PyTorchKR Papers

최신 논문

총 2,066편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.06032

Cross-modal Image Retrieval with Deep Mutual Information Maximization

In this paper, we study the cross-modal image retrieval, where the inputs contain a source image plus some text that describes certain modifications to this image and the desired image. Prior work usually uses a three-stage strategy to tackle this task: 1) extract the features of the inputs; 2) fuse the feature of the source image and its modified text to obtain fusion feature; 3) learn a similarity metric between the desired image and the source image + modified text by using deep metric learning. Since classical image/text encoders can learn the useful representation and common pair-based loss functions of distance metric learning are enough for cross-modal retrieval, people usually improve retrieval accuracy by designing new fusion networks. However, these methods do not successfully handle the modality gap caused by the inconsistent distribution and representation of the features of different modalities, which greatly influences the feature fusion and similarity learning. To alleviate this problem, we adopt the contrastive self-supervised learning method Deep InforMax (DIM) to our approach to bridge this gap by enhancing the dependence between the text, the image, and their fusion. Specifically, our method narrows the modality gap between the text modality and the image modality by maximizing mutual information between their not exactly semantically identical representation. Moreover, we seek an effective common subspace for the semantically same fusion feature and desired image's feature by utilizing Deep InforMax between the low-level layer of the image encoder and the high-level layer of the fusion network. Extensive experiments on three large-scale benchmark datasets show that we have bridged the modality gap between different modalities and achieve state-of-the-art retrieval performance.

논문 ID: publication/3461921

Hierarchical Gumbel Attention Network for Text-based Person Search

Text-based person search aims to retrieve the pedestrian images that best match a given textual description from gallery images. Previous methods utilize the soft-attention mechanism to infer the semantic alignments between the regions of image and the corresponding words in sentence. However, these methods may fuse the irrelevant multi-modality features together which cause matching redundancy problem. In this work, we propose a novel hierarchical Gumbel attention network for text-based person search via Gumbel top-k re-parameterization algorithm. Specifically, it adaptively selects the strong semantically relevant image regions and words/phrases from images and texts for precise alignment and similarity calculation. This hard selection strategy is able to fuse the strong-relevant multi-modality features for alleviating the problem of matching redundancy. Meanwhile, a Gumbel top-k reparameterization algorithm is designed as a low-variance, unbiased gradient estimator to handle the discreteness problem of hard attention mechanism by an end-to-end manner. Moreover, a hierarchical adaptive matching strategy is employed by the model from three different granularities, i.e., word-level, phrase-level, and sentencelevel, towards fine-grained matching. Extensive experimental results demonstrate the state-of-the-art performance. Compared the existed best method, we achieve the 8.24% Rank-1 and 7.6% mAP relative improvements in the text-to-image retrieval task, and 5.58% Rank-1 and 6.3% mAP relative improvements in the image-to-text retrieval task on CUHK-PEDES dataset, respectively

arXiv:2103.04778

Bridging the Distribution Gap of Visible-Infrared Person Re-identification with Modality Batch Normalization

Visible-infrared cross-modality person re-identification (VI-ReID), whose aim is to match person images between visible and infrared modality, is a challenging cross-modality image retrieval task. Most existing works integrate batch normalization layers into their neural network, but we found out that batch normalization layers would lead to two types of distribution gap: 1) inter-mini-batch distribution gap -- the distribution gap of the same modality between each mini-batch; 2) intra-mini-batch modality distribution gap -- the distribution gap of different modality within the same mini-batch. To address these problems, we propose a new batch normalization layer called Modality Batch Normalization (MBN), which normalizes each modality sub-mini-batch respectively instead of the whole mini-batch, and can reduce these distribution gap significantly. Extensive experiments show that our MBN is able to boost the performance of VI-ReID models, even with different datasets, backbones and losses.

arXiv:2103.04607

Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification

Visible-Infrared cross-modality person re-identification (VI-ReID), whose aim is to match person images between visible and infrared modality, is a challenging cross-modality image retrieval task. Batch Hard Triplet loss is widely used in person re-identification tasks, but it does not perform well in the Visible-Infrared person re-identification task. Because it only optimizes the hardest triplet for each anchor image within the mini-batch, samples in the hardest triplet may all belong to the same modality, which will lead to the imbalance problem of modality optimization. To address this problem, we adopt the batch all triplet selection strategy, which selects all the possible triplets among samples to optimize instead of the hardest triplet. Furthermore, we introduce Unified Batch All Triplet loss and Cosine Softmax loss to collaboratively optimize the cosine distance between image vectors. Similarly, we rewrite the Hetero Center Triplet loss, which is proposed for VI-ReID task, into a batch all form to improve model performance. Extensive experiments indicate the effectiveness of the proposed methods, which outperform state-of-the-art methods by a wide margin.

