PyTorchKR Papers

최신 논문

총 2,066편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2307.16395

Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks

In recent times there has been a surge of multi-modal architectures based on Large Language Models, which leverage the zero shot generation capabilities of LLMs and project image embeddings into the text space and then use the auto-regressive capacity to solve tasks such as VQA, captioning, and image retrieval. We name these architectures as "bridge-architectures" as they project from the image space to the text space. These models deviate from the traditional recipe of training transformer based multi-modal models, which involve using large-scale pre-training and complex multi-modal interactions through co or cross attention. However, the capabilities of bridge architectures have not been tested on complex visual reasoning tasks which require fine grained analysis about the image. In this project, we investigate the performance of these bridge-architectures on the NLVR2 dataset, and compare it to state-of-the-art transformer based architectures. We first extend the traditional bridge architectures for the NLVR2 dataset, by adding object level features to faciliate fine-grained object reasoning. Our analysis shows that adding object level features to bridge architectures does not help, and that pre-training on multi-modal data is key for good performance on complex reasoning tasks such as NLVR2. We also demonstrate some initial results on a recently bridge-architecture, LLaVA, in the zero shot setting and analyze its performance.

arXiv:2307.13254

Conditional Cross Attention Network for Multi-Space Embedding without Entanglement in Only a SINGLE Network

Many studies in vision tasks have aimed to create effective embedding spaces for single-label object prediction within an image. However, in reality, most objects possess multiple specific attributes, such as shape, color, and length, with each attribute composed of various classes. To apply models in real-world scenarios, it is essential to be able to distinguish between the granular components of an object. Conventional approaches to embedding multiple specific attributes into a single network often result in entanglement, where fine-grained features of each attribute cannot be identified separately. To address this problem, we propose a Conditional Cross-Attention Network that induces disentangled multi-space embeddings for various specific attributes with only a single backbone. Firstly, we employ a cross-attention mechanism to fuse and switch the information of conditions (specific attributes), and we demonstrate its effectiveness through a diverse visualization example. Secondly, we leverage the vision transformer for the first time to a fine-grained image retrieval task and present a simple yet effective framework compared to existing methods. Unlike previous studies where performance varied depending on the benchmark dataset, our proposed method achieved consistent state-of-the-art performance on the FashionAI, DARN, DeepFashion, and Zappos50K benchmark datasets.

arXiv:2307.11702

SACReg: Scene-Agnostic Coordinate Regression for Visual Localization

Scene coordinates regression (SCR), i.e., predicting 3D coordinates for every pixel of a given image, has recently shown promising potential. However, existing methods remain limited to small scenes memorized during training, and thus hardly scale to realistic datasets and scenarios. In this paper, we propose a generalized SCR model trained once to be deployed in new test scenes, regardless of their scale, without any finetuning. Instead of encoding the scene coordinates into the network weights, our model takes as input a database image with some sparse 2D pixel to 3D coordinate annotations, extracted from e.g. off-the-shelf Structure-from-Motion or RGB-D data, and a query image for which are predicted a dense 3D coordinate map and its confidence, based on cross-attention. At test time, we rely on existing off-the-shelf image retrieval systems and fuse the predictions from a shortlist of relevant database images w.r.t. the query. Afterwards camera pose is obtained using standard Perspective-n-Point (PnP). Starting from selfsupervised CroCo pretrained weights, we train our model on diverse datasets to ensure generalizabilty across various scenarios, and significantly outperform other scene regression approaches, including scene-specific models, on multiple visual localization benchmarks. Finally, we show that the database representation of images and their 2D-3D annotations can be highly compressed with negligible loss of localization performance.

arXiv:2307.09172

Jean-Luc Picard at Touché 2023: Comparing Image Generation, Stance Detection and Feature Matching for Image Retrieval for Arguments

Participating in the shared task "Image Retrieval for arguments", we used different pipelines for image retrieval containing Image Generation, Stance Detection, Preselection and Feature Matching. We submitted four different runs with different pipeline layout and compare them to given baseline. Our pipelines perform similarly to the baseline.

