PyTorchKR Papers

최신 논문

총 2,066편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2011.08824

Improving Calibration in Deep Metric Learning With Cross-Example Softmax

Modern image retrieval systems increasingly rely on the use of deep neural networks to learn embedding spaces in which distance encodes the relevance between a given query and image. In this setting, existing approaches tend to emphasize one of two properties. Triplet-based methods capture top-$k$ relevancy, where all top-$k$ scoring documents are assumed to be relevant to a given query Pairwise contrastive models capture threshold relevancy, where all documents scoring higher than some threshold are assumed to be relevant. In this paper, we propose Cross-Example Softmax which combines the properties of top-$k$ and threshold relevancy. In each iteration, the proposed loss encourages all queries to be closer to their matching images than all queries are to all non-matching images. This leads to a globally more calibrated similarity metric and makes distance more interpretable as an absolute measure of relevance. We further introduce Cross-Example Negative Mining, in which each pair is compared to the hardest negative comparisons across the entire batch. Empirically, we show in a series of experiments on Conceptual Captions and Flickr30k, that the proposed method effectively improves global calibration and also retrieval performance.

arXiv:2011.08518공식 코드 · Papers with Code

DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition

Sequence-based place recognition methods for all-weather navigation are well-known for producing state-of-the-art results under challenging day-night or summer-winter transitions. These systems, however, rely on complex handcrafted heuristics for sequential matching - which are applied on top of a pre-computed pairwise similarity matrix between reference and query image sequences of a single route - to further reduce false-positive rates compared to single-frame retrieval methods. As a result, performing multi-frame place recognition can be extremely slow for deployment on autonomous vehicles or evaluation on large datasets, and fail when using relatively short parameter values such as a sequence length of 2 frames. In this paper, we propose DeepSeqSLAM: a trainable CNN+RNN architecture for jointly learning visual and positional representations from a single monocular image sequence of a route. We demonstrate our approach on two large benchmark datasets, Nordland and Oxford RobotCar - recorded over 728 km and 10 km routes, respectively, each during 1 year with multiple seasons, weather, and lighting conditions. On Nordland, we compare our method to two state-of-the-art sequence-based methods across the entire route under summer-winter changes using a sequence length of 2 and show that our approach can get over 72% AUC compared to 27% AUC for Delta Descriptors and 2% AUC for SeqSLAM; while drastically reducing the deployment time from around 1 hour to 1 minute against both. The framework code and video are available at https://mchancan.github.io/deepseqslam

arXiv:2011.06490

Content-based Image Retrieval and the Semantic Gap in the Deep Learning Era

Content-based image retrieval has seen astonishing progress over the past decade, especially for the task of retrieving images of the same object that is depicted in the query image. This scenario is called instance or object retrieval and requires matching fine-grained visual patterns between images. Semantics, however, do not play a crucial role. This brings rise to the question: Do the recent advances in instance retrieval transfer to more generic image retrieval scenarios? To answer this question, we first provide a brief overview of the most relevant milestones of instance retrieval. We then apply them to a semantic image retrieval task and find that they perform inferior to much less sophisticated and more generic methods in a setting that requires image understanding. Following this, we review existing approaches to closing this so-called semantic gap by integrating prior world knowledge. We conclude that the key problem for the further advancement of semantic image retrieval lies in the lack of a standardized task definition and an appropriate benchmark dataset.

arXiv:2011.06224

Decomposing Normal and Abnormal Features of Medical Images for Content-based Image Retrieval

Medical images can be decomposed into normal and abnormal features, which is considered as the compositionality. Based on this idea, we propose an encoder-decoder network to decompose a medical image into two discrete latent codes: a normal anatomy code and an abnormal anatomy code. Using these latent codes, we demonstrate a similarity retrieval by focusing on either normal or abnormal features of medical images.