arXiv:2103.02927

QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval

We study the query-based attack against image retrieval to evaluate its robustness against adversarial examples under the black-box setting, where the adversary only has query access to the top-k ranked unlabeled images from the database. Compared with query attacks in image classification, which produce adversaries according to the returned labels or confidence score, the challenge becomes even more prominent due to the difficulty in quantifying the attack effectiveness on the partial retrieved list. In this paper, we make the first attempt in Query-based Attack against Image Retrieval (QAIR), to completely subvert the top-k retrieval results. Specifically, a new relevance-based loss is designed to quantify the attack effects by measuring the set similarity on the top-k retrieval results before and after attacks and guide the gradient optimization. To further boost the attack efficiency, a recursive model stealing method is proposed to acquire transferable priors on the target model and generate the prior-guided gradients. Comprehensive experiments show that the proposed attack achieves a high attack success rate with few queries against the image retrieval systems under the black-box setting. The attack evaluations on the real-world visual search engine show that it successfully deceives a commercial system such as Bing Visual Search with 98% attack success rate by only 33 queries on average.

arXiv:2103.02074공식 코드 · Papers with Code

Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition

Sequential matching using hand-crafted heuristics has been standard practice in route-based place recognition for enhancing pairwise similarity results for nearly a decade. However, precision-recall performance of these algorithms dramatically degrades when searching on short temporal window (TW) lengths, while demanding high compute and storage costs on large robotic datasets for autonomous navigation research. Here, influenced by biological systems that robustly navigate spacetime scales even without vision, we develop a joint visual and positional representation learning technique, via a sequential process, and design a learning-based CNN+LSTM architecture, trainable via backpropagation through time, for viewpoint- and appearance-invariant place recognition. Our approach, Sequential Place Learning (SPL), is based on a CNN function that visually encodes an environment from a single traversal, thus reducing storage capacity, while an LSTM temporally fuses each visual embedding with corresponding positional data -- obtained from any source of motion estimation -- for direct sequential inference. Contrary to classical two-stage pipelines, e.g., match-then-temporally-filter, our network directly eliminates false-positive rates while jointly learning sequence matching from a single monocular image sequence, even using short TWs. Hence, we demonstrate that our model outperforms 15 classical methods while setting new state-of-the-art performance standards on 4 challenging benchmark datasets, where one of them can be considered solved with recall rates of 100% at 100% precision, correctly matching all places under extreme sunlight-darkness changes. In addition, we show that SPL can be up to 70x faster to deploy than classical methods on a 729 km route comprising 35,768 consecutive frames. Extensive experiments demonstrate the... Baseline code available at https://github.com/mchancan/deepseqslam

arXiv:2103.01654공식 코드 · Papers with Code

Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query

Text-based image retrieval has seen considerable progress in recent years. However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description. In this work, we introduce the partial-query problem and extensively analyze its influence on text-based image retrieval. Previous interactive methods tackle the problem by passively receiving users' feedback to supplement the incomplete query iteratively, which is time-consuming and requires heavy user effort. Instead, we propose a novel retrieval framework that conducts the interactive process in an Ask-and-Confirm fashion, where AI actively searches for discriminative details missing in the current query, and users only need to confirm AI's proposal. Specifically, we propose an object-based interaction to make the interactive retrieval more user-friendly and present a reinforcement-learning-based policy to search for discriminative objects. Furthermore, since fully-supervised training is often infeasible due to the difficulty of obtaining human-machine dialog data, we present a weakly-supervised training strategy that needs no human-annotated dialogs other than a text-image dataset. Experiments show that our framework significantly improves the performance of text-based image retrieval. Code is avaiable at https://github.com/CuthbertCai/Ask-Confirm.

arXiv:2103.01584

A Practical Framework for ROI Detection in Medical Images -- a case study for hip detection in anteroposterior pelvic radiographs

