Image Retrieval Tasks Research Articles

H-QNN: A Hybrid Quantum–Classical Neural Network for Improved Binary Image Classification

Image classification is an important application for deep learning. With the advent of quantum technology, quantum neural networks (QNNs) have become the focus of research. Traditional deep learning-based image classification involves using a convolutional neural network (CNN) to extract features from the image and a multi-layer perceptron (MLP) network to create the decision boundaries. However, quantum circuits with parameters can extract rich features from images and also create complex decision boundaries. This paper proposes a hybrid QNN (H-QNN) model designed for binary image classification that capitalizes on the strengths of quantum computing and classical neural networks. Our H-QNN model uses a compact, two-qubit quantum circuit integrated with a classical convolutional architecture, making it highly efficient for computation on noisy intermediate-scale quantum (NISQ) devices that are currently leading the way in practical quantum computing applications. Our H-QNN model significantly enhances classification accuracy, achieving a 90.1% accuracy rate on binary image datasets. In addition, we have extensively evaluated baseline CNN and our proposed H-QNN models for image retrieval tasks. The obtained quantitative results exhibit the generalization of our H-QNN for downstream image retrieval tasks. Furthermore, our model addresses the issue of overfitting for small datasets, making it a valuable tool for practical applications.

Cross-modality sub-image retrieval using contrastive multimodal image representations

In tissue characterization and cancer diagnostics, multimodal imaging has emerged as a powerful technique. Thanks to computational advances, large datasets can be exploited to discover patterns in pathologies and improve diagnosis. However, this requires efficient and scalable image retrieval methods. Cross-modality image retrieval is particularly challenging, since images of similar (or even the same) content captured by different modalities might share few common structures. We propose a new application-independent content-based image retrieval (CBIR) system for reverse (sub-)image search across modalities, which combines deep learning to generate representations (embedding the different modalities in a common space) with robust feature extraction and bag-of-words models for efficient and reliable retrieval. We illustrate its advantages through a replacement study, exploring a number of feature extractors and learned representations, as well as through comparison to recent (cross-modality) CBIR methods. For the task of (sub-)image retrieval on a (publicly available) dataset of brightfield and second harmonic generation microscopy images, the results show that our approach is superior to all tested alternatives. We discuss the shortcomings of the compared methods and observe the importance of equivariance and invariance properties of the learned representations and feature extractors in the CBIR pipeline. Code is available at: https://github.com/MIDA-group/CrossModal_ImgRetrieval.

A MultiModal Vigilance (MMV) dataset during RSVP and SSVEP brain-computer interface tasks

Vigilance represents an ability to sustain prolonged attention and plays a crucial role in ensuring the reliability and optimal performance of various tasks. In this report, we describe a MultiModal Vigilance (MMV) dataset comprising seven physiological signals acquired during two Brain-Computer Interface (BCI) tasks. The BCI tasks encompass a rapid serial visual presentation (RSVP)-based target image retrieval task and a steady-state visual evoked potential (SSVEP)-based cursor-control task. The MMV dataset includes four sessions of seven physiological signals for 18 subjects, which encompasses electroencephalogram(EEG), electrooculogram (EOG), electrocardiogram (ECG), photoplethysmogram (PPG), electrodermal activity (EDA), electromyogram (EMG), and eye movement. The MMV dataset provides data from four stages: 1) raw data, 2) pre-processed data, 3) trial data, and 4) feature data that can be directly used for vigilance estimation. We believe this dataset will achieve flexible reuse and meet the various needs of researchers. And this dataset will greatly contribute to advancing research on physiological signal-based vigilance research and estimation.

Discriminative Feature Enhancement Network for few-shot classification and beyond

Few-shot classification aims to recognize query samples from novel classes given scarce labeled data, which remains a challenging problem in machine learning. This paper proposes a Discriminative Feature Enhancement Network (DFENet) to distinguish the discriminative feature of a novel category with the following characteristics: (1) a Cross-Modal Guidance Module (CMG-Module) is proposed to enrich the query vectors via leveraging label information from the additional modality; (2) a Neural-Decoding based Attention Module (NDA-Module) further explores the relationship between the query and support samples, and the attention weights depend on contribution of the support to the reconstructed query. The main intuition of the NDA-Module is to deepen our understanding of the self-attention mechanism from a neural decoding perspective, emphasizing that the best reconstruction can be used as a universal guideline; (3) a flexible triplet loss is designed to incorporate the semantic context among all classes and distinguish samples from different classes. The experimental results on two few-shot classification datasets show that our DFENet can learn a more discriminative representation for novel classes progressively. We also test the proposed method on image retrieval and facial expression recognition tasks, demonstrating consistent improvement.

