Xinge You

Yu Wang, Shuo Ye, Shujian Yu et al.

Fine-grained visual categorization (FGVC) aims to discriminate similar subcategories, whose main challenge is the large intraclass diversities and subtle inter-class differences. Existing FGVC methods usually select discriminant regions found by a trained model, which is prone to neglect other potential discriminant information. On the other hand, the massive interactions between the sequence of image patches in ViT make the resulting class-token contain lots of redundant information, which may also impacts FGVC performance. In this paper, we present a novel approach for FGVC, which can simultaneously make use of partial yet sufficient discriminative information in environmental cues and also compress the redundant information in class-token with respect to the target. Specifically, our model calculates the ratio of high-weight regions in a batch, adaptively adjusts the masking threshold and achieves moderate extraction of background information in the input space. Moreover, we also use the Information Bottleneck~(IB) approach to guide our network to learn a minimum sufficient representations in the feature space. Experimental results on three widely-used benchmark datasets verify that our approach can achieve outperforming performance than other state-of-the-art approaches and baseline models.

Yufeng Shi, Shuhuang Chen, Xinge You et al.

Mapping X-ray images, radiology reports, and other medical data as binary codes in the common space, which can assist clinicians to retrieve pathology-related data from heterogeneous modalities (i.e., hashing-based cross-modal medical data retrieval), provides a new view to promot computeraided diagnosis. Nevertheless, there remains a barrier to boost medical retrieval accuracy: how to reveal the ambiguous semantics of medical data without the distraction of superfluous information. To circumvent this drawback, we propose Deep Supervised Information Bottleneck Hashing (DSIBH), which effectively strengthens the discriminability of hash codes. Specifically, the Deep Deterministic Information Bottleneck (Yu, Yu, and Principe 2021) for single modality is extended to the cross-modal scenario. Benefiting from this, the superfluous information is reduced, which facilitates the discriminability of hash codes. Experimental results demonstrate the superior accuracy of the proposed DSIBH compared with state-of-the-arts in cross-modal medical data retrieval tasks.

Beihao Xia, Conghao Wong, Duanquan Xu et al.

With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more trajectories with different forms, such as coordinates, bounding boxes, and even high-dimensional human skeletons, need to be analyzed and forecasted. Among these heterogeneous trajectories, interactions between different elements within a frame of trajectory, which we call ``Dimension-wise Interactions'', would be more complex and challenging. However, most previous approaches focus mainly on a specific form of trajectories, and potential dimension-wise interactions are less concerned. In this work, we expand the trajectory prediction task by introducing the trajectory dimensionality $M$, thus extending its application scenarios to heterogeneous trajectories. We first introduce the Haar transform as an alternative to Fourier transform to better capture the time-frequency properties of each trajectory-dimension. Then, we adopt the bilinear structure to model and fuse two factors simultaneously, including the time-frequency response and the dimension-wise interaction, to forecast heterogeneous trajectories via trajectory spectrums hierarchically in a generic way. Experiments show that the proposed model outperforms most state-of-the-art methods on ETH-UCY, SDD, nuScenes, and Human3.6M with heterogeneous trajectories, including 2D coordinates, 2D/3D bounding boxes, and 3D human skeletons.

Sichao Fu, Qinmu Peng, Yang He et al.

In recent years, graph neural networks (GNN) have achieved significant developments in a variety of graph analytical tasks. Nevertheless, GNN's superior performance will suffer from serious damage when the collected node features or structure relationships are partially missing owning to numerous unpredictable factors. Recently emerged graph completion learning (GCL) has received increasing attention, which aims to reconstruct the missing node features or structure relationships under the guidance of a specifically supervised task. Although these proposed GCL methods have made great success, they still exist the following problems: the reliance on labels, the bias of the reconstructed node features and structure relationships. Besides, the generalization ability of the existing GCL still faces a huge challenge when both collected node features and structure relationships are partially missing at the same time. To solve the above issues, we propose a more general GCL framework with the aid of self-supervised learning for improving the task performance of the existing GNN variants on graphs with features and structure missing, termed unsupervised GCL (UGCL). Specifically, to avoid the mismatch between missing node features and structure during the message-passing process of GNN, we separate the feature reconstruction and structure reconstruction and design its personalized model in turn. Then, a dual contrastive loss on the structure level and feature level is introduced to maximize the mutual information of node representations from feature reconstructing and structure reconstructing paths for providing more supervision signals. Finally, the reconstructed node features and structure can be applied to the downstream node classification task. Extensive experiments on eight datasets, three GNN variants and five missing rates demonstrate the effectiveness of our proposed method.

