In the context of zero-shot learning, retrieving natural images using sketch queries is referred to as Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR). The core problems of ZS-SBIR arise from the significant domain gap between sketches and photographs. The knowledge gap between seen and unseen categories is a crucial problems as well. To address these two issues, we propose a modality-aware bidirectional mining strategy aimed at enhancing the model’s understanding of multimodal data and mitigating the modality gap between sketches and photographs. Additionally, we introduce an improved Mixed Sample Data Augmentation (MSDA) technique to generate mixed samples as supplementary training data. Based on these generated mixed samples, we propose a mixed embedding mining strategy. This strategy aims to optimize the embedding space and enhance the model’s generalization ability from seen to unseen categories. Extensive experimental results on the TU-Berlin Ext., Sketchy Ext., and QuickDraw Ext. datasets demonstrate that our proposed model outperforms existing methods.

The goal of compositional zero-shot learning (CZSL) is to train a model to recognize images containing known attribute-object pairs. This reduces the reliance on extensive training data and enables the model to identify unseen combinations. Current CZSL methods face several challenges, including multiple attributes for a single object, disconnected training and test sets, long-tailed distribution of visual categories, and substantial differences in state representation between different objects. These factors collectively impede the precise identification of new combinations. In response to these challenges, we propose a Semi-Negative Contrastive Subclass Discriminative Network (SN-CSDN) based on contrastive learning. Firstly, we propose a semi-negative sampling strategy that incorporates carefully selected negative samples into the training process. This approach enables the model to effectively distinguish between different classes while enhancing its ability to capture fine-grained subclass features. By improving the model's sensitivity to inter-class differences and refining its recognition of subtle intra-class variations, this strategy significantly boosts overall discrimination performance. Additionally, we introduce a decoupled network branch designed to capture the intricate relationships between attributes and objects by generating more representative compositional embeddings. This branch leverages subclass information to ensure an accurate classification of synthesized embeddings while preserving the inherent visual distinctions of the original decoupled embeddings across different combinations. By improving feature representation capacity and mitigating sample imbalance, this design effectively improves model performance in long-tailed distributions. Our method has been comprehensively evaluated on three benchmark datasets, with results showing significant performance improvements that demonstrate the method's effectiveness and reliability.

Sketch-based image retrieval (SBIR) relies on free-hand sketches to retrieve natural photos within the same class. However, its practical application is limited by its inability to retrieve classes absent from the training set. To address this limitation, the task has evolved into Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR), where model performance is evaluated on unseen categories. Traditional SBIR primarily focuses on narrowing the domain gap between photo and sketch modalities. However, in the zero-shot setting, the model not only needs to address this cross-modal discrepancy but also requires a strong generalization capability to transfer knowledge to unseen categories. To this end, we propose a novel framework for ZS-SBIR that employs a pair-based relation-aware quadruplet loss to bridge feature gaps. By incorporating two negative samples from different modalities, the approach prevents positive features from becoming disproportionately distant from one modality while remaining close to another, thus enhancing inter-class separability. We also propose a Relation-Aware Meta-Learning Network (RAMLN) to obtain the margin, a hyper-parameter of cross-modal quadruplet loss, to improve the generalization ability of the model. RAMLN leverages external memory to store feature information, which it utilizes to assign optimal margin values. Experimental results obtained on the extended Sketchy and TU-Berlin datasets show a sharp improvement over existing state-of-the-art methods in ZS-SBIR.