An experimental evaluation of Siamese Neural Networks for robot localization using omnidirectional imaging in indoor environments

The objective of this paper is to address the localization problem using omnidirectional images captured by a catadioptric vision system mounted on the robot. For this purpose, we explore the potential of Siamese Neural Networks for modeling indoor environments using panoramic images as the unique source of information. Siamese Neural Networks are characterized by their ability to generate a similarity function between two input data, in this case, between two panoramic images. In this study, Siamese Neural Networks composed of two Convolutional Neural Networks (CNNs) are used. The output of each CNN is a descriptor which is used to characterize each image. The dissimilarity of the images is computed by measuring the distance between these descriptors. This fact makes Siamese Neural Networks particularly suitable to perform image retrieval tasks. First, we evaluate an initial task strongly related to localization that consists in detecting whether two images have been captured in the same or in different rooms. Next, we assess Siamese Neural Networks in the context of a global localization problem. The results outperform previous techniques for solving the localization task using the COLD-Freiburg dataset, in a variety of lighting conditions, specially when using images captured in cloudy and night conditions.

A unified deep semantic expansion framework for domain-generalized person re-identification

Supervised Person Re-identification (Person ReID) methods have achieved excellent performance when training and testing within one camera network. However, they usually suffer from considerable performance degradation when applied to different camera systems. In recent years, many Domain Adaptation Person ReID methods have been proposed, achieving impressive performance without requiring labeled data from the target domain. However, these approaches still need the unlabeled data of the target domain during the training process, making them impractical in many real-world scenarios. Our work focuses on the more practical Domain Generalized Person Re-identification (DG-ReID) problem. Given one or more source domains, it aims to learn a generalized model that can be applied to unseen target domains. One promising research direction in DG-ReID is the use of implicit deep semantic feature expansion, and our previous method, Domain Embedding Expansion (DEX), is one such example that achieves powerful results in DG-ReID. However, in this work we show that DEX and other similar implicit deep semantic feature expansion methods, due to limitations in their proposed loss function, fail to reach their full potential on large evaluation benchmarks as they have a tendency to saturate too early. Leveraging on this analysis, we propose Unified Deep Semantic Expansion, our novel framework that unifies implicit and explicit semantic feature expansion techniques in a single framework to mitigate this early over-fitting and achieve a new state-of-the-art (SOTA) in all DG-ReID benchmarks. Further, we apply our method on more general image retrieval tasks, also surpassing the current SOTA in all of these benchmarks by wide margins.

Markov Chains for User Queries Mining: Image Retrieval Application using Internet

Abstract: We suggest a brand-new technique for automatically annotating, indexing, and retrieving photos based on annotations. We introduce the novel technique, which we term Markovian Semantic Indexing (MSI), within the framework of an image retrieval system in online mode. In the event that such a system exists, the queries entered by the users are utilised to build an Aggregate Markov Chain (AMC), which defines the significance between the terms the system sees. The photographs are automatically annotated based on the queries entered by the users. Next, depending on the annotation of each image and the keyword relevance recorded in the AMC, a stochastic distance between them is presented. The suggested distance is given geometric meanings, and its relationship to a grouping in the keyword space is examined. The optimality qualities of the suggested distance are demonstrated by the use of a novel Markovian state similarity measure, the mean first cross passage time (CPT). Images are represented as points in a vector space, and MSI is used to calculate how similar two images are. In Annotation-Based Image Retrieval (ABIR) tasks, it is demonstrated that the novel method outperforms Latent Semantic Indexing (LSI) and probabilistic Latent Semantic Indexing (pLSI) methods in terms of Precision against Recall and has some theoretical advantages.

