen VFM features are first decomposed into the phase and amplitude components in the frequency space, which mainly contain the information of content and style, respectively, and then separately processed by learnable tokens for task-specific information extraction. Particularly, the frozen VFM features are first decomposed into the phase and amplitude components in the frequency space, which mainly contain the information of content and style, respectively, and then separately processed by learnable tokens for task-specific information extraction.After the decomposition, style variation primarily impacts the token-based feature enhancement within the amplitude branch. To address this issue, we further develop an attention optimization method to bridge the gap between style-affected representation and static tokens during inference. Extensive cross-domain experiments show its state-of-the-art performance.

Disease grading is a crucial task in medical image analysis. Due to the continuous progression of diseases, i.e., the variability within the same level and the similarity between adjacent stages, accurate grading is highly challenging. Furthermore, in real-world scenarios, models trained on limited source domain datasets should also be capable of handling data from unseen target domains. Due to the cross-domain variants, the feature distribution between source and unseen target domains can be dramatically different, leading to a substantial decrease in model performance. To address these challenges in cross-domain disease grading, we propose a Severity-aware Recurrent Modeling (Samba) method in this paper. As the core objective of most staging tasks is to identify the most severe lesions, which may only occupy a small portion of the image, we propose to encode image patches in a sequential and recurrent manner. Specifically, a state space model is tailored to store and transport the severity information by hidden states. Moreover, to mitigate the impact of cross-domain variants, an Expectation-Maximization (EM) based state recalibration mechanism is designed to map the patch embeddings into a more compact space. We model the feature distributions of different lesions through the Gaussian Mixture Model (GMM) and reconstruct the intermediate features based on learnable severity bases. Extensive experiments show the proposed Samba outperforms the VMamba baseline by an average accuracy of 23.5\%, 5.6\% and 4.1\% on the cross-domain grading of fatigue fracture, breast cancer and diabetic retinopathy, respectively. Source code is available at \url{https://github.com/BiQiWHU/Samba}.

The emerging vision foundation model (VFM) has inherited the ability to generalize to unseen images. Nevertheless, the key challenge of domain-generalized semantic segmentation (DGSS) lies in the domain gap attributed to the cross-domain styles, i.e., the variance of urban landscape and environment dependencies. Hence, maintaining the style-invariant property with varying domain styles becomes the key bottleneck in harnessing VFM for DGSS. The frequency space after Haar wavelet transformation provides a feasible way to decouple the style information from the domain-invariant content, since the content and style information are retained in the low- and high- frequency components of the space, respectively. To this end, we propose a novel Frequency-Adapted (FADA) learning scheme to advance the frontier. Its overall idea is to separately tackle the content and style information by frequency tokens throughout the learning process. Particularly, the proposed FADA consists of two branches, i.e., low- and high- frequency branches. The former one is able to stabilize the scene content, while the latter one learns the scene styles and eliminates its impact to DGSS. Experiments conducted on various DGSS settings show the state-of-the-art performance of our FADA and its versatility to a variety of VFMs. Source code is available at \url{https://github.com/BiQiWHU/FADA}.

The existing deep learning based methods have shown great potential for the aurora image classification problem. However, there are many differences in the morphology and distribution patterns of aurora images from different observation stations, and the differences between Antarctic and Arctic aurora images are particularly obvious. Currently, there are 76 research stations in 31 countries in Antarctica and more than 100 land-based stations in the Arctic. In the face of the difference in morphology and distribution patterns between Antarctic and Arctic auroras, the current popular methods cannot maintain a consistent classification ability. At the same time, it is important to effectively use both historical and real-time information to enable continual learning of aurora classification models to take full advantage of the high temporal resolution of streaming aurora image data. In this paper, a cross-station continual (CSC) aurora image classification framework is proposed to tackle these problems. To simulate a cross-station aurora image data stream, aurora images from three observation stations located in the Antarctic and the Arctic were selected and split into mini-batches in chronological order to form the cross-station streaming (CSS) aurora image dataset. Based on the vision transformer model, the CSC framework sequentially learns the semantic representation of streaming aurora data by learning dynamic prompts in the prompt bank selected by the average cosine distance. For the cross-station aurora discrepancy phenomenon, a local-global enhancement (LGE) module is designed, by organically combining the local and global semantics of aurora images to reduce the microscopic intra-class similarity and macroscopic inter-class confusion. Extensive experiments conducted on the CSS dataset show that the proposed method can achieve efficient continual learning of streaming aurora data and a competitive classification accuracy under the condition of joint training of data from multiple observation stations.

Generic image classification has been widely studied in the past decade. However, for the bird-view aerial images, aerial scene classification remains challenging due to the dramatic variation of the scale and object size. Existing methods usually learn the aerial scene representation from the convolutional neural networks (CNN), which focus on the local response of an image. In contrast, the recently-developed vision transformers (ViT) can learn stronger global representation for aerial scenes, but are not qualified enough to highlight the key objects in an aerial scene due to the dramatic size and scale variation. To address this challenge, in this paper, we propose a local-global interactive vision transformer (LG-ViT) for this task. It is based on our deliberately designed local-global feature interactive learning scheme, which intends to jointly utilize the local-wise and global-wise feature representations. To realize the learning scheme in an end-to-end manner, the proposed LG-ViT consists of three key components, namely, local-global feature extraction, local-global feature interaction, and local-global semantic constraints. Extensive experiments on three aerial scene classification benchmarks, namely, UCM, AID and NWPU, demonstrate the effectiveness of the proposed LG-ViT against the state-of-the-art methods. The effectiveness of each component and generalization capability is also validated.

Existing deep learning based methods effectively prompt the performance of aerial scene classification. However, due to the large amount of parameters and computational cost, it is rather difficult to apply these methods to multiple real-time remote sensing applications such as on-board data preception on drones and satellites. In this paper, we address this task by developing a light-weight ConvNet named multi-stage duplex fusion network (MSDF-Net). The key idea is to use parameters as little as possible while obtaining as strong as possible scene representation capability. To this end, a residual-dense duplex fusion strategy is developed to enhance the feature propagation while re-using parameters as much as possible, and is realized by our duplex fusion block (DFblock). Specifically, our MSDF-Net consists of multi-stage structures with DFblock. Moreover, duplex semantic aggregation (DSA) module is developed to mine the remote sensing scene information from extracted convolutional features, which also contains two parallel branches for semantic description. Extensive experiments are conducted on three widely-used aerial scene classification benchmarks, and reflect that our MSDF-Net can achieve a competitive performance against the recent state-of-art while reducing up to 80% parameter numbers. Particularly, an accuracy of 92.96% is achieved on AID with only 0.49M parameters.

Aerial image classification is challenging for current deep learning models due to the varied geo-spatial object scales and the complicated scene spatial arrangement. Thus, it is necessary to stress the key local feature response from a variety of scales so as to represent discriminative convolutional features. In this paper, we propose a deep multi-scale multiple instance learning (DMSMIL) framework to tackle the above challenges. Firstly, we develop a differential multi-scale dilated convolution feature extractor to exploit the different patterns from different scales. Then, the deep features of each scale are fed into a multiple instance learning module to generate a bag-level probability prediction. Lastly, probability predictions from all the MIL branches are fused to generate the final semantic prediction. Extensive experiments on three widely-utilized aerial scene classification benchmarks demonstrate that our proposed DMSMIL outperforms the state-of-the-art approaches by a large margin.