Purpose Automated detection of region of interest (ROI) is a critical step for many medical image applications such as heart ROIs detection in perfusion MRI images, lung boundary detection in chest X-rays, and femoral head detection in pelvic radiographs. Thus, we proposed a practical framework of ROIs detection in medical images, with a case study for hip detection in anteroposterior (AP) pelvic radiographs. Materials and Methods: We conducted a retrospective study which analyzed hip joints seen on 7,399 AP pelvic radiographs from three diverse sources, including 4,290 high resolution radiographs from Chang Gung Memorial Hospital Osteoarthritis, 3,008 low to medium resolution radiographs from Osteoarthritis Initiative, and 101 heterogeneous radiographs from Google image search engine. We presented a deep learning-based ROI detection framework utilizing single-shot multi-box detector (SSD) with ResNet-101 backbone and customized head structure based on the characteristics of the obtained datasets, whose ground truths were labeled by non-medical annotators in a simple graphical interface. Results: Our method achieved average intersection over union (IoU)=0.8115, average confidence=0.9812, and average precision with threshold IoU=0.5 (AP50)=0.9901 in the independent test set, suggesting that the detected hip regions have appropriately covered main features of the hip joints. Conclusion: The proposed approach featured on low-cost labeling, data-driven model design, and heterogeneous data testing. We have demonstrated the feasibility of training a robust hip region detector for AP pelvic radiographs. This practical framework has a promising potential for a wide range of medical image applications.

arXiv:2103.01913공식 코드 · Papers with Code

WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning

The milestone improvements brought about by deep representation learning and pre-training techniques have led to large performance gains across downstream NLP, IR and Vision tasks. Multimodal modeling techniques aim to leverage large high-quality visio-linguistic datasets for learning complementary information (across image and text modalities). In this paper, we introduce the Wikipedia-based Image Text (WIT) Dataset (https://github.com/google-research-datasets/wit) to better facilitate multimodal, multilingual learning. WIT is composed of a curated set of 37.6 million entity rich image-text examples with 11.5 million unique images across 108 Wikipedia languages. Its size enables WIT to be used as a pretraining dataset for multimodal models, as we show when applied to downstream tasks such as image-text retrieval. WIT has four main and unique advantages. First, WIT is the largest multimodal dataset by the number of image-text examples by 3x (at the time of writing). Second, WIT is massively multilingual (first of its kind) with coverage over 100+ languages (each of which has at least 12K examples) and provides cross-lingual texts for many images. Third, WIT represents a more diverse set of concepts and real world entities relative to what previous datasets cover. Lastly, WIT provides a very challenging real-world test set, as we empirically illustrate using an image-text retrieval task as an example.

arXiv:2103.00370

Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning

Visual search, recommendation, and contrastive similarity learning power technologies that impact billions of users worldwide. Modern model architectures can be complex and difficult to interpret, and there are several competing techniques one can use to explain a search engine's behavior. We show that the theory of fair credit assignment provides a $\textit{unique}$ axiomatic solution that generalizes several existing recommendation- and metric-explainability techniques in the literature. Using this formalism, we show when existing approaches violate "fairness" and derive methods that sidestep these shortcomings and naturally handle counterfactual information. More specifically, we show existing approaches implicitly approximate second-order Shapley-Taylor indices and extend CAM, GradCAM, LIME, SHAP, SBSM, and other methods to search engines. These extensions can extract pairwise correspondences between images from trained $\textit{opaque-box}$ models. We also introduce a fast kernel-based method for estimating Shapley-Taylor indices that require orders of magnitude fewer function evaluations to converge. Finally, we show that these game-theoretic measures yield more consistent explanations for image similarity architectures.

arXiv:2102.13392

Unifying Remote Sensing Image Retrieval and Classification with Robust Fine-tuning

Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated dataset-specific methods. Moreover, typical tasks such as classification and retrieval lack a systematic evaluation on standard benchmarks and training datasets, which make it hard to identify durable and generalizable scientific contributions. We aim at unifying remote sensing image retrieval and classification with a new large-scale training and testing dataset, SF300, including both vertical and oblique aerial images and made available to the research community, and an associated fine-tuning method. We additionally propose a new adversarial fine-tuning method for global descriptors. We show that our framework systematically achieves a boost of retrieval and classification performance on nine different datasets compared to an ImageNet pretrained baseline, with currently no other method to compare to.