arXiv:2307.08417공식 코드 · Papers with Code

Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition

Visual Place recognition is commonly addressed as an image retrieval problem. However, retrieval methods are impractical to scale to large datasets, densely sampled from city-wide maps, since their dimension impact negatively on the inference time. Using approximate nearest neighbour search for retrieval helps to mitigate this issue, at the cost of a performance drop. In this paper we investigate whether we can effectively approach this task as a classification problem, thus bypassing the need for a similarity search. We find that existing classification methods for coarse, planet-wide localization are not suitable for the fine-grained and city-wide setting. This is largely due to how the dataset is split into classes, because these methods are designed to handle a sparse distribution of photos and as such do not consider the visual aliasing problem across neighbouring classes that naturally arises in dense scenarios. Thus, we propose a partitioning scheme that enables a fast and accurate inference, preserving a simple learning procedure, and a novel inference pipeline based on an ensemble of novel classifiers that uses the prototypes learned via an angular margin loss. Our method, Divide&Classify (D&C), enjoys the fast inference of classification solutions and an accuracy competitive with retrieval methods on the fine-grained, city-wide setting. Moreover, we show that D&C can be paired with existing retrieval pipelines to speed up computations by over 20 times while increasing their recall, leading to new state-of-the-art results.

arXiv:2307.08316공식 코드 · Papers with Code

Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification

Visible-Infrared person Re-IDentification (VI-ReID) is a challenging cross-modality image retrieval task that aims to match pedestrians' images across visible and infrared cameras. To solve the modality gap, existing mainstream methods adopt a learning paradigm converting the image retrieval task into an image classification task with cross-entropy loss and auxiliary metric learning losses. These losses follow the strategy of adjusting the distribution of extracted embeddings to reduce the intra-class distance and increase the inter-class distance. However, such objectives do not precisely correspond to the final test setting of the retrieval task, resulting in a new gap at the optimization level. By rethinking these keys of VI-ReID, we propose a simple and effective method, the Multi-level Cross-modality Joint Alignment (MCJA), bridging both modality and objective-level gap. For the former, we design the Modality Alignment Augmentation, which consists of three novel strategies, the weighted grayscale, cross-channel cutmix, and spectrum jitter augmentation, effectively reducing modality discrepancy in the image space. For the latter, we introduce a new Cross-Modality Retrieval loss. It is the first work to constrain from the perspective of the ranking list, aligning with the goal of the testing stage. Moreover, based on the global feature only, our method exhibits good performance and can serve as a strong baseline method for the VI-ReID community.

arXiv:2307.08015공식 코드 · Papers with Code

Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer

Image retrieval-based cross-view localization methods often lead to very coarse camera pose estimation, due to the limited sampling density of the database satellite images. In this paper, we propose a method to increase the accuracy of a ground camera's location and orientation by estimating the relative rotation and translation between the ground-level image and its matched/retrieved satellite image. Our approach designs a geometry-guided cross-view transformer that combines the benefits of conventional geometry and learnable cross-view transformers to map the ground-view observations to an overhead view. Given the synthesized overhead view and observed satellite feature maps, we construct a neural pose optimizer with strong global information embedding ability to estimate the relative rotation between them. After aligning their rotations, we develop an uncertainty-guided spatial correlation to generate a probability map of the vehicle locations, from which the relative translation can be determined. Experimental results demonstrate that our method significantly outperforms the state-of-the-art. Notably, the likelihood of restricting the vehicle lateral pose to be within 1m of its Ground Truth (GT) value on the cross-view KITTI dataset has been improved from $35.54\%$ to $76.44\%$, and the likelihood of restricting the vehicle orientation to be within $1^{\circ}$ of its GT value has been improved from $19.64\%$ to $99.10\%$.

arXiv:2307.07407

Phoneme-retrieval; voice recognition; vowels recognition

A phoneme-retrieval technique is proposed, which is due to the particular way of the construction of the network. An initial set of neurons is given. The number of these neurons is approximately equal to the number of typical structures of the data. For example if the network is built for voice retrieval then the number of neurons must be equal to the number of characteristic phonemes of the alphabet of the language spoken by the social group to which the particular person belongs. Usually this task is very complicated and the network can depend critically on the samples used for the learning. If the network is built for image retrieval then it works only if the data to be retrieved belong to a particular set of images. If the network is built for voice recognition it works only for some particular set of words. A typical example is the words used for the flight of airplanes. For example a command like the "airplane should make a turn of 120 degrees towards the east" can be easily recognized by the network if a suitable learning procedure is used.