With the rapid development of remote sensing technology, the range of its applications, such as urban planning and environmental monitoring, has broadened considerably. However, the vast increase in remote sensing data poses challenges for training deep neural networks, primarily due to the extensive labeled datasets required. To address this issue, zero-shot learning (ZSL) emerges as a viable approach, enabling recognition of unseen categories without relying on training samples. In this paper, we introduce a Robust and Discriminative Visual-Semantic Alignment (RDVSA) model, which utilizes attribute-guided contrastive learning for enhanced performance. By incorporating category centroids into the embedding space of visual features and attribute descriptions, our model enhances the discriminative power of learned features and stabilizes the learning process, particularly in the presence of complex data distributions and noise in remote sensing images. Additionally, we employ a Vision Transformer (ViT) and a “mean-teacher" framework to capture both global context and local details, ensuring robustness in occluded or irrelevant attribute regions. Comprehensive experiments on large-scale remote sensing benchmarks reveal that our approach surpasses current state-of-the-art methods in both ZSL and generalized zero-shot learning (GZSL) scenarios. These results underscore the effectiveness of using attribute-based contrastive learning alongside consistency constraints.

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging prior knowledge of known primitives. However, real-world visual features of attributes and objects are often entangled, causing distribution shifts between seen and unseen combinations. Existing methods often ignore intrinsic variations and interactions among primitives, leading to poor feature discrimination and biased predictions. To address these challenges, we propose Multi-level Contextual Prototype Modulation (MCPM), a transformer-based framework with a hierarchical structure that effectively integrates attributes and objects to generate richer visual embeddings. At the feature level, we apply contrastive learning to improve discriminability across compositional tasks. At the prototype level, a subclass-driven modulator captures fine-grained attribute-object interactions, enabling better adaptation to long-tail distributions. Additionally, we introduce a Minority Attribute Enhancement (MAE) strategy that synthesizes virtual samples by mixing attribute classes, further mitigating data imbalance. Experiments on four benchmark datasets (MIT-States, C-GQA, UT-Zappos, and VAW-CZSL) show that MCPM brings significant performance improvements, verifying its effectiveness in complex composition scenes.

Compositional zero-shot learning (CZSL) aims to identify unobservable compositional concepts with prior knowledge of known primitives (attributes and objects). Due to distribution differences between seen and unseen components, existing methods for CZSL often ignore intrinsic variations between primitives and suffer from domain bias problems. To address this challenge, we proposed a concept-aware graph convolutional network (GCN) that utilizes cross-attentions to extract features unique to attributes and objects from paired concept-sharing inputs. The proposed model utilizes the cosine similarity between visual features and synthetic embeddings to estimate the feasibility score for each unseen composition. This score is then employed as a weight in the graph adjacency matrix. Additionally, the proposed model incorporates the Earth mover's distance (EMD) to further limit the concept of learning interest in disentanglers. Experimental results on three challenging dataset benchmarks, including UT-Zappos 50K, C-GQA, and MIT-States, demonstrate that the proposed model outperforms prior work in both closed- and open-world CZSL (OW-CZSL).

Abstract The acquisition cycle of remote sensing images is slow, and the labelling process encounters challenges, which have become prominent with the rapid development of remote sensing image object detection research. Therefore, this article provides a way to make the model better capture the diversity and contextual relationships in the data, and solve this problem by more than just data augmentation. Specifically, this method is a few‐shot object detection method for remote sensing based on global context combined with implicit knowledge decoupled head (GC‐IKDH). This method first uses a segmentation strategy to convert high‐resolution images into low‐resolution images and expands the sample size through a generative model. Secondly, GC attention is introduced to generate a GC vector by weighting and averaging the information of each position in the input sequence, which helps the model better understand the semantics of the input sequence. Finally, an IKDH is added to improve the model head, which is used to learn specific features in the data so that the model can better handle the diversity in the data. Experimental results show that GC attention and IKDH boosting provide a good performance boost to the baseline model. Compared with other few‐shot samples, this method achieves state‐of‐the‐art performance under different shot settings and highly competitive results on two benchmark datasets (NWPU VHR‐10 and DIOR).