arXiv:2102.12728

Scene Retrieval for Contextual Visual Mapping

Visual navigation localizes a query place image against a reference database of place images, also known as a `visual map'. Localization accuracy requirements for specific areas of the visual map, `scene classes', vary according to the context of the environment and task. State-of-the-art visual mapping is unable to reflect these requirements by explicitly targetting scene classes for inclusion in the map. Four different scene classes, including pedestrian crossings and stations, are identified in each of the Nordland and St. Lucia datasets. Instead of re-training separate scene classifiers which struggle with these overlapping scene classes we make our first contribution: defining the problem of `scene retrieval'. Scene retrieval extends image retrieval to classification of scenes defined at test time by associating a single query image to reference images of scene classes. Our second contribution is a triplet-trained convolutional neural network (CNN) to address this problem which increases scene classification accuracy by up to 7% against state-of-the-art networks pre-trained for scene recognition. The second contribution is an algorithm `DMC' that combines our scene classification with distance and memorability for visual mapping. Our analysis shows that DMC includes 64% more images of our chosen scene classes in a visual map than just using distance interval mapping. State-of-the-art visual place descriptors AMOS-Net, Hybrid-Net and NetVLAD are finally used to show that DMC improves scene class localization accuracy by a mean of 3% and localization accuracy of the remaining map images by a mean of 10% across both datasets.

arXiv:2102.11603공식 코드 · Papers with Code

SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition

Visual Place Recognition (VPR) is the task of matching current visual imagery from a camera to images stored in a reference map of the environment. While initial VPR systems used simple direct image methods or hand-crafted visual features, recent work has focused on learning more powerful visual features and further improving performance through either some form of sequential matcher / filter or a hierarchical matching process. In both cases the performance of the initial single-image based system is still far from perfect, putting significant pressure on the sequence matching or (in the case of hierarchical systems) pose refinement stages. In this paper we present a novel hybrid system that creates a high performance initial match hypothesis generator using short learnt sequential descriptors, which enable selective control sequential score aggregation using single image learnt descriptors. Sequential descriptors are generated using a temporal convolutional network dubbed SeqNet, encoding short image sequences using 1-D convolutions, which are then matched against the corresponding temporal descriptors from the reference dataset to provide an ordered list of place match hypotheses. We then perform selective sequential score aggregation using shortlisted single image learnt descriptors from a separate pipeline to produce an overall place match hypothesis. Comprehensive experiments on challenging benchmark datasets demonstrate the proposed method outperforming recent state-of-the-art methods using the same amount of sequential information. Source code and supplementary material can be found at https://github.com/oravus/seqNet.

arXiv:2102.10370

EMDS-5: Environmental Microorganism Image Dataset Fifth Version for Multiple Image Analysis Tasks

Environmental Microorganism Data Set Fifth Version (EMDS-5) is a microscopic image dataset including original Environmental Microorganism (EM) images and two sets of Ground Truth (GT) images. The GT image sets include a single-object GT image set and a multi-object GT image set. The EMDS-5 dataset has 21 types of EMs, each of which contains 20 original EM images, 20 single-object GT images and 20 multi-object GT images. EMDS-5 can realize to evaluate image preprocessing, image segmentation, feature extraction, image classification and image retrieval functions. In order to prove the effectiveness of EMDS-5, for each function, we select the most representative algorithms and price indicators for testing and evaluation. The image preprocessing functions contain two parts: image denoising and image edge detection. Image denoising uses nine kinds of filters to denoise 13 kinds of noises, respectively. In the aspect of edge detection, six edge detection operators are used to detect the edges of the images, and two evaluation indicators, peak-signal to noise ratio and mean structural similarity, are used for evaluation. Image segmentation includes single-object image segmentation and multi-object image segmentation. Six methods are used for single-object image segmentation, while k-means and U-net are used for multi-object segmentation.We extract nine features from the images in EMDS-5 and use the Support Vector Machine classifier for testing. In terms of image classification, we select the VGG16 feature to test different classifiers. We test two types of retrieval approaches: texture feature retrieval and deep learning feature retrieval. We select the last layer of features of these two deep learning networks as feature vectors. We use mean average precision as the evaluation index for retrieval.

arXiv:2102.10802

PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval

Differential Privacy offers strong guarantees such as immutable privacy under post processing. Thus it is often looked to as a solution to learning on scattered and isolated data. This work focuses on supervised manifold learning, a paradigm that can generate fine-tuned manifolds for a target use case. Our contributions are two fold. 1) We present a novel differentially private method \textit{PrivateMail} for supervised manifold learning, the first of its kind to our knowledge. 2) We provide a novel private geometric embedding scheme for our experimental use case. We experiment on private "content based image retrieval" - embedding and querying the nearest neighbors of images in a private manner - and show extensive privacy-utility tradeoff results, as well as the computational efficiency and practicality of our methods.