Global semantics correlation transmitting and learning for sketch-based cross-domain visual retrieval

Sketch-based cross-domain visual data retrieval is the process of searching for images or 3D models using sketches as input. Achieving feature alignment is a significantly challenging task due to the high heterogeneity of cross-domain data. However, the alignment process faces significant challenges, such as domain gap, semantic gap, and knowledge gap. The existing methods adopt different ideas for sketch-based image and 3D shape retrieval tasks, one is domain alignment, and the other is semantic alignment. Technically, both tasks verify the accuracy of extracted features. Hence, we propose a method based on the global feature correlation and the feature similarity for multiple sketch-based cross-domain retrieval tasks. Specifically, the data from various modalities are fed into separate feature extractors to generate original features. Then, these features are projected to the shared subspace. Finally, domain consistency learning, semantic consistency learning, feature correlation learning and feature similarity learning are performed jointly to make the projected features modality-invariance. We evaluate our method on multiple benchmark datasets. Where the MAP in Sketchy, TU-Berlin, SHREC 2013 and SHREC 2014 are 0.466, 0.473, 0.860 and 0.816. The extensive experimental results demonstrate the superiority and generalization of the proposed method, compared to the state-of-the-art approaches. The in-depth analyses of various design choices are also provided to gain insight into the effectiveness of the proposed method. The outcomes of this research contribute to advancing the field of sketch-based cross-domain visual data retrieval and are expected to be applied to a variety of applications that require efficient retrieval of cross-domain domain data.

Enhancing Medical Image Retrieval with UMLS-Integrated CNN-Based Text Indexing.

In recent years, Convolutional Neural Network (CNN) models have demonstrated notable advancements in various domains such as image classification and Natural Language Processing (NLP). Despite their success in image classification tasks, their potential impact on medical image retrieval, particularly in text-based medical image retrieval (TBMIR) tasks, has not yet been fully realized. This could be attributed to the complexity of the ranking process, as there is ambiguity in treating TBMIR as an image retrieval task rather than a traditional information retrieval or NLP task. To address this gap, our paper proposes a novel approach to re-ranking medical images using a Deep Matching Model (DMM) and Medical-Dependent Features (MDF). These features incorporate categorical attributes such as medical terminologies and imaging modalities. Specifically, our DMM aims to generate effective representations for query and image metadata using a personalized CNN, facilitating matching between these representations. By using MDF, a semantic similarity matrix based on Unified Medical Language System (UMLS) meta-thesaurus, and a set of personalized filters taking into account some ranking features, our deep matching model can effectively consider the TBMIR task as an image retrieval task, as previously mentioned. To evaluate our approach, we performed experiments on the medical ImageCLEF datasets from 2009 to 2012. The experimental results show that the proposed model significantly enhances image retrieval performance compared to the baseline and state-of-the-art approaches.

Performance evaluation of attention-deep hashing based medical image retrieval in brain MRI datasets

BackgroundBrain MRI images pose significant challenges due to their complexity and voluminous data, which often hinder the accuracy of traditional image retrieval methods. In response, this research delves into a novel medical image retrieval approach grounded in attention mechanisms and deep hashing techniques. MethodologyThe study enhances the network's edge perception capability by incorporating a dual mixed attention module (CBAM-MA dual attention) into the convolutional neural network architecture. This addition optimally captures edge saliency and distributional features by introducing an extra attention layer atop CBAM. Furthermore, a novel triple loss function is introduced, amalgamating Euclidean and cosine distances. This fusion exploits the strengths of both distance metrics to comprehensively consider sample geometric attributes, thereby generating more robust and expressive feature representations crucial for preserving categorical details. ResultsExperimental evaluations showcase significant performance advancements in MRI image retrieval tasks using the proposed method. The average hit rate stands at 0.7783, average precision at 0.752246, and average inverse rank at 0.956721. These metrics collectively underscore the method's efficacy in enhancing the quality and expediting the diagnosis of brain diseases. ConclusionThe research underscores the critical role of attention and deep hashing techniques in augmenting the accuracy and efficiency of medical image retrieval, particularly in the context of brain MRI images. The proposed method's notable performance improvements pave the way for enhanced diagnostic capabilities, signaling a significant step forward in improving healthcare outcomes related to brain diseases.