The performance of zero-shot learning (ZSL) can be improved progressively by learning better features and generating pseudosamples for unseen classes. Existing ZSL works typically learn feature extractors and generators independently, which may shift the unseen samples away from their real distribution and suffers from the domain bias problem. In this article, to tackle this challenge, we propose a variational autoencoder (VAE)-based framework, that is, joint Attentive Region Embedding with Enhanced Semantics (AREES), which is tailored to advance the zero-shot recognition. Specifically, AREES is end-to-end trainable and consists of three network branches: 1) attentive region embedding is used to learn the semantic-guided visual features by the attention mechanism (AM); 2) a decomposition structure and a semantic pivot regularization are used to extract enhanced semantics; and 3) a multimodal VAE (mVAE) with the cross-reconstruction loss and the distribution alignment loss is used to obtain a shared latent embedding space of visual features and semantics. Finally, features' extraction and features' generation are optimized together in AREES to address the domain shift problem to a large extent. The comprehensive evaluations on six benchmarks, including the ImageNet, demonstrate the superiority of the proposed model over its state-of-the-art counterparts.

Zero-shot learning (ZSL) aims to classify unseen samples based on the relationship between the learned visual features and semantic features. Traditional ZSL methods typically capture the underlying multimodal data structures by learning an embedding function between the visual space and the semantic space with the Euclidean metric. However, these models suffer from the hubness problem and domain bias problem, which leads to unsatisfactory performance, especially in the generalized ZSL (GZSL) task. To tackle such a problem, we formulate a discriminative cross-aligned variational autoencoder (DCA-VAE) for ZSL. The proposed model effectively utilizes a modified cross-modal-alignment variational autoencoder (VAE) to transform both visual features and semantic features obtained by the discriminative cosine metric into latent features. The key to our method is that we collect principal discriminative information from visual and semantic features to construct latent features which contain the discriminative multimodal information associated with unseen samples. Finally, the proposed model DCA-VAE is validated on six benchmarks including the large dataset ImageNet, and several experimental results demonstrate the superiority of DCA-VAE over most existing embedding or generative ZSL models on the standard ZSL and the more realistic GZSL tasks.

Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute descriptions shared between different classes, which are strong prior for localization of object attribute for representing discriminative region features enabling significant visual-semantic interaction. Although few attention-based models have attempted to learn such region features in a single image, the transferability and discriminative attribute localization of visual features are typically neglected. In this paper, we propose an attribute-guided Transformer network to learn the attribute localization for discriminative visual-semantic embedding representations in ZSL, termed TransZero. Specifically, TransZero takes a feature augmentation encoder to alleviate the cross-dataset bias between ImageNet and ZSL benchmarks and improve the transferability of visual features by reducing the entangled relative geometry relationships among region features. To learn locality-augmented visual features, TransZero employs a visual-semantic decoder to localize the most relevant image regions to each attributes from a given image under the guidance of attribute semantic information. Then, the locality-augmented visual features and semantic vectors are used for conducting effective visual-semantic interaction in a visual-semantic embedding network. Extensive experiments show that TransZero achieves a new state-of-the-art on three ZSL benchmarks. The codes are available at: https://github.com/shiming-chen/TransZero.

Benefiting from the pioneering design of generic object detectors, significant achievements have been made in the field of face detection. Typically, the architectures of the backbone, feature pyramid layer, and detection head module within the face detector all assimilate the excellent experience from general object detectors. However, several effective methods, including label assignment and scale-level data augmentation strategy, fail to maintain consistent superiority when applying on the face detector directly. Concretely, the former strategy involves a vast body of hyperparameters and the latter one suffers from the challenge of scale distribution bias between different detection tasks, which both limit their generalization abilities. Furthermore, in order to provide accurate face bounding boxes for facial down-stream tasks, the face detector imperatively requires the elimination of false alarms. As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are necessary for advancing face detectors. In this paper, we focus on resolving three aforementioned challenges that exiting methods are difficult to finish off and present a novel face detector, termed MogFace. In our Mogface, three key components, Adaptive Online Incremental Anchor Mining Strategy, Selective Scale Enhancement Strategy and Hierarchical Context-Aware Module, are separately proposed to boost the performance of face detectors. Finally, to the best of our knowledge, our MogFace is the best face detector on the Wider Face leader-board, achieving all champions across different testing scenarios. The code is available at https://github.com/damo-cv/MogFace.

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}.