arXiv:2102.09186공식 코드 · Papers with Code

Hierarchical Attention Fusion for Geo-Localization

Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale variations because they only exploit features from one semantic level for image representations. To address this limitation, we introduce a hierarchical attention fusion network using multi-scale features for geo-localization. We extract the hierarchical feature maps from a convolutional neural network (CNN) and organically fuse the extracted features for image representations. Our training is self-supervised using adaptive weights to control the attention of feature emphasis from each hierarchical level. Evaluation results on the image retrieval and the large-scale geo-localization benchmarks indicate that our method outperforms the existing state-of-the-art methods. Code is available here: \url{https://github.com/YanLiqi/HAF}.

arXiv:2102.09375공식 코드 · Papers with Code

Hierarchical Similarity Learning for Language-based Product Image Retrieval

This paper aims for the language-based product image retrieval task. The majority of previous works have made significant progress by designing network structure, similarity measurement, and loss function. However, they typically perform vision-text matching at certain granularity regardless of the intrinsic multiple granularities of images. In this paper, we focus on the cross-modal similarity measurement, and propose a novel Hierarchical Similarity Learning (HSL) network. HSL first learns multi-level representations of input data by stacked encoders, and object-granularity similarity and image-granularity similarity are computed at each level. All the similarities are combined as the final hierarchical cross-modal similarity. Experiments on a large-scale product retrieval dataset demonstrate the effectiveness of our proposed method. Code and data are available at https://github.com/liufh1/hsl.

arXiv:2102.07917

Information Ranking Using Optimum-Path Forest

The task of learning to rank has been widely studied by the machine learning community, mainly due to its use and great importance in information retrieval, data mining, and natural language processing. Therefore, ranking accurately and learning to rank are crucial tasks. Context-Based Information Retrieval systems have been of great importance to reduce the effort of finding relevant data. Such systems have evolved by using machine learning techniques to improve their results, but they are mainly dependent on user feedback. Although information retrieval has been addressed in different works along with classifiers based on Optimum-Path Forest (OPF), these have so far not been applied to the learning to rank task. Therefore, the main contribution of this work is to evaluate classifiers based on Optimum-Path Forest, in such a context. Experiments were performed considering the image retrieval and ranking scenarios, and the performance of OPF-based approaches was compared to the well-known SVM-Rank pairwise technique and a baseline based on distance calculation. The experiments showed competitive results concerning precision and outperformed traditional techniques in terms of computational load.

arXiv:2102.07611

Colored Kimia Path24 Dataset: Configurations and Benchmarks with Deep Embeddings

The Kimia Path24 dataset has been introduced as a classification and retrieval dataset for digital pathology. Although it provides multi-class data, the color information has been neglected in the process of extracting patches. The staining information plays a major role in the recognition of tissue patterns. To address this drawback, we introduce the color version of Kimia Path24 by recreating sample patches from all 24 scans to propose Kimia Path24C. We run extensive experiments to determine the best configuration for selected patches. To provide preliminary results for setting a benchmark for the new dataset, we utilize VGG16, InceptionV3 and DenseNet-121 model as feature extractors. Then, we use these feature vectors to retrieve test patches. The accuracy of image retrieval using DenseNet was 95.92% while the highest accuracy using InceptionV3 and VGG16 reached 92.45% and 92%, respectively. We also experimented with "deep barcodes" and established that with a small loss in accuracy (e.g., 93.43% for binarized features for DenseNet instead of 95.92% when the features themselves are used), the search operations can be significantly accelerated.

arXiv:2102.07753공식 코드 · Papers with Code

Learning Intra-Batch Connections for Deep Metric Learning

The goal of metric learning is to learn a function that maps samples to a lower-dimensional space where similar samples lie closer than dissimilar ones. Particularly, deep metric learning utilizes neural networks to learn such a mapping. Most approaches rely on losses that only take the relations between pairs or triplets of samples into account, which either belong to the same class or two different classes. However, these methods do not explore the embedding space in its entirety. To this end, we propose an approach based on message passing networks that takes all the relations in a mini-batch into account. We refine embedding vectors by exchanging messages among all samples in a given batch allowing the training process to be aware of its overall structure. Since not all samples are equally important to predict a decision boundary, we use an attention mechanism during message passing to allow samples to weigh the importance of each neighbor accordingly. We achieve state-of-the-art results on clustering and image retrieval on the CUB-200-2011, Cars196, Stanford Online Products, and In-Shop Clothes datasets. To facilitate further research, we make available the code and the models at https://github.com/dvl-tum/intra_batch_connections.