arXiv:2307.07336공식 코드 · Papers with Code

Risk Controlled Image Retrieval

Most image retrieval research prioritizes improving predictive performance, often overlooking situations where the reliability of predictions is equally important. The gap between model performance and reliability requirements highlights the need for a systematic approach to analyze and address the risks associated with image retrieval. Uncertainty quantification technique can be applied to mitigate this issue by assessing uncertainty for retrieval sets, but it provides only a heuristic estimate of uncertainty rather than a guarantee. To address these limitations, we present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets with coverage guarantee, i.e., retrieval sets that are guaranteed to contain the true nearest neighbors with a predefined probability. RCIR can be easily integrated with existing uncertainty-aware image retrieval systems, agnostic to data distribution and model selection. To the best of our knowledge, this is the first work that provides coverage guarantees to image retrieval. The validity and efficiency of RCIR are demonstrated on four real-world datasets: CAR-196, CUB-200, Pittsburgh, and ChestX-Det.

arXiv:2307.06458

Discovering Image Usage Online: A Case Study With "Flatten the Curve''

Understanding the spread of images across the web helps us understand the reuse of scientific visualizations and their relationship with the public. The "Flatten the Curve" graphic was heavily used during the COVID-19 pandemic to convey a complex concept in a simple form. It displays two curves comparing the impact on case loads for medical facilities if the populace either adopts or fails to adopt protective measures during a pandemic. We use five variants of the "Flatten the Curve" image as a case study for viewing the spread of an image online. To evaluate its spread, we leverage three information channels: reverse image search engines, social media, and web archives. Reverse image searches give us a current view into image reuse. Social media helps us understand a variant's popularity over time. Web archives help us see when it was preserved, highlighting a view of popularity for future researchers. Our case study leverages document URLs can be used as a proxy for images when studying the spread of images online.

arXiv:2307.05017

Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification

Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools, making the prediction of deep learning models more explainable, transparent, and trustworthy. However, all the CAM-based methods (e.g., CAM, Grad-CAM, and Relevance-CAM) can only be used for interpreting CNN models with fully-connected (FC) layers as a classifier. It is worth noting that many deep learning models classify images without FC layers, e.g., few-shot learning image classification, contrastive learning image classification, and image retrieval tasks. In this work, a post-hoc interpretation tool named feature activation map (FAM) is proposed, which can interpret deep learning models without FC layers as a classifier. In the proposed FAM algorithm, the channel-wise contribution weights are derived from the similarity scores between two image embeddings. The activation maps are linearly combined with the corresponding normalized contribution weights, forming the explanation map for visualization. The quantitative and qualitative experiments conducted on ten deep learning models for few-shot image classification, contrastive learning image classification and image retrieval tasks demonstrate the effectiveness of the proposed FAM algorithm.

arXiv:2307.04047

Threshold-Consistent Margin Loss for Open-World Deep Metric Learning

Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice of using a fixed threshold to declare a match, this gives rise to significant performance variations in terms of false accept rate (FAR) and false reject rate (FRR) across test classes and data distributions. We define this issue in DML as threshold inconsistency. In real-world applications, such inconsistency often complicates the threshold selection process when deploying commercial image retrieval systems. To measure this inconsistency, we propose a novel variance-based metric called Operating-Point-Inconsistency-Score (OPIS) that quantifies the variance in the operating characteristics across classes. Using the OPIS metric, we find that achieving high accuracy levels in a DML model does not automatically guarantee threshold consistency. In fact, our investigation reveals a Pareto frontier in the high-accuracy regime, where existing methods to improve accuracy often lead to degradation in threshold consistency. To address this trade-off, we introduce the Threshold-Consistent Margin (TCM) loss, a simple yet effective regularization technique that promotes uniformity in representation structures across classes by selectively penalizing hard sample pairs. Extensive experiments demonstrate TCM's effectiveness in enhancing threshold consistency while preserving accuracy, simplifying the threshold selection process in practical DML settings.

arXiv:2307.04520

Efficient Match Pair Retrieval for Large-scale UAV Images via Graph Indexed Global Descriptor