Multi‐label logo recognition and retrieval based on weighted fusion of neural features

AbstractClassifying logo images is a challenging task as they contain elements such as text or shapes that can represent anything from known objects to abstract shapes. While the current state of the art for logo classification addresses the problem as a multi‐class task focusing on a single characteristic, logos can have several simultaneous labels, such as different colours. This work proposes a method that allows visually similar logos to be classified and searched from a set of data according to their shape, colour, commercial sector, semantics, general characteristics, or a combination of features selected by the user. Unlike previous approaches, the proposal employs a series of multi‐label deep neural networks specialized in specific attributes and combines the obtained features to perform the similarity search. To delve into the classification system, different existing logo topologies are compared and some of their problems are analysed, such as the incomplete labelling that trademark registration databases usually contain. The proposal is evaluated considering 76,000 logos (seven times more than previous approaches) from the European Union Trademarks dataset, which is organized hierarchically using the Vienna ontology. Overall, experimentation attains reliable quantitative and qualitative results, reducing the normalized average rank error of the state‐of‐the‐art from 0.040 to 0.018 for the Trademark Image Retrieval task. Finally, given that the semantics of logos can often be subjective, graphic design students and professionals were surveyed. Results show that the proposed methodology provides better labelling than a human expert operator, improving the label ranking average precision from 0.53 to 0.68.

Enhancing MRI image retrieval using autoencoder-based deep learning: A solution for efficient clinical and teaching applications

BackgroundMagnetic resonance imaging (MRI) image retrieval holds significant value in clinical contexts and medical education due to the shortcomings of traditional methods: slow speed, low accuracy, and limited learning capabilities. Improving this retrieval process is crucial for enhancing medical diagnostics and educational outcomes. Efforts to overcome these challenges are paramount for advancing healthcare practices and educational methodologies. MethodThis study explores the use of autoencoders in deep learning to effectively retrieve MRI images from databases for medical education, emphasizing the model's capacity to be trained with a small amount of labeled data. This work intends to improve the MRI image retrieval process by utilizing autoencoders, demonstrating the promise of deep learning technologies in medical image analysis without the need for large labeled datasets for training. ResultsResearch has demonstrated the exceptional advantages of this method for MRI image retrieval tasks, with an average accuracy of 99.09%. This indicates that the technique performs exceptionally well in this particular domain and is very effective and reliable in extracting MRI images. ConclusionsThis innovative approach can improve the archival management and diagnostic functions of medical images, providing an efficient and reliable solution for MRI image retrieval. It not only helps doctors with clinical diagnosis and medical teaching and research more quickly but also suggests a convenient solution for file management related to medical images.

A Transformer and Visual Foundation Model-Based Method for Cross-View Remote Sensing Image Retrieval

Abstract. Retrieving UAV images that lack POS information with georeferenced satellite orthoimagery is challenging due to the differences in angles of views. Most existing methods rely on deep neural networks with a large number of parameters, leading to substantial time and financial investments in network training. Consequently, these methods may not be well-suited for downstream tasks that have high timeliness requirements. In this work, we propose a cross-view remote sensing image retrieval method based on transformer and visual foundation model. We investigated the potential of visual foundation model for extracting common features from cross-view images. Training is only conducted on a small, self-designed retrieval head, alleviating the burden of network training. Specifically, we designed a CVV module to optimize the features extracted from the visual foundation model, making these features more adept for cross-view image retrieval tasks. And we designed an MLP head to achieve similarity discrimination. The method is verified on a publicly available dataset containing multiple scenes. Our method shows excellent results in terms of both efficiency and accuracy on 15 sub-datasets (10 or 50 scene categories) derived from the public dataset, which holds practical value in engineering applications with streamlined scene categories and constrained computational resources. Furthermore, we initiated a comprehensive discussion and conducted ablation experiments on the network design to validate its efficacy. Additionally, we analyzed the presence of overfitting within the network and deliberated on the limitations of our study, proposing potential avenues for future enhancements.

A robust self-supervised image hashing method for content identification with forensic detection of content-preserving manipulations

Image content identification systems have many applications in industry and academia. In particular, a hash-based content identification system uses a robust image hashing function that computes a short binary identifier summarizing the perceptual content in a picture and is invariant against a set of expected manipulations while being capable of differentiating between different pictures. A common approach to designing these algorithms is crafting a processing pipeline by hand. Unfortunately, once the context changes, the researcher may need to define a new function to adapt. A deep hashing approach exploits the feature learning capabilities in deep networks to generate a feature vector that summarizes the perceptual content in the image, achieving outstanding performance for the image retrieval task, which requires measuring semantic and perceptual similarity between items. However, its application to robust content identification systems is an open area of opportunity. Also, image hashing functions are valuable tools for image authentication. However, to our knowledge, its application to content-preserving manipulation detection for image forensics tasks is still an open research area. In this work, we propose a deep hashing method exploiting the metric learning capabilities in contrastive self-supervised learning with a new modular loss function for robust image hashing. Moreover, we propose a novel approach for content-preserving manipulation detection for image forensics through a sensitivity component in our loss function. We validate our method through extensive experimentation in different data sets and configurations, validating the generalization properties in our work.

Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval.

The composed image retrieval (CIR) task aims to retrieve the desired target image for a given multimodal query, i.e., a reference image with its corresponding modification text. The key limitations encountered by existing efforts are two aspects: 1) ignoring the multiple query-target matching factors; 2) ignoring the potential unlabeled reference-target image pairs in existing benchmark datasets. To address these two limitations is non-trivial due to the following challenges: 1) how to effectively model the multiple matching factors in a latent way without direct supervision signals; 2) how to fully utilize the potential unlabeled reference-target image pairs to improve the generalization ability of the CIR model. To address these challenges, in this work, we first propose a CLIP-Transformer based muLtI-factor Matching Network (LIMN), which consists of three key modules: disentanglement-based latent factor tokens mining, dual aggregation-based matching token learning, and dual query-target matching modeling. Thereafter, we design an iterative dual self-training paradigm to further enhance the performance of LIMN by fully utilizing the potential unlabeled reference-target image pairs in a weakly-supervised manner. Specifically, we denote the iterative dual self-training paradigm enhanced LIMN as LIMN+. Extensive experiments on four datasets, including FashionIQ, Shoes, CIRR, and Fashion200 K, show that our proposed LIMN and LIMN+ significantly surpass the state-of-the-art baselines.

Privacy Preserving Image Retrieval Using Multi-Key Random Projection Encryption and Machine Learning Decryption

Homomorphic Encryption (HE), Multiparty Computation (MPC), Differential Privacy (DP) and Random Projection (RP) have been used in privacy preserving computing. The main benefit of the random projection approach is the lighter time and space complexity compared to the other available techniques. However, RP is typically used in a symmetric encryption mode, with one random projection matrix single key, making it vulnerable to attacks. An enhanced multi-key RP approach is proposed in this paper where a set of N random matrices are used as projection keys. Moreover, a randomly chosen one is used for each new query. Machine learning models are trained to perform specific vector operations on the randomly projected vectors and produce another randomly projected results vector. Another machine learning model is trained to decrypt the final result at the user’s side. The proposed system is shown to offer privacy against known plaintext and cipher-only attacks while preserving Euclidean distance calculations accuracy in the randomly projected domain which are demonstrated on the COREL 1K image retrieval task. Results show that the cyphertext space took sixteen times less than the ciphertext done with homomorphic encryption, and the computation of distance using random projection was 8 times faster than homomorphic encryption distance calculation.

A RESEARCH OF THE LATEST APPROACHES TO VISUAL IMAGE RECOGNITION AND CLASSIFICATION

Context. The paper provides an overview of current methods for recognizing and classifying visual images in static images or video stream. The paper will discuss various approaches, including machine learning, current problems of these methods and possible improvements. The biggest challenges of the visual image retrieval and classification task are discussed. The main emphasis is placed on the review of such promising algorithms as SSD, YOLO, R-CNN, an overview of the principles of these methods, network architectures.
 Objective. The aim of the work is to analyze existing studies and find the best algorithm for recognizing and classifying visual images for further activities.
 Method. Primary method is to compare different factors of algorithms in order to select the most perspective one. There are different marks to compare, like image processing speed, accuracy. There are a number of studies and publications that propose methods and algorithms for solving the problem of finding and classifying images in an image [3–6]. It should be noted that most promising approaches are based on machine learning methods. It is worth noting that the proposed methods have drawbacks due to the imperfect implementation of the Faster R-CNN, YOLO, SSD algorithms for working with streaming video. The impact of these drawbacks can be significantly reduced by applying the following solutions: development of combined identification methods, processing of edge cases – tracking the position of identified objects, using the difference between video frames, additional preliminary preparation of input data. Another major area for improvement is the optimization of methods to work with real-time video data, as most current methods focus on images.
 Results. As an outcome of the current research we have found an optimal algorithm for further researches and optimizations.
 Conclusions. Analysis of existent papers and researches has demonstrated the most promising algorithm for further optimizations and experiments. Also current approaches still have some space for further. The next step is to take the chosen algorithm and investigate possibilities to enhance it.

