PyTorchKR Papers

최신 논문

총 2,066편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2205.15761공식 코드 · Papers with Code

Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark

Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two purposes: (1) provide an approximate pose estimate or (2) determine which parts of the scene are potentially visible in a given query image. It is common practice to use state-of-the-art image retrieval algorithms for both of them. These algorithms are often trained for the goal of retrieving the same landmark under a large range of viewpoint changes which often differs from the requirements of visual localization. In order to investigate the consequences for visual localization, this paper focuses on understanding the role of image retrieval for multiple visual localization paradigms. First, we introduce a novel benchmark setup and compare state-of-the-art retrieval representations on multiple datasets using localization performance as metric. Second, we investigate several definitions of "ground truth" for image retrieval. Using these definitions as upper bounds for the visual localization paradigms, we show that there is still sgnificant room for improvement. Third, using these tools and in-depth analysis, we show that retrieval performance on classical landmark retrieval or place recognition tasks correlates only for some but not all paradigms to localization performance. Finally, we analyze the effects of blur and dynamic scenes in the images. We conclude that there is a need for retrieval approaches specifically designed for localization paradigms. Our benchmark and evaluation protocols are available at https://github.com/naver/kapture-localization.

arXiv:2205.15213공식 코드 · Papers with Code

Backpropagation through Combinatorial Algorithms: Identity with Projection Works

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, therefore a meaningful replacement is crucial for effective gradient-based learning. Prior works rely on smoothing the solver with input perturbations, relaxing the solver to continuous problems, or interpolating the loss landscape with techniques that typically require additional solver calls, introduce extra hyper-parameters, or compromise performance. We propose a principled approach to exploit the geometry of the discrete solution space to treat the solver as a negative identity on the backward pass and further provide a theoretical justification. Our experiments demonstrate that such a straightforward hyper-parameter-free approach is able to compete with previous more complex methods on numerous experiments such as backpropagation through discrete samplers, deep graph matching, and image retrieval. Furthermore, we substitute the previously proposed problem-specific and label-dependent margin with a generic regularization procedure that prevents cost collapse and increases robustness.

arXiv:2205.13115공식 코드 · Papers with Code

Fine-grained Image Captioning with CLIP Reward

Modern image captioning models are usually trained with text similarity objectives. However, since reference captions in public datasets often describe the most salient common objects, models trained with text similarity objectives tend to ignore specific and detailed aspects of an image that distinguish it from others. Toward more descriptive and distinctive caption generation, we propose using CLIP, a multimodal encoder trained on huge image-text pairs from web, to calculate multimodal similarity and use it as a reward function. We also propose a simple finetuning strategy of the CLIP text encoder to improve grammar that does not require extra text annotation. This completely eliminates the need for reference captions during the reward computation. To comprehensively evaluate descriptive captions, we introduce FineCapEval, a new dataset for caption evaluation with fine-grained criteria: overall, background, object, relations. In our experiments on text-to-image retrieval and FineCapEval, the proposed CLIP-guided model generates more distinctive captions than the CIDEr-optimized model. We also show that our unsupervised grammar finetuning of the CLIP text encoder alleviates the degeneration problem of the naive CLIP reward. Lastly, we show human analysis where the annotators strongly prefer the CLIP reward to the CIDEr and MLE objectives according to various criteria. Code and Data: https://github.com/j-min/CLIP-Caption-Reward

arXiv:2205.12522

Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset

Research in massively multilingual image captioning has been severely hampered by a lack of high-quality evaluation datasets. In this paper we present the Crossmodal-3600 dataset (XM3600 in short), a geographically diverse set of 3600 images annotated with human-generated reference captions in 36 languages. The images were selected from across the world, covering regions where the 36 languages are spoken, and annotated with captions that achieve consistency in terms of style across all languages, while avoiding annotation artifacts due to direct translation. We apply this benchmark to model selection for massively multilingual image captioning models, and show superior correlation results with human evaluations when using XM3600 as golden references for automatic metrics.

arXiv:2205.12544

Deep Dense Local Feature Matching and Vehicle Removal for Indoor Visual Localization

Visual localization is an essential component of intelligent transportation systems, enabling broad applications that require understanding one's self location when other sensors are not available. It is mostly tackled by image retrieval such that the location of a query image is determined by its closest match in the previously collected images. Existing approaches focus on large scale localization where landmarks are helpful in finding the location. However, visual localization becomes challenging in small scale environments where objects are hardly recognizable. In this paper, we propose a visual localization framework that robustly finds the match for a query among the images collected from indoor parking lots. It is a challenging problem when the vehicles in the images share similar appearances and are frequently replaced such as parking lots. We propose to employ a deep dense local feature matching that resembles human perception to find correspondences and eliminating matches from vehicles automatically with a vehicle detector. The proposed solution is robust to the scenes with low textures and invariant to false matches caused by vehicles. We compare our framework with alternatives to validate our superiority on a benchmark dataset containing 267 pre-collected images and 99 query images taken from 34 sections of a parking lot. Our method achieves 86.9 percent accuracy, outperforming the alternatives.