arXiv:2011.04219공식 코드 · Papers with Code

Mitigating Bias in Set Selection with Noisy Protected Attributes

Subset selection algorithms are ubiquitous in AI-driven applications, including, online recruiting portals and image search engines, so it is imperative that these tools are not discriminatory on the basis of protected attributes such as gender or race. Currently, fair subset selection algorithms assume that the protected attributes are known as part of the dataset. However, protected attributes may be noisy due to errors during data collection or if they are imputed (as is often the case in real-world settings). While a wide body of work addresses the effect of noise on the performance of machine learning algorithms, its effect on fairness remains largely unexamined. We find that in the presence of noisy protected attributes, in attempting to increase fairness without considering noise, one can, in fact, decrease the fairness of the result! Towards addressing this, we consider an existing noise model in which there is probabilistic information about the protected attributes (e.g., [58, 34, 20, 46]), and ask is fair selection possible under noisy conditions? We formulate a ``denoised'' selection problem which functions for a large class of fairness metrics; given the desired fairness goal, the solution to the denoised problem violates the goal by at most a small multiplicative amount with high probability. Although this denoised problem turns out to be NP-hard, we give a linear-programming based approximation algorithm for it. We evaluate this approach on both synthetic and real-world datasets. Our empirical results show that this approach can produce subsets which significantly improve the fairness metrics despite the presence of noisy protected attributes, and, compared to prior noise-oblivious approaches, has better Pareto-tradeoffs between utility and fairness.

arXiv:2011.03234

Efficient image retrieval using multi neural hash codes and bloom filters

This paper aims to deliver an efficient and modified approach for image retrieval using multiple neural hash codes and limiting the number of queries using bloom filters by identifying false positives beforehand. Traditional approaches involving neural networks for image retrieval tasks tend to use higher layers for feature extraction. But it has been seen that the activations of lower layers have proven to be more effective in a number of scenarios. In our approach, we have leveraged the use of local deep convolutional neural networks which combines the powers of both the features of lower and higher layers for creating feature maps which are then compressed using PCA and fed to a bloom filter after binary sequencing using a modified multi k-means approach. The feature maps obtained are further used in the image retrieval process in a hierarchical coarse-to-fine manner by first comparing the images in the higher layers for semantically similar images and then gradually moving towards the lower layers searching for structural similarities. While searching, the neural hashes for the query image are again calculated and queried in the bloom filter which tells us whether the query image is absent in the set or maybe present. If the bloom filter doesn't necessarily rule out the query, then it goes into the image retrieval process. This approach can be particularly helpful in cases where the image store is distributed since the approach supports parallel querying.

arXiv:1706.06064

Recent Advance in Content-based Image Retrieval: A Literature Survey

The explosive increase and ubiquitous accessibility of visual data on the Web have led to the prosperity of research activity in image search or retrieval. With the ignorance of visual content as a ranking clue, methods with text search techniques for visual retrieval may suffer inconsistency between the text words and visual content. Content-based image retrieval (CBIR), which makes use of the representation of visual content to identify relevant images, has attracted sustained attention in recent two decades. Such a problem is challenging due to the intention gap and the semantic gap problems. Numerous techniques have been developed for content-based image retrieval in the last decade. The purpose of this paper is to categorize and evaluate those algorithms proposed during the period of 2003 to 2016. We conclude with several promising directions for future research.

arXiv:2011.02099

Augmenting Images for ASR and TTS through Single-loop and Dual-loop Multimodal Chain Framework

Previous research has proposed a machine speech chain to enable automatic speech recognition (ASR) and text-to-speech synthesis (TTS) to assist each other in semi-supervised learning and to avoid the need for a large amount of paired speech and text data. However, that framework still requires a large amount of unpaired (speech or text) data. A prototype multimodal machine chain was then explored to further reduce the need for a large amount of unpaired data, which could improve ASR or TTS even when no more speech or text data were available. Unfortunately, this framework relied on the image retrieval (IR) model, and thus it was limited to handling only those images that were already known during training. Furthermore, the performance of this framework was only investigated with single-speaker artificial speech data. In this study, we revamp the multimodal machine chain framework with image generation (IG) and investigate the possibility of augmenting image data for ASR and TTS using single-loop and dual-loop architectures on multispeaker natural speech data. Experimental results revealed that both single-loop and dual-loop multimodal chain frameworks enabled ASR and TTS to improve their performance using an image-only dataset.