The fundamental problem of Zero-Shot Learning (ZSL) is that the one-hot label space is discrete, which leads to a complete loss of the relationships between seen and unseen classes. Conventional approaches rely on using semantic auxiliary information, e.g. attributes, to re-encode each class so as to preserve the inter-class associations. However, existing learning algorithms only focus on unifying visual and semantic spaces without jointly considering the label space. More importantly, because the final classification is conducted in the label space through a compatibility function, the gap between attribute and label spaces leads to significant performance degradation. Therefore, this paper proposes a novel pathway that uses the label space to jointly reconcile visual and semantic spaces directly, which is named Attributing Label Space (ALS). In the training phase, one-hot labels of seen classes are directly used as prototypes in a common space, where both images and attributes are mapped. Since mappings can be optimized independently, the computational complexity is extremely low. In addition, the correlation between semantic attributes has less influence on visual embedding training because features are mapped into labels instead of attributes. In the testing phase, the discrete condition of label space is removed, and priori one-hot labels are used to denote seen classes and further compose labels of unseen classes. Therefore, the label space is very discriminative for the Generalized ZSL (GZSL), which is more reasonable and challenging for real-world applications. Extensive experiments on five benchmarks manifest improved performance over all of compared state-of-the-art methods.

For Zero-Shot Learning (ZSL), the Nearest Neighbor (NN) search is generally conducted for classification, which may cause unacceptable computational complexity for large-scale datasets. To compress zero-shot classes by the trained quantizer for efficient search, it tends to induce large quantization error because distributions between seen and unseen classes are different. However, as semantic attributes of classes are available in ZSL, both seen and unseen classes have the same distribution for one specific property, e.g., animals have or not have spots. Based on this intuition, a Product Quantization Zero-Shot Learning (PQZSL) method is proposed to learn embeddings as well as quantizers to compress visual features into compact codes for Approximate NN (ANN) search. Particularly, visual features are projected into an orthogonal semantic space, and then the Product Quantization (PQ) is utilized to quantize individual properties. Experimental results on five benchmark datasets demonstrate that unseen classes are represented by the Cartesian product of quantized properties with little quantization error. As classes in orthogonal common space are more discriminative, the classification based on PQZSL achieves state-of-the-art performance in Generalized Zero-Shot Learning (GZSL) task, meanwhile, the speed of ANN search is 10-100 times higher than traditional NN search.

Feature selection plays a critical role in data mining, driven by increasing feature dimensionality in target problems. In this paper, we propose a new criterion for discriminative feature selection, worst-case discriminative feature selection (WDFS). Unlike Fisher Score and other methods based on the discriminative criteria considering the overall (or average) separation of data, WDFS adopts a new perspective called worst-case view which arguably is more suitable for classification applications. Specifically, WDFS directly maximizes the ratio of the minimum of between-class variance of all class pairs over the maximum of within-class variance, and thus it duly considers the separation of all classes. Otherwise, we take a greedy strategy by finding one feature at a time, but it is very easy to implement. Moreover, we also utilize the correlation between features to help reduce the redundancy and extend WDFS to uncorrelated WDFS (UWDFS). To evaluate the effectiveness of the proposed algorithm, we conduct classification experiments on many real data sets. In the experiment, we respectively use the original features and the score vectors of features over all class pairs to calculate the correlation coefficients, and analyze the experimental results in these two ways. Experimental results demonstrate the effectiveness of WDFS and UWDFS.

Zero-shot learning (ZSL) aims to build models to recognize novel visual categories that have no associated labelled training samples. The basic framework is to transfer knowledge from seen classes to unseen classes by learning the visual-semantic embedding. However, most of approaches do not preserve the underlying sub-manifold of samples in the embedding space. In addition, whether the mapping can precisely reconstruct the original visual feature is not investigated in-depth. In order to solve these problems, we formulate a novel framework named Graph and Autoencoder Based Feature Extraction (GAFE) to seek a low-rank mapping to preserve the sub-manifold of samples. Taking the encoder-decoder paradigm, the encoder part learns a mapping from the visual feature to the semantic space, while decoder part reconstructs the original features with the learned mapping. In addition, a graph is constructed to guarantee the learned mapping can preserve the local intrinsic structure of the data. To this end, an L21 norm sparsity constraint is imposed on the mapping to identify features relevant to the target domain. Extensive experiments on five attribute datasets demonstrate the effectiveness of the proposed model.