arXiv:2205.10878공식 코드 · Papers with Code

Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval

The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks. In this paper, we investigate an extremely challenging task: given a ground-view image of a landmark, we aim to achieve cross-view geo-localization by searching out its corresponding satellite-view images. Specifically, the challenge comes from the gap between ground-view and satellite-view, which includes not only large viewpoint changes (some parts of the landmark may be invisible from front view to top view) but also highly irrelevant background (the target landmark tend to be hidden in other surrounding buildings), making it difficult to learn a common representation or a suitable mapping. To address this issue, we take advantage of drone-view information as a bridge between ground-view and satellite-view domains. We propose a Peer Learning and Cross Diffusion (PLCD) framework. PLCD consists of three parts: 1) a peer learning across ground-view and drone-view to find visible parts to benefit ground-drone cross-view representation learning; 2) a patch-based network for satellite-drone cross-view representation learning; 3) a cross diffusion between ground-drone space and satellite-drone space. Extensive experiments conducted on the University-Earth and University-Google datasets show that our method outperforms state-of-the-arts significantly.

arXiv:2205.11195

Deep Image Retrieval is not Robust to Label Noise

Large-scale datasets are essential for the success of deep learning in image retrieval. However, manual assessment errors and semi-supervised annotation techniques can lead to label noise even in popular datasets. As previous works primarily studied annotation quality in image classification tasks, it is still unclear how label noise affects deep learning approaches to image retrieval. In this work, we show that image retrieval methods are less robust to label noise than image classification ones. Furthermore, we, for the first time, investigate different types of label noise specific to image retrieval tasks and study their effect on model performance.

arXiv:2205.10178공식 코드 · Papers with Code

Visually-Augmented Language Modeling

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which precludes them from utilizing relevant visual information when necessary. To address this, we propose a novel pre-training framework, named VaLM, to Visually-augment text tokens with retrieved relevant images for Language Modeling. Specifically, VaLM builds on a novel latent text-image alignment method via an image retrieval module to fetch corresponding images given a textual context. With the visually-augmented context, VaLM uses a visual knowledge fusion layer to enable multimodal grounded language modeling by attending to both text context and visual knowledge in images. We evaluate VaLM on various visual knowledge-intensive commonsense reasoning tasks, which require visual information to excel. The experimental results illustrate that VaLM outperforms all strong language-only and vision-language baselines with substantial gains in reasoning object commonsense including color, size, and shape. Our code is available at https://github.com/Victorwz/VaLM.

arXiv:2205.08935

Deep Features for CBIR with Scarce Data using Hebbian Learning

Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR). In recent work, biologically inspired \textit{Hebbian} learning algorithms have shown promises for DNN training. In this contribution, we study the performance of such algorithms in the development of feature extractors for CBIR tasks. Specifically, we consider a semi-supervised learning strategy in two steps: first, an unsupervised pre-training stage is performed using Hebbian learning on the image dataset; second, the network is fine-tuned using supervised Stochastic Gradient Descent (SGD) training. For the unsupervised pre-training stage, we explore the nonlinear Hebbian Principal Component Analysis (HPCA) learning rule. For the supervised fine-tuning stage, we assume sample efficiency scenarios, in which the amount of labeled samples is just a small fraction of the whole dataset. Our experimental analysis, conducted on the CIFAR10 and CIFAR100 datasets shows that, when few labeled samples are available, our Hebbian approach provides relevant improvements compared to various alternative methods.

arXiv:2205.06126

One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code

People perceive the world with multiple senses (e.g., through hearing sounds, reading words and seeing objects). However, most existing AI systems only process an individual modality. This paper presents an approach that excels at handling multiple modalities of information with a single model. In our "{SkillNet}" model, different parts of the parameters are specialized for processing different modalities. Unlike traditional dense models that always activate all the model parameters, our model sparsely activates parts of the parameters whose skills are relevant to the task. Such model design enables SkillNet to learn skills in a more interpretable way. We develop our model for five modalities including text, image, sound, video and code. Results show that, SkillNet performs comparably to five modality-specific fine-tuned models. Moreover, our model supports self-supervised pretraining with the same sparsely activated way, resulting in better initialized parameters for different modalities. We find that pretraining significantly improves the performance of SkillNet on five modalities, on par with or even better than baselines with modality-specific pretraining. On the task of Chinese text-to-image retrieval, our final system achieves higher accuracy than existing leading systems including Wukong{ViT-B} and Wenlan 2.0 while using less number of activated parameters.