arXiv:2011.00270

A Privacy-Preserving Content-Based Image Retrieval Scheme Allowing Mixed Use Of Encrypted And Plain Images

In this paper, we propose a novel content based-image retrieval scheme allowing the mixed use of encrypted and plain images for the first time. In the proposed scheme, images are encrypted by a block-scrambling method developed for encryption-then-compression (EtC) systems. The encrypted images, referred to as EtC images, can be compressed with JPEG, as well as for plain images. Image descriptors used for the proposed retrieval is designed to avoid the effect of image encryption. As a result, the use of EtC images and the descriptors allows us to carry out retrieval of both encrypted images and plain ones. In an experiment, the proposed scheme is demonstrated to have the same performance as conventional retrieval methods with plain images, even under the mixed use of plain images and EtC ones.

arXiv:2010.13357

Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network

Fashion products typically feature in compositions of a variety of styles at different clothing parts. In order to distinguish images of different fashion products, we need to extract both appearance (i.e., "how to describe") and localization (i.e.,"where to look") information, and their interactions. To this end, we propose a biologically inspired framework for image-based fashion product retrieval, which mimics the hypothesized twostream visual processing system of human brain. The proposed attentional heterogeneous bilinear network (AHBN) consists of two branches: a deep CNN branch to extract fine-grained appearance attributes and a fully convolutional branch to extract landmark localization information. A joint channel-wise attention mechanism is further applied to the extracted heterogeneous features to focus on important channels, followed by a compact bilinear pooling layer to model the interaction of the two streams. Our proposed framework achieves satisfactory performance on three image-based fashion product retrieval benchmarks.

arXiv:2010.10867공식 코드 · Papers with Code

LCD -- Line Clustering and Description for Place Recognition

Current research on visual place recognition mostly focuses on aggregating local visual features of an image into a single vector representation. Therefore, high-level information such as the geometric arrangement of the features is typically lost. In this paper, we introduce a novel learning-based approach to place recognition, using RGB-D cameras and line clusters as visual and geometric features. We state the place recognition problem as a problem of recognizing clusters of lines instead of individual patches, thus maintaining structural information. In our work, line clusters are defined as lines that make up individual objects, hence our place recognition approach can be understood as object recognition. 3D line segments are detected in RGB-D images using state-of-the-art techniques. We present a neural network architecture based on the attention mechanism for frame-wise line clustering. A similar neural network is used for the description of these clusters with a compact embedding of 128 floating point numbers, trained with triplet loss on training data obtained from the InteriorNet dataset. We show experiments on a large number of indoor scenes and compare our method with the bag-of-words image-retrieval approach using SIFT and SuperPoint features and the global descriptor NetVLAD. Trained only on synthetic data, our approach generalizes well to real-world data captured with Kinect sensors, while also providing information about the geometric arrangement of instances.

arXiv:2010.10197공식 코드 · Papers with Code

ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments

This competition succeeds upon a line of competitions for writer and style analysis of historical document images. In particular, we investigate the performance of large-scale retrieval of historical document fragments in terms of style and writer identification. The analysis of historic fragments is a difficult challenge commonly solved by trained humanists. In comparison to previous competitions, we make the results more meaningful by addressing the issue of sample granularity and moving from writer to page fragment retrieval. The two approaches, style and author identification, provide information on what kind of information each method makes better use of and indirectly contribute to the interpretability of the participating method. Therefore, we created a large dataset consisting of more than 120 000 fragments. Although the most teams submitted methods based on convolutional neural networks, the winning entry achieves an mAP below 40%.

