Fast diagnosis and treatment of pneumothorax, a collapsed or dropped lung, is crucial to avoid fatalities. Pneumothorax is typically detected on a chest X-ray image through visual inspection by experienced radiologists. However, the detection rate is quite low. Therefore, there is a strong need for automated detection systems to assist radiologists. Despite the high accuracy levels generally reported for deep learning classifiers in many applications, they may not be useful in clinical practice due to the lack of large number of high-quality labelled images as well as a lack of interpretation possibility. Alternatively, searching in the archive of past cases to find matching images may serve as a 'virtual second opinion' through accessing the metadata of matched evidently diagnosed cases. To use image search as a triaging/diagnosis tool, all chest X-ray images must first be tagged with identifiers, i.e., deep features. Then, given a query chest X-ray image, the majority vote among the top k retrieved images can provide a more explainable output. While image search can be clinically more viable, its detection performance needs to be investigated at a scale closer to real-world practice. We combined 3 public datasets to assemble a repository with more than 550,000 chest X-ray images. We developed the Autoencoding Thorax Net (short AutoThorax-Net) for image search in chest radiographs compressing three inputs: the left chest side, the flipped right side, and the entire chest image. Experimental results show that image search based on AutoThorax-Net features can achieve high identification rates providing a path towards real-world deployment. We achieved 92% AUC accuracy for a semi-automated search in 194,608 images (pneumothorax and normal) and 82% AUC accuracy for fully automated search in 551,383 images (normal, pneumothorax and many other chest diseases).
Searching for relative mobile user interface (UI) design examples can aid interface designers in gaining inspiration and comparing design alternatives. However, finding such design examples is challenging, especially as current search systems rely on only text-based queries and do not consider the UI structure and content into account. This paper introduces VINS, a visual search framework, that takes as input a UI image (wireframe, high-fidelity) and retrieves visually similar design examples. We first survey interface designers to better understand their example finding process. We then develop a large-scale UI dataset that provides an accurate specification of the interface's view hierarchy (i.e., all the UI components and their specific location). By utilizing this dataset, we propose an object-detection based image retrieval framework that models the UI context and hierarchical structure. The framework achieves a mean Average Precision of 76.39\% for the UI detection and high performance in querying similar UI designs.
We present a method for automatically labelling all faces in video archives, such as TV broadcasts, by combining multiple evidence sources and multiple modalities (visual and audio). We target the problem of ever-growing online video archives, where an effective, scalable indexing solution cannot require a user to provide manual annotation or supervision. To this end, we make three key contributions: (1) We provide a novel, simple, method for determining if a person is famous or not using image-search engines. In turn this enables a face-identity model to be built reliably and robustly, and used for high precision automatic labelling; (2) We show that even for less-famous people, image-search engines can then be used for corroborative evidence to accurately label faces that are named in the scene or the speech; (3) Finally, we quantitatively demonstrate the benefits of our approach on different video domains and test settings, such as TV shows and news broadcasts. Our method works across three disparate datasets without any explicit domain adaptation, and sets new state-of-the-art results on all the public benchmarks.
Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers for generating image descriptors and train the resulting model with a metric learning objective, which combines a contrastive loss with a differential entropy regularizer. Our results show consistent and significant improvements of transformers over convolution-based approaches. In particular, our method outperforms the state of the art on several public benchmarks for category-level retrieval, namely Stanford Online Product, In-Shop and CUB-200. Furthermore, our experiments on ROxford and RParis also show that, in comparable settings, transformers are competitive for particular object retrieval, especially in the regime of short vector representations and low-resolution images.
Most existing image retrieval systems use text queries as a way for the user to express what they are looking for. However, fine-grained image retrieval often requires the ability to also express where in the image the content they are looking for is. The text modality can only cumbersomely express such localization preferences, whereas pointing is a more natural fit. In this paper, we propose an image retrieval setup with a new form of multimodal queries, where the user simultaneously uses both spoken natural language (the what) and mouse traces over an empty canvas (the where) to express the characteristics of the desired target image. We then describe simple modifications to an existing image retrieval model, enabling it to operate in this setup. Qualitative and quantitative experiments show that our model effectively takes this spatial guidance into account, and provides significantly more accurate retrieval results compared to text-only equivalent systems.