An Image Retrieval Method for Lunar Complex Craters Integrating Visual and Depth Features

In the geological research of the Moon and other celestial bodies, the identification and analysis of impact craters are crucial for understanding the geological history of these bodies. With the rapid increase in the volume of high-resolution imagery data returned from exploration missions, traditional image retrieval methods face dual challenges of efficiency and accuracy when processing lunar complex crater image data. Deep learning techniques offer a potential solution. This paper proposes an image retrieval model for lunar complex craters that integrates visual and depth features (LC2R-Net) to overcome these difficulties. For depth feature extraction, we employ the Swin Transformer as the core architecture for feature extraction and enhance the recognition capability for key crater features by integrating the Convolutional Block Attention Module with Effective Channel Attention (CBAMwithECA). Furthermore, a triplet loss function is introduced to generate highly discriminative image embeddings, further optimizing the embedding space for similarity retrieval. In terms of visual feature extraction, we utilize Local Binary Patterns (LBP) and Hu moments to extract the texture and shape features of crater images. By performing a weighted fusion of these features and utilizing Principal Component Analysis (PCA) for dimensionality reduction, we effectively combine visual and depth features and optimize retrieval efficiency. Finally, cosine similarity is used to calculate the similarity between query images and images in the database, returning the most similar images as retrieval results. Validation experiments conducted on the lunar complex impact crater dataset constructed in this article demonstrate that LC2R-Net achieves a retrieval precision of 83.75%, showcasing superior efficiency. These experimental results confirm the advantages of LC2R-Net in handling the task of lunar complex impact crater image retrieval.

DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels

Driven by generative AI and the Internet, there is an increasing availability of a wide variety of images, leading to the significant and popular task of cross-domain image retrieval. To reduce annotation costs and increase performance, this paper focuses on an untouched but challenging problem, i.e., cross-domain image retrieval with partial labels (PCIR). Specifically, PCIR faces great challenges due to the ambiguous supervision signal and the domain gap. To address these challenges, we propose a novel method called disambiguated domain alignment (DiDA) for cross-domain retrieval with partial labels. In detail, DiDA elaborates a novel prototype-score unitization learning mechanism (PSUL) to extract common discriminative representations by simultaneously disambiguating the partial labels and narrowing the domain gap. Additionally, DiDA proposes a prototype-based domain alignment mechanism (PBDA) to further bridge the inherent cross-domain discrepancy. Attributed to PSUL and PBDA, our DiDA effectively excavates domain-invariant discrimination for cross-domain image retrieval. We demonstrate the effectiveness of DiDA through comprehensive experiments on three benchmarks, comparing it to existing state-of-the-art methods. Code available: https://github.com/lhrrrrrr/DiDA.

Differentiable Auxiliary Learning for Sketch Re-Identification

Sketch re-identification (Re-ID) seeks to match pedestrians' photos from surveillance videos with corresponding sketches. However, we observe that existing works still have two critical limitations: (i) cross- and intra-modality discrepancies hinder the extraction of modality-shared features, (ii) standard triplet loss fails to constrain latent feature distribution in each modality with inadequate samples. To overcome the above issues, we propose a differentiable auxiliary learning network (DALNet) to explore a robust auxiliary modality for Sketch Re-ID. Specifically, for (i) we construct an auxiliary modality by using a dynamic auxiliary generator (DAG) to bridge the gap between sketch and photo modalities. The auxiliary modality highlights the described person in photos to mitigate background clutter and learns sketch style through style refinement. Moreover, a modality interactive attention module (MIA) is presented to align the features and learn the invariant patterns of two modalities by auxiliary modality. To address (ii), we propose a multi-modality collaborative learning scheme (MMCL) to align the latent distribution of three modalities. An intra-modality circle loss in MMCL brings learned global and modality-shared features of the same identity closer in the case of insufficient samples within each modality. Extensive experiments verify the superior performance of our DALNet over the state-of-the-art methods for Sketch Re-ID, and the generalization in sketch-based image retrieval and sketch-photo face recognition tasks.