arXiv:2010.09202

Rotation Invariant Aerial Image Retrieval with Group Convolutional Metric Learning

Remote sensing image retrieval (RSIR) is the process of ranking database images depending on the degree of similarity compared to the query image. As the complexity of RSIR increases due to the diversity in shooting range, angle, and location of remote sensors, there is an increasing demand for methods to address these issues and improve retrieval performance. In this work, we introduce a novel method for retrieving aerial images by merging group convolution with attention mechanism and metric learning, resulting in robustness to rotational variations. For refinement and emphasis on important features, we applied channel attention in each group convolution stage. By utilizing the characteristics of group convolution and channel-wise attention, it is possible to acknowledge the equality among rotated but identically located images. The training procedure has two main steps: (i) training the network with Aerial Image Dataset (AID) for classification, (ii) fine-tuning the network with triplet-loss for retrieval with Google Earth South Korea and NWPU-RESISC45 datasets. Results show that the proposed method performance exceeds other state-of-the-art retrieval methods in both rotated and original environments. Furthermore, we utilize class activation maps (CAM) to visualize the distinct difference of main features between our method and baseline, resulting in better adaptability in rotated environments.

arXiv:2010.08020

On the Exploration of Incremental Learning for Fine-grained Image Retrieval

In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting. To this end, we propose an incremental learning method to mitigate retrieval performance degradation caused by the forgetting issue. Without accessing any samples of the original classes, the classifier of the original network provides soft "labels" to transfer knowledge to train the adaptive network, so as to preserve the previous capability for classification. More importantly, a regularization function based on Maximum Mean Discrepancy is devised to minimize the discrepancy of new classes features from the original network and the adaptive network, respectively. Extensive experiments on two datasets show that our method effectively mitigates the catastrophic forgetting on the original classes while achieving high performance on the new classes.

arXiv:2010.07258

Self-Supervised Ranking for Representation Learning

We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two intuitions: first, a good representation of images must yield a high-quality image ranking in a retrieval task; second, we would expect random views of an image to be ranked closer to a reference view of that image than random views of other images. Hence, we model representation learning as a learning to rank problem for image retrieval. We train a representation encoder by maximizing average precision (AP) for ranking, where random views of an image are considered positively related, and that of the other images considered negatives. The new framework, dubbed S2R2, enables computing a global objective on multiple views, compared to the local objective in the popular contrastive learning framework, which is calculated on pairs of views. In principle, by using a ranking criterion, we eliminate reliance on object-centric curated datasets. When trained on STL10 and MS-COCO, S2R2 outperforms SimCLR and the clustering-based contrastive learning model, SwAV, while being much simpler both conceptually and at implementation. On MS-COCO, S2R2 outperforms both SwAV and SimCLR with a larger margin than on STl10. This indicates that S2R2 is more effective on diverse scenes and could eliminate the need for an object-centric large training dataset for self-supervised representation learning.

arXiv:2010.04292공식 코드 · Papers with Code

comp-syn: Perceptually Grounded Word Embeddings with Color

Popular approaches to natural language processing create word embeddings based on textual co-occurrence patterns, but often ignore embodied, sensory aspects of language. Here, we introduce the Python package comp-syn, which provides grounded word embeddings based on the perceptually uniform color distributions of Google Image search results. We demonstrate that comp-syn significantly enriches models of distributional semantics. In particular, we show that (1) comp-syn predicts human judgments of word concreteness with greater accuracy and in a more interpretable fashion than word2vec using low-dimensional word-color embeddings, and (2) comp-syn performs comparably to word2vec on a metaphorical vs. literal word-pair classification task. comp-syn is open-source on PyPi and is compatible with mainstream machine-learning Python packages. Our package release includes word-color embeddings for over 40,000 English words, each associated with crowd-sourced word concreteness judgments.

arXiv:2010.03378

Descriptive analysis of computational methods for automating mammograms with practical applications