This paper introduces the large scale visual search algorithm and system infrastructure at Alibaba. The following challenges are discussed under the E-commercial circumstance at Alibaba (a) how to handle heterogeneous image data and bridge the gap between real-shot images from user query and the online images. (b) how to deal with large scale indexing for massive updating data. (c) how to train deep models for effective feature representation without huge human annotations. (d) how to improve the user engagement by considering the quality of the content. We take advantage of large image collection of Alibaba and state-of-the-art deep learning techniques to perform visual search at scale. We present solutions and implementation details to overcome those problems and also share our learnings from building such a large scale commercial visual search engine. Specifically, model and search-based fusion approach is introduced to effectively predict categories. Also, we propose a deep CNN model for joint detection and feature learning by mining user click behavior. The binary index engine is designed to scale up indexing without compromising recall and precision. Finally, we apply all the stages into an end-to-end system architecture, which can simultaneously achieve highly efficient and scalable performance adapting to real-shot images. Extensive experiments demonstrate the advancement of each module in our system. We hope visual search at Alibaba becomes more widely incorporated into today's commercial applications.
Optimizing the approximation of Average Precision (AP) has been widely studied for image retrieval. Limited by the definition of AP, such methods consider both negative and positive instances ranking before each positive instance. However, we claim that only penalizing negative instances before positive ones is enough, because the loss only comes from these negative instances. To this end, we propose a novel loss, namely Penalizing Negative instances before Positive ones (PNP), which can directly minimize the number of negative instances before each positive one. In addition, AP-based methods adopt a fixed and sub-optimal gradient assignment strategy. Therefore, we systematically investigate different gradient assignment solutions via constructing derivative functions of the loss, resulting in PNP-I with increasing derivative functions and PNP-D with decreasing ones. PNP-I focuses more on the hard positive instances by assigning larger gradients to them and tries to make all relevant instances closer. In contrast, PNP-D pays less attention to such instances and slowly corrects them. For most real-world data, one class usually contains several local clusters. PNP-I blindly gathers these clusters while PNP-D keeps them as they were. Therefore, PNP-D is more superior. Experiments on three standard retrieval datasets show consistent results with the above analysis. Extensive evaluations demonstrate that PNP-D achieves the state-of-the-art performance. Code is available at https://github.com/interestingzhuo/PNPloss
Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted the attention of the computer vision community due to it's real-world applications, and the more realistic and challenging setting than found in SBIR. ZS-SBIR inherits the main challenges of multiple computer vision problems including content-based Image Retrieval (CBIR), zero-shot learning and domain adaptation. The majority of previous studies using deep neural networks have achieved improved results through either projecting sketch and images into a common low-dimensional space or transferring knowledge from seen to unseen classes. However, those approaches are trained with complex frameworks composed of multiple deep convolutional neural networks (CNNs) and are dependent on category-level word labels. This increases the requirements on training resources and datasets. In comparison, we propose a simple and efficient framework that does not require high computational training resources, and can be trained on datasets without semantic categorical labels. Furthermore, at training and inference stages our method only uses a single CNN. In this work, a pre-trained ImageNet CNN (e.g., ResNet50) is fine-tuned with three proposed learning objects: domain-aware quadruplet loss, semantic classification loss, and semantic knowledge preservation loss. The domain-aware quadruplet and semantic classification losses are introduced to learn discriminative, semantic and domain invariant features through considering ZS-SBIR as object detection and verification problem. ...
Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision (e.g., object detection) and the convolutional architecture (e.g., ResNet). Although disregarded in the literature, we find it problematic in terms of both (1) efficiency/speed, that simply extracting input features requires much more computation than the multimodal interaction steps; and (2) expressive power, as it is upper bounded to the expressive power of the visual embedder and its predefined visual vocabulary. In this paper, we present a minimal VLP model, Vision-and-Language Transformer (ViLT), monolithic in the sense that the processing of visual inputs is drastically simplified to just the same convolution-free manner that we process textual inputs. We show that ViLT is up to tens of times faster than previous VLP models, yet with competitive or better downstream task performance. Our code and pre-trained weights are available at https://github.com/dandelin/vilt.