arXiv:2205.05419

Multi-Label Logo Recognition and Retrieval based on Weighted Fusion of Neural Features

Classifying 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 colors. This work proposes a method that allows visually similar logos to be classified and searched from a set of data according to their shape, color, 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 analyzed, such as the incomplete labeling that trademark registration databases usually contain. The proposal is evaluated considering 76,000 logos (7 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 labeling than a human expert operator, improving the label ranking average precision from 0.53 to 0.68.

arXiv:2205.04883공식 코드 · Papers with Code

Identical Image Retrieval using Deep Learning

In recent years, we know that the interaction with images has increased. Image similarity involves fetching similar-looking images abiding by a given reference image. The target is to find out whether the image searched as a query can result in similar pictures. We are using the BigTransfer Model, which is a state-of-art model itself. BigTransfer(BiT) is essentially a ResNet but pre-trained on a larger dataset like ImageNet and ImageNet-21k with additional modifications. Using the fine-tuned pre-trained Convolution Neural Network Model, we extract the key features and train on the K-Nearest Neighbor model to obtain the nearest neighbor. The application of our model is to find similar images, which are hard to achieve through text queries within a low inference time. We analyse the benchmark of our model based on this application.

arXiv:2205.04255공식 코드 · Papers with Code

Improved Evaluation and Generation of Grid Layouts using Distance Preservation Quality and Linear Assignment Sorting

Images sorted by similarity enables more images to be viewed simultaneously, and can be very useful for stock photo agencies or e-commerce applications. Visually sorted grid layouts attempt to arrange images so that their proximity on the grid corresponds as closely as possible to their similarity. Various metrics exist for evaluating such arrangements, but there is low experimental evidence on correlation between human perceived quality and metric value. We propose Distance Preservation Quality (DPQ) as a new metric to evaluate the quality of an arrangement. Extensive user testing revealed stronger correlation of DPQ with user-perceived quality and performance in image retrieval tasks compared to other metrics. In addition, we introduce Fast Linear Assignment Sorting (FLAS) as a new algorithm for creating visually sorted grid layouts. FLAS achieves very good sorting qualities while improving run time and computational resources.

arXiv:2205.03871

Adversarial Learning of Hard Positives for Place Recognition

Image retrieval methods for place recognition learn global image descriptors that are used for fetching geo-tagged images at inference time. Recent works have suggested employing weak and self-supervision for mining hard positives and hard negatives in order to improve localization accuracy and robustness to visibility changes (e.g. in illumination or view point). However, generating hard positives, which is essential for obtaining robustness, is still limited to hard-coded or global augmentations. In this work we propose an adversarial method to guide the creation of hard positives for training image retrieval networks. Our method learns local and global augmentation policies which will increase the training loss, while the image retrieval network is forced to learn more powerful features for discriminating increasingly difficult examples. This approach allows the image retrieval network to generalize beyond the hard examples presented in the data and learn features that are robust to a wide range of variations. Our method achieves state-of-the-art recalls on the Pitts250 and Tokyo 24/7 benchmarks and outperforms recent image retrieval methods on the rOxford and rParis datasets by a noticeable margin.

arXiv:2205.03860공식 코드 · Papers with Code

CCMB: A Large-scale Chinese Cross-modal Benchmark

Vision-language pre-training (VLP) on large-scale datasets has shown premier performance on various downstream tasks. In contrast to plenty of available benchmarks with English corpus, large-scale pre-training datasets and downstream datasets with Chinese corpus remain largely unexplored. In this work, we build a large-scale high-quality Chinese Cross-Modal Benchmark named CCMB for the research community, which contains the currently largest public pre-training dataset Zero and five human-annotated fine-tuning datasets for downstream tasks. Zero contains 250 million images paired with 750 million text descriptions, plus two of the five fine-tuning datasets are also currently the largest ones for Chinese cross-modal downstream tasks. Along with the CCMB, we also develop a VLP framework named R2D2, applying a pre-Ranking + Ranking strategy to learn powerful vision-language representations and a two-way distillation method (i.e., target-guided Distillation and feature-guided Distillation) to further enhance the learning capability. With the Zero and the R2D2 VLP framework, we achieve state-of-the-art performance on twelve downstream datasets from five broad categories of tasks including image-text retrieval, image-text matching, image caption, text-to-image generation, and zero-shot image classification. The datasets, models, and codes are available at https://github.com/yuxie11/R2D2