Mammography is a vital screening technique for early revealing and identification of breast cancer in order to assist to decrease mortality rate. Practical applications of mammograms are not limited to breast cancer revealing, identification ,but include task based lens design, image compression, image classification, content based image retrieval and a host of others. Mammography computational analysis methods are a useful tool for specialists to reveal hidden features and extract significant information in mammograms. Digital mammograms are mammography images available along with the conventional screen-film mammography to make automation of mammograms easier. In this paper, we descriptively discuss computational advancement in digital mammograms to serve as a compass for research and practice in the domain of computational mammography and related fields. The discussion focuses on research aiming at a variety of applications and automations of mammograms. It covers different perspectives on image pre-processing, feature extraction, application of mammograms, screen-film mammogram, digital mammogram and development of benchmark corpora for experimenting with digital mammograms.

arXiv:2010.03116

DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval

With a small number of labeled samples for training, it can save considerable manpower and material resources, especially when the amount of high spatial resolution remote sensing images (HSR-RSIs) increases considerably. However, many deep models face the problem of overfitting when using a small number of labeled samples. This might degrade HSRRSI retrieval accuracy. Aiming at obtaining more accurate HSR-RSI retrieval performance with small training samples, we develop a deep metric learning approach with generative adversarial network regularization (DML-GANR) for HSR-RSI retrieval. The DML-GANR starts from a high-level feature extraction (HFE) to extract high-level features, which includes convolutional layers and fully connected (FC) layers. Each of the FC layers is constructed by deep metric learning (DML) to maximize the interclass variations and minimize the intraclass variations. The generative adversarial network (GAN) is adopted to mitigate the overfitting problem and validate the qualities of extracted high-level features. DML-GANR is optimized through a customized approach, and the optimal parameters are obtained. The experimental results on the three data sets demonstrate the superior performance of DML-GANR over state-of-the-art techniques in HSR-RSI retrieval.

arXiv:2010.02949

Learning to Represent Image and Text with Denotation Graph

Learning to fuse vision and language information and representing them is an important research problem with many applications. Recent progresses have leveraged the ideas of pre-training (from language modeling) and attention layers in Transformers to learn representation from datasets containing images aligned with linguistic expressions that describe the images. In this paper, we propose learning representations from a set of implied, visually grounded expressions between image and text, automatically mined from those datasets. In particular, we use denotation graphs to represent how specific concepts (such as sentences describing images) can be linked to abstract and generic concepts (such as short phrases) that are also visually grounded. This type of generic-to-specific relations can be discovered using linguistic analysis tools. We propose methods to incorporate such relations into learning representation. We show that state-of-the-art multimodal learning models can be further improved by leveraging automatically harvested structural relations. The representations lead to stronger empirical results on downstream tasks of cross-modal image retrieval, referring expression, and compositional attribute-object recognition. Both our codes and the extracted denotation graphs on the Flickr30K and the COCO datasets are publically available on https://sha-lab.github.io/DG.

arXiv:2010.01148

Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification

Person re-identification (re-ID) requires one to match images of the same person across camera views. As a more challenging task, semi-supervised re-ID tackles the problem that only a number of identities in training data are fully labeled, while the remaining are unlabeled. Assuming that such labeled and unlabeled training data share disjoint identity labels, we propose a novel framework of Semantics-Guided Clustering with Deep Progressive Learning (SGC-DPL) to jointly exploit the above data. By advancing the proposed Semantics-Guided Affinity Propagation (SG-AP), we are able to assign pseudo-labels to selected unlabeled data in a progressive fashion, under the semantics guidance from the labeled ones. As a result, our approach is able to augment the labeled training data in the semi-supervised setting. Our experiments on two large-scale person re-ID benchmarks demonstrate the superiority of our SGC-DPL over state-of-the-art methods across different degrees of supervision. In extension, the generalization ability of our SGC-DPL is also verified in other tasks like vehicle re-ID or image retrieval with the semi-supervised setting.