Most existing robust principal component analysis (PCA) involve mean estimation for extracting low-dimensional representation. However, they do not get the optimal mean for real data, which include outliers, under the different robust distances metric learning, such as L1-norm and L2,1-norm. This affects the robustness of algorithms. Motivated by the fact that the variance of data can be characterized by the variation between each pair of data, we propose a novel robust formulation for PCA. It avoids computing the mean of data in the criterion function. Our method employs L2,p-norm as the distance metric to measure the variation in the criterion function and aims to seek the projection matrix that maximizes the sum of variation between each pair of the projected data. Both theoretical analysis and experimental results demonstrate that our methods are efficient and superior to most existing robust methods for data reconstruction.

Sparse representation based classification (SRC) has gained great success in image recognition. Motivated by the fact that kernel trick can capture the nonlinear similarity of features, which may help improve the separability and margin between nearby data points, we propose Euler SRC for image classification, which is essentially the SRC with Euler sparse representation. To be specific, it first maps the images into the complex space by Euler representation, which has a negligible effect for outliers and illumination, and then performs complex SRC with Euler representation. The major advantage of our method is that Euler representation is explicit with no increase of the image space dimensionality, thereby enabling this technique to be easily deployed in real applications. To solve Euler SRC, we present an efficient algorithm, which is fast and has good convergence. Extensive experimental results illustrate that Euler SRC outperforms traditional SRC and achieves better performance for image classification.

Zero-shot learning (ZSL) has been widely researched and get successful in machine learning. Most existing ZSL methods aim to accurately recognize objects of unseen classes by learning a shared mapping from the feature space to a semantic space. However, such methods did not investigate in-depth whether the mapping can precisely reconstruct the original visual feature. Motivated by the fact that the data have low intrinsic dimensionality e.g. low-dimensional subspace. In this paper, we formulate a novel framework named Low-rank Embedded Semantic AutoEncoder (LESAE) to jointly seek a low-rank mapping to link visual features with their semantic representations. Taking the encoder-decoder paradigm, the encoder part aims to learn a low-rank mapping from the visual feature to the semantic space, while decoder part manages to reconstruct the original data with the learned mapping. In addition, a non-greedy iterative algorithm is adopted to solve our model. Extensive experiments on six benchmark datasets demonstrate its superiority over several state-of-the-art algorithms.

Due to the importance and efficiency of learning complex structures hidden in data, graph-based methods have been widely studied and get successful in unsupervised learning. Generally, most existing graph-based clustering methods require post-processing on the original data graph to extract the clustering indicators. However, there are two drawbacks with these methods: (1) the cluster structures are not explicit in the clustering results; (2) the final clustering performance is sensitive to the construction of the original data graph. To solve these problems, in this paper, a novel learning model is proposed to learn a graph based on the given data graph such that the new obtained optimal graph is more suitable for the clustering task. We also propose an efficient algorithm to solve the model. Extensive experimental results illustrate that the proposed model outperforms other state-of-the-art clustering algorithms.

2-D principal component analysis (2DPCA), which employs squared -norm as the distance metric, has been widely used in dimensionality reduction for data representation and classification. It, however, is commonly known that squared -norm is very sensitivity to outliers. To handle this problem, we present a novel formulation for 2DPCA, namely Angle-2DPCA. It employs -norm as the distance metric and takes into consideration the relationship between reconstruction error and variance in the objective function. We present a fast iterative algorithm to solve the solution of Angle-2DPCA. Experimental results on the Extended Yale B, AR, and PIE face image databases illustrate the effectiveness of our proposed approach.