arXiv:2205.04449공식 코드 · Papers with Code

Introspective Deep Metric Learning for Image Retrieval

This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images. Conventional deep metric learning methods produce confident semantic distances between images regardless of the uncertainty level. However, we argue that a good similarity model should consider the semantic discrepancies with caution to better deal with ambiguous images for more robust training. To achieve this, we propose to represent an image using not only a semantic embedding but also an accompanying uncertainty embedding, which describes the semantic characteristics and ambiguity of an image, respectively. We further propose an introspective similarity metric to make similarity judgments between images considering both their semantic differences and ambiguities. The proposed IDML framework improves the performance of deep metric learning through uncertainty modeling and attains state-of-the-art results on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets for image retrieval and clustering. We further provide an in-depth analysis of our framework to demonstrate the effectiveness and reliability of IDML. Code is available at: https://github.com/wzzheng/IDML.

arXiv:2205.02849공식 코드 · Papers with Code

AdaTriplet: Adaptive Gradient Triplet Loss with Automatic Margin Learning for Forensic Medical Image Matching

This paper tackles the challenge of forensic medical image matching (FMIM) using deep neural networks (DNNs). FMIM is a particular case of content-based image retrieval (CBIR). The main challenge in FMIM compared to the general case of CBIR, is that the subject to whom a query image belongs may be affected by aging and progressive degenerative disorders, making it difficult to match data on a subject level. CBIR with DNNs is generally solved by minimizing a ranking loss, such as Triplet loss (TL), computed on image representations extracted by a DNN from the original data. TL, in particular, operates on triplets: anchor, positive (similar to anchor) and negative (dissimilar to anchor). Although TL has been shown to perform well in many CBIR tasks, it still has limitations, which we identify and analyze in this work. In this paper, we introduce (i) the AdaTriplet loss -- an extension of TL whose gradients adapt to different difficulty levels of negative samples, and (ii) the AutoMargin method -- a technique to adjust hyperparameters of margin-based losses such as TL and our proposed loss dynamically. Our results are evaluated on two large-scale benchmarks for FMIM based on the Osteoarthritis Initiative and Chest X-ray-14 datasets. The codes allowing replication of this study have been made publicly available at \url{https://github.com/Oulu-IMEDS/AdaTriplet}.

arXiv:2205.02414

Subverting Fair Image Search with Generative Adversarial Perturbations

In this work we explore the intersection fairness and robustness in the context of ranking: when a ranking model has been calibrated to achieve some definition of fairness, is it possible for an external adversary to make the ranking model behave unfairly without having access to the model or training data? To investigate this question, we present a case study in which we develop and then attack a state-of-the-art, fairness-aware image search engine using images that have been maliciously modified using a Generative Adversarial Perturbation (GAP) model. These perturbations attempt to cause the fair re-ranking algorithm to unfairly boost the rank of images containing people from an adversary-selected subpopulation. We present results from extensive experiments demonstrating that our attacks can successfully confer significant unfair advantage to people from the majority class relative to fairly-ranked baseline search results. We demonstrate that our attacks are robust across a number of variables, that they have close to zero impact on the relevance of search results, and that they succeed under a strict threat model. Our findings highlight the danger of deploying fair machine learning algorithms in-the-wild when (1) the data necessary to achieve fairness may be adversarially manipulated, and (2) the models themselves are not robust against attacks.

arXiv:2204.13913공식 코드 · Papers with Code

Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval

Current text-image approaches (e.g., CLIP) typically adopt dual-encoder architecture us- ing pre-trained vision-language representation. However, these models still pose non-trivial memory requirements and substantial incre- mental indexing time, which makes them less practical on mobile devices. In this paper, we present an effective two-stage framework to compress large pre-trained dual-encoder for lightweight text-image retrieval. The result- ing model is smaller (39% of the original), faster (1.6x/2.9x for processing image/text re- spectively), yet performs on par with or bet- ter than the original full model on Flickr30K and MSCOCO benchmarks. We also open- source an accompanying realistic mobile im- age search application.

arXiv:2204.13919

Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval

The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images. A pioneering work introduced backward-compatible training, where the new model can be directly deployed in a backfill-free manner, i.e., the new query can be directly compared to the old gallery features. Despite a possible solution, its improvement in sequential model upgrades is gradually limited by the fixed and under-quality old gallery embeddings. To this end, we propose a new model upgrade paradigm, termed Bidirectional Compatible Training (BiCT), which will upgrade the old gallery embeddings by forward-compatible training towards the embedding space of the backward-compatible new model. We conduct comprehensive experiments to verify the prominent improvement by BiCT and interestingly observe that the inconspicuous loss weight of backward compatibility actually plays an essential role for both backward and forward retrieval performance. To summarize, we introduce a new and valuable problem named privacy-preserving model upgrades, with a proper solution BiCT. Several intriguing insights are further proposed to get the most out of our method.