Chengxiang Lei, Sichao Fu, Yuetian Wang et al.

Graph neural networks (GNNs) with missing node features have recently received increasing interest. Such missing node features seriously hurt the performance of the existing GNNs. Some recent methods have been proposed to reconstruct the missing node features by the information propagation among nodes with known and unknown attributes. Although these methods have achieved superior performance, how to exactly exploit the complex data correlations among nodes to reconstruct missing node features is still a great challenge. To solve the above problem, we propose a self-supervised guided hypergraph feature propagation (SGHFP). Specifically, the feature hypergraph is first generated according to the node features with missing information. And then, the reconstructed node features produced by the previous iteration are fed to a two-layer GNNs to construct a pseudo-label hypergraph. Before each iteration, the constructed feature hypergraph and pseudo-label hypergraph are fused effectively, which can better preserve the higher-order data correlations among nodes. After then, we apply the fused hypergraph to the feature propagation for reconstructing missing features. Finally, the reconstructed node features by multi-iteration optimization are applied to the downstream semi-supervised classification task. Extensive experiments demonstrate that the proposed SGHFP outperforms the existing semi-supervised classification with missing node feature methods.

Yuetian Wang, Wenjin Hou, Qinmu Peng et al.

Fine-grained recognition, a pivotal task in visual signal processing, aims to distinguish between similar subclasses based on discriminative information present in samples. However, prevailing methods often erroneously focus on background areas, neglecting the capture of genuinely effective discriminative information from the subject, thus impeding practical application. To facilitate research into the impact of background noise on models and enhance their ability to concentrate on the subject's discriminative features, we propose an engineered pipeline that leverages the capabilities of SAM and Detic to create fine-grained datasets with only foreground subjects, devoid of background. Extensive cross-experiments validate this approach as a preprocessing step prior to training, enhancing algorithmic performance and holding potential for further modal expansion of the data.

Xingye Chen, Wei Feng, Zhenbang Du et al.

In web data, advertising images are crucial for capturing user attention and improving advertising effectiveness. Most existing methods generate background for products primarily focus on the aesthetic quality, which may fail to achieve satisfactory online performance. To address this limitation, we explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective. Firstly, we build targeted pre-training tasks, and leverage a large-scale e-commerce multimodal dataset to equip MLLMs with initial capabilities for advertising image generation tasks. To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL), which can jointly utilize multimodal features and accurately reflect user click preferences. Meanwhile, a product-centric preference optimization strategy is developed to ensure that the generated background content aligns with the product characteristics after fine-tuning, enhancing the overall relevance and effectiveness of the advertising images. Extensive experiments have demonstrated that our method achieves state-of-the-art performance in both online and offline metrics. Our code and pre-trained models are publicly available at: https://github.com/Chenguoz/CAIG.

Shiming Chen, Guo-Sen Xie, Yang Liu et al.

Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. Typically, to guarantee desirable knowledge transfer, a common (latent) space is adopted for associating the visual and semantic domains in ZSL. However, existing common space learning methods align the semantic and visual domains by merely mitigating distribution disagreement through one-step adaptation. This strategy is usually ineffective due to the heterogeneous nature of the feature representations in the two domains, which intrinsically contain both distribution and structure variations. To address this and advance ZSL, we propose a novel hierarchical semantic-visual adaptation (HSVA) framework. Specifically, HSVA aligns the semantic and visual domains by adopting a hierarchical two-step adaptation, i.e., structure adaptation and distribution adaptation. In the structure adaptation step, we take two task-specific encoders to encode the source data (visual domain) and the target data (semantic domain) into a structure-aligned common space. To this end, a supervised adversarial discrepancy (SAD) module is proposed to adversarially minimize the discrepancy between the predictions of two task-specific classifiers, thus making the visual and semantic feature manifolds more closely aligned. In the distribution adaptation step, we directly minimize the Wasserstein distance between the latent multivariate Gaussian distributions to align the visual and semantic distributions using a common encoder. Finally, the structure and distribution adaptation are derived in a unified framework under two partially-aligned variational autoencoders. Extensive experiments on four benchmark datasets demonstrate that HSVA achieves superior performance on both conventional and generalized ZSL. The code is available at \url{https://github.com/shiming-chen/HSVA} .

Zhimeng Xin, Tianxu Wu, Yixiong Zou et al.

Due to the limited training samples in few-shot object detection (FSOD), we observe that current methods may struggle to accurately extract effective features from each channel. Specifically, this issue manifests in two aspects: i) channels with high weights may not necessarily be effective, and ii) channels with low weights may still hold significant value. To handle this problem, we consider utilizing the inter-channel correlation to facilitate the novel model's adaptation process to novel conditions, ensuring the model can correctly highlight effective channels and rectify those incorrect ones. Since the channel sequence is also 1-dimensional, its similarity with the temporal sequence inspires us to take Mamba for modeling the correlation in the channel sequence. Based on this concept, we propose a Spatial-Channel State Space Modeling (SCSM) module for spatial-channel state modeling, which highlights the effective patterns and rectifies those ineffective ones in feature channels. In SCSM, we design the Spatial Feature Modeling (SFM) module to balance the learning of spatial relationships and channel relationships, and then introduce the Channel State Modeling (CSM) module based on Mamba to learn correlation in channels. Extensive experiments on the VOC and COCO datasets show that the SCSM module enables the novel detector to improve the quality of focused feature representation in channels and achieve state-of-the-art performance.

Jiamiao Xu, Fangzhao Wang, Qinmu Peng et al.

Low-rank Multi-view Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL based methods are incapable of well handling view discrepancy and discriminancy simultaneously, which thus leads to the performance degradation when there is a large discrepancy among multi-view data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose Structured Low-rank Matrix Recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address data contaminated by predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such limitation, modal regression is elegantly incorporated into the framework of SLMR (term it MR-SLMR). Different from previous LMvSL based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to efficiently optimize MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise.

Shiming Chen, Peng Zhang, Guo-Sen Xie et al.

Dynamic texture (DT) exhibits statistical stationarity in the spatial domain and stochastic repetitiveness in the temporal dimension, indicating that different frames of DT possess a high similarity correlation that is critical prior knowledge. However, existing methods cannot effectively learn a promising synthesis model for high-dimensional DT from a small number of training data. In this paper, we propose a novel DT synthesis method, which makes full use of similarity prior knowledge to address this issue. Our method bases on the proposed kernel similarity embedding, which not only can mitigate the high-dimensionality and small sample issues, but also has the advantage of modeling nonlinear feature relationship. Specifically, we first raise two hypotheses that are essential for DT model to generate new frames using similarity correlation. Then, we integrate kernel learning and extreme learning machine into a unified synthesis model to learn kernel similarity embedding for representing DT. Extensive experiments on DT videos collected from the internet and two benchmark datasets, i.e., Gatech Graphcut Textures and Dyntex, demonstrate that the learned kernel similarity embedding can effectively exhibit the discriminative representation for DT. Accordingly, our method is capable of preserving the long-term temporal continuity of the synthesized DT sequences with excellent sustainability and generalization. Meanwhile, it effectively generates realistic DT videos with fast speed and low computation, compared with the state-of-the-art methods. The code and more synthesis videos are available at our project page https://shiming-chen.github.io/Similarity-page/Similarit.html.