As hashing becomes an increasingly appealing technique for large-scale image retrieval, multi-label hashing is also attracting more attention for the ability to exploit multi-level semantic contents. In this paper, we propose a novel deep hashing method for scalable multi-label image search. Unlike existing approaches with conventional objectives such as contrast and triplet losses, we employ a rank list, rather than pairs or triplets, to provide sufficient global supervision information for all the samples. Specifically, a new rank-consistency objective is applied to align the similarity orders from two spaces, the original space and the hamming space. A powerful loss function is designed to penalize the samples whose semantic similarity and hamming distance are mismatched in two spaces. Besides, a multi-label softmax cross-entropy loss is presented to enhance the discriminative power with a concise formulation of the derivative function. In order to manipulate the neighborhood structure of the samples with different labels, we design a multi-label clustering loss to cluster the hashing vectors of the samples with the same labels by reducing the distances between the samples and their multiple corresponding class centers. The state-of-the-art experimental results achieved on three public multi-label datasets, MIRFLICKR-25K, IAPRTC12 and NUS-WIDE, demonstrate the effectiveness of the proposed method.
Deep hashing methods have shown great retrieval accuracy and efficiency in large-scale image retrieval. How to optimize discrete hash bits is always the focus in deep hashing methods. A common strategy in these methods is to adopt an activation function, e.g. $\operatorname{sigmoid}(\cdot)$ or $\operatorname{tanh}(\cdot)$, and minimize a quantization loss to approximate discrete values. However, this paradigm may make more and more hash bits stuck into the wrong saturated area of the activation functions and never escaped. We call this problem "Dead Bits Problem~(DBP)". Besides, the existing quantization loss will aggravate DBP as well. In this paper, we propose a simple but effective gradient amplifier which acts before activation functions to alleviate DBP. Moreover, we devise an error-aware quantization loss to further alleviate DBP. It avoids the negative effect of quantization loss based on the similarity between two images. The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods. Experimental results on three datasets demonstrate the efficiency of the proposed gradient amplifier and the error-aware quantization loss.
Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations. Focusing on zero-shot image retrieval tasks, we study three important factors which can impact the quality of learned representations: pretraining data, the attention mechanism, and loss functions. By pretraining models on six datasets, we observe that dataset noise and language similarity to our downstream task are important indicators of model performance. Through architectural analysis, we learn that models with a multimodal attention mechanism can outperform deeper models with modality specific attention mechanisms. Finally, we show that successful contrastive losses used in the self-supervised learning literature do not yield similar performance gains when used in multimodal transformers
Deep hashing methods have been shown to be the most efficient approximate nearest neighbor search techniques for large-scale image retrieval. However, existing deep hashing methods have a poor small-sample ranking performance for case-based medical image retrieval. The top-ranked images in the returned query results may be as a different class than the query image. This ranking problem is caused by classification, regions of interest (ROI), and small-sample information loss in the hashing space. To address the ranking problem, we propose an end-to-end framework, called Attention-based Triplet Hashing (ATH) network, to learn low-dimensional hash codes that preserve the classification, ROI, and small-sample information. We embed a spatial-attention module into the network structure of our ATH to focus on ROI information. The spatial-attention module aggregates the spatial information of feature maps by utilizing max-pooling, element-wise maximum, and element-wise mean operations jointly along the channel axis. The triplet cross-entropy loss can help to map the classification information of images and similarity between images into the hash codes. Extensive experiments on two case-based medical datasets demonstrate that our proposed ATH can further improve the retrieval performance compared to the state-of-the-art deep hashing methods and boost the ranking performance for small samples. Compared to the other loss methods, the triplet cross-entropy loss can enhance the classification performance and hash code-discriminability
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics. This abundance of content creation and sharing has introduced new challenges, particularly that of searching databases for similar content-Content Based Image Retrieval (CBIR)-a long-established research area in which improved efficiency and accuracy are needed for real-time retrieval. Artificial intelligence has made progress in CBIR and has significantly facilitated the process of instance search. In this survey we review recent instance retrieval works that are developed based on deep learning algorithms and techniques, with the survey organized by deep network architecture types, deep features, feature embedding and aggregation methods, and network fine-tuning strategies. Our survey considers a wide variety of recent methods, whereby we identify milestone work, reveal connections among various methods and present the commonly used benchmarks, evaluation results, common challenges, and propose promising future directions.
In this paper, we focus on removing interference of motion blur by the derivation of motion blur invariants.Unlike earlier work, we don't restore any blurred image. Based on geometric moment and mathematical model of motion blur, we prove that geometric moments of blurred image and original image are linearly related. Depending on this property, we can analyse whether an existing moment-based feature is invariant to motion blur. Surprisingly, we find some geometric moment invariants are invariants to not only spatial transform but also motion blur. Meanwhile, we test invariance and robustness of these invariants using synthetic and real blur image datasets. And the results show these invariants outperform some widely used blur moment invariants and non-moment image features in image retrieval, classification and template matching.