Zhengqiang Zhang, Shujian Yu, Shi Yin et al.

Weakly-supervised semantic segmentation aims to assign each pixel a semantic category under weak supervisions, such as image-level tags. Most of existing weakly-supervised semantic segmentation methods do not use any feedback from segmentation output and can be considered as open-loop systems. They are prone to accumulated errors because of the static seeds and the sensitive structure information. In this paper, we propose a generic self-adaptation mechanism for existing weakly-supervised semantic segmentation methods by introducing two feedback chains, thus constituting a closed-loop system. Specifically, the first chain iteratively produces dynamic seeds by incorporating cross-image structure information, whereas the second chain further expands seed regions by a customized random walk process to reconcile inner-image structure information characterized by superpixels. Experiments on PASCAL VOC 2012 suggest that our network outperforms state-of-the-art methods with significantly less computational and memory burden.

Peng Zhang, Shujian Yu, Jiamiao Xu et al.

It remains a huge challenge to design effective and efficient trackers under complex scenarios, including occlusions, illumination changes and pose variations. To cope with this problem, a promising solution is to integrate the temporal consistency across consecutive frames and multiple feature cues in a unified model. Motivated by this idea, we propose a novel correlation filter-based tracker in this work, in which the temporal relatedness is reconciled under a multi-task learning framework and the multiple feature cues are modeled using a multi-view learning approach. We demonstrate the resulting regression model can be efficiently learned by exploiting the structure of blockwise diagonal matrix. A fast blockwise diagonal matrix inversion algorithm is developed thereafter for efficient online tracking. Meanwhile, we incorporate an adaptive scale estimation mechanism to strengthen the stability of scale variation tracking. We implement our tracker using two types of features and test it on two benchmark datasets. Experimental results demonstrate the superiority of our proposed approach when compared with other state-of-the-art trackers. project homepage http://bmal.hust.edu.cn/project/KMF2JMTtracking.html

Chaojian Yu, Xinyi Zhao, Qi Zheng et al.

Fine-grained visual recognition is challenging because it highly relies on the modeling of various semantic parts and fine-grained feature learning. Bilinear pooling based models have been shown to be effective at fine-grained recognition, while most previous approaches neglect the fact that inter-layer part feature interaction and fine-grained feature learning are mutually correlated and can reinforce each other. In this paper, we present a novel model to address these issues. First, a cross-layer bilinear pooling approach is proposed to capture the inter-layer part feature relations, which results in superior performance compared with other bilinear pooling based approaches. Second, we propose a novel hierarchical bilinear pooling framework to integrate multiple cross-layer bilinear features to enhance their representation capability. Our formulation is intuitive, efficient and achieves state-of-the-art results on the widely used fine-grained recognition datasets.

Jiamiao Xu, Shujian Yu, Xinge You et al.

We present a novel cross-view classification algorithm where the gallery and probe data come from different views. A popular approach to tackle this problem is the multi-view subspace learning (MvSL) that aims to learn a latent subspace shared by multi-view data. Despite promising results obtained on some applications, the performance of existing methods deteriorates dramatically when the multi-view data is sampled from nonlinear manifolds or suffers from heavy outliers. To circumvent this drawback, motivated by the Divide-and-Conquer strategy, we propose Multi-view Hybrid Embedding (MvHE), a unique method of dividing the problem of cross-view classification into three subproblems and building one model for each subproblem. Specifically, the first model is designed to remove view discrepancy, whereas the second and third models attempt to discover the intrinsic nonlinear structure and to increase discriminability in intra-view and inter-view samples respectively. The kernel extension is conducted to further boost the representation power of MvHE. Extensive experiments are conducted on four benchmark datasets. Our methods demonstrate overwhelming advantages against the state-of-the-art MvSL based cross-view classification approaches in terms of classification accuracy and robustness.