This paper introduces a plug-and-play descriptor that can be effectively adopted for image retrieval tasks without prior initialization or preparation. The description method utilizes the recently proposed Vision Transformer network while it does not require any training data to adjust parameters. In image retrieval tasks, the use of Handcrafted global and local descriptors has been very successfully replaced, over the last years, by the Convolutional Neural Networks (CNN)-based methods. However, the experimental evaluation conducted in this paper on several benchmarking datasets against 36 state-of-the-art descriptors from the literature demonstrates that a neural network that contains no convolutional layer, such as Vision Transformer, can shape a global descriptor and achieve competitive results. As fine-tuning is not required, the presented methodology's low complexity encourages adoption of the architecture as an image retrieval baseline model, replacing the traditional and well adopted CNN-based approaches and inaugurating a new era in image retrieval approaches.
Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words. However, how to make the most of these alignments to infer more accurate matching scores is still underexplored. In this paper, we propose a novel Similarity Graph Reasoning and Attention Filtration (SGRAF) network for image-text matching. Specifically, the vector-based similarity representations are firstly learned to characterize the local and global alignments in a more comprehensive manner, and then the Similarity Graph Reasoning (SGR) module relying on one graph convolutional neural network is introduced to infer relation-aware similarities with both the local and global alignments. The Similarity Attention Filtration (SAF) module is further developed to integrate these alignments effectively by selectively attending on the significant and representative alignments and meanwhile casting aside the interferences of non-meaningful alignments. We demonstrate the superiority of the proposed method with achieving state-of-the-art performances on the Flickr30K and MSCOCO datasets, and the good interpretability of SGR and SAF modules with extensive qualitative experiments and analyses.
Text-to-image retrieval is an essential task in cross-modal information retrieval, i.e., retrieving relevant images from a large and unlabelled dataset given textual queries. In this paper, we propose VisualSparta, a novel (Visual-text Sparse Transformer Matching) model that shows significant improvement in terms of both accuracy and efficiency. VisualSparta is capable of outperforming previous state-of-the-art scalable methods in MSCOCO and Flickr30K. We also show that it achieves substantial retrieving speed advantages, i.e., for a 1 million image index, VisualSparta using CPU gets ~391X speedup compared to CPU vector search and ~5.4X speedup compared to vector search with GPU acceleration. Experiments show that this speed advantage even gets bigger for larger datasets because VisualSparta can be efficiently implemented as an inverted index. To the best of our knowledge, VisualSparta is the first transformer-based text-to-image retrieval model that can achieve real-time searching for large-scale datasets, with significant accuracy improvement compared to previous state-of-the-art methods.
Modern deep learning methods have achieved great success in machine learning and computer vision fields by learning a set of pre-defined datasets. Howerver, these methods perform unsatisfactorily when applied into real-world situations. The reason of this phenomenon is that learning new tasks leads the trained model quickly forget the knowledge of old tasks, which is referred to as catastrophic forgetting. Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks and ignore the problem existing in embedding networks, which are the basic networks for image retrieval, face recognition, zero-shot learning, etc. Different from traditional incremental classification networks, the semantic gap between the embedding spaces of two adjacent tasks is the main challenge for embedding networks under incremental learning setting. Thus, we propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI), which leverages zero-shot translation to estimate and compensate the semantic gap without any exemplars. Then, we try to learn a unified representation for two adjacent tasks in sequential learning process, which captures the relationships of previous classes and current classes precisely. In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks. We conduct extensive experiments on CUB-200-2011 and CIFAR100, and the experiment results prove the effectiveness of our method. The code of our method has been released.
Visual place recognition is an important subproblem of mobile robot localization. Since it is a special case of image retrieval, the basic source of information is the pairwise similarity of image descriptors. However, the embedding of the image retrieval problem in this robotic task provides additional structure that can be exploited, e.g. spatio-temporal consistency. Several algorithms exist to exploit this structure, e.g., sequence processing approaches or descriptor standardization approaches for changing environments. In this paper, we propose a graph-based framework to systematically exploit different types of additional structure and information. The graphical model is used to formulate a non-linear least squares problem that can be optimized with standard tools. Beyond sequences and standardization, we propose the usage of intra-set similarities within the database and/or the query image set as additional source of information. If available, our approach also allows to seamlessly integrate additional knowledge about poses of database images. We evaluate the system on a variety of standard place recognition datasets and demonstrate performance improvements for a large number of different configurations including different sources of information, different types of constraints, and online or offline place recognition setups.