SfM (Structure from Motion) has been extensively used for UAV (Unmanned Aerial Vehicle) image orientation. Its efficiency is directly influenced by feature matching. Although image retrieval has been extensively used for match pair selection, high computational costs are consumed due to a large number of local features and the large size of the used codebook. Thus, this paper proposes an efficient match pair retrieval method and implements an integrated workflow for parallel SfM reconstruction. First, an individual codebook is trained online by considering the redundancy of UAV images and local features, which avoids the ambiguity of training codebooks from other datasets. Second, local features of each image are aggregated into a single high-dimension global descriptor through the VLAD (Vector of Locally Aggregated Descriptors) aggregation by using the trained codebook, which remarkably reduces the number of features and the burden of nearest neighbor searching in image indexing. Third, the global descriptors are indexed via the HNSW (Hierarchical Navigable Small World) based graph structure for the nearest neighbor searching. Match pairs are then retrieved by using an adaptive threshold selection strategy and utilized to create a view graph for divide-and-conquer based parallel SfM reconstruction. Finally, the performance of the proposed solution has been verified using three large-scale UAV datasets. The test results demonstrate that the proposed solution accelerates match pair retrieval with a speedup ratio ranging from 36 to 108 and improves the efficiency of SfM reconstruction with competitive accuracy in both relative and absolute orientation.

arXiv:2307.03798공식 코드 · Papers with Code

Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints

Models leveraging both visual and textual data such as Contrastive Language-Image Pre-training (CLIP), are the backbone of many recent advances in artificial intelligence. In this work, we show that despite their versatility, such models are vulnerable to what we refer to as fooling master images. Fooling master images are capable of maximizing the confidence score of a CLIP model for a significant number of widely varying prompts, while being either unrecognizable or unrelated to the attacked prompts for humans. The existence of such images is problematic as it could be used by bad actors to maliciously interfere with CLIP-trained image retrieval models in production with comparably small effort as a single image can attack many different prompts. We demonstrate how fooling master images for CLIP (CLIPMasterPrints) can be mined using stochastic gradient descent, projected gradient descent, or blackbox optimization. Contrary to many common adversarial attacks, the blackbox optimization approach allows us to mine CLIPMasterPrints even when the weights of the model are not accessible. We investigate the properties of the mined images, and find that images trained on a small number of image captions generalize to a much larger number of semantically related captions. We evaluate possible mitigation strategies, where we increase the robustness of the model and introduce an approach to automatically detect CLIPMasterPrints to sanitize the input of vulnerable models. Finally, we find that vulnerability to CLIPMasterPrints is related to a modality gap in contrastive pre-trained multi-modal networks. Code available at https://github.com/matfrei/CLIPMasterPrints.

arXiv:2306.17019공식 코드 · Papers with Code

Histopathology Slide Indexing and Search: Are We There Yet?

The search and retrieval of digital histopathology slides is an important task that has yet to be solved. In this case study, we investigate the clinical readiness of three state-of-the-art histopathology slide search engines, Yottixel, SISH, and RetCCL, on three patients with solid tumors. We provide a qualitative assessment of each model's performance in providing retrieval results that are reliable and useful to pathologists. We found that all three image search engines fail to produce consistently reliable results and have difficulties in capturing granular and subtle features of malignancy, limiting their diagnostic accuracy. Based on our findings, we also propose a minimal set of requirements to further advance the development of accurate and reliable histopathology image search engines for successful clinical adoption.

arXiv:2306.15769공식 코드 · Papers with Code

What Makes ImageNet Look Unlike LAION

ImageNet was famously created from Flickr image search results. What if we recreated ImageNet instead by searching the massive LAION dataset based on image captions alone? In this work, we carry out this counterfactual investigation. We find that the resulting ImageNet recreation, which we call LAIONet, looks distinctly unlike the original. Specifically, the intra-class similarity of images in the original ImageNet is dramatically higher than it is for LAIONet. Consequently, models trained on ImageNet perform significantly worse on LAIONet. We propose a rigorous explanation for the discrepancy in terms of a subtle, yet important, difference in two plausible causal data-generating processes for the respective datasets, that we support with systematic experimentation. In a nutshell, searching based on an image caption alone creates an information bottleneck that mitigates the selection bias otherwise present in image-based filtering. Our explanation formalizes a long-held intuition in the community that ImageNet images are stereotypical, unnatural, and overly simple representations of the class category. At the same time, it provides a simple and actionable takeaway for future dataset creation efforts.

arXiv:2306.15651

Dental CLAIRES: Contrastive LAnguage Image REtrieval Search for Dental Research

Learning about diagnostic features and related clinical information from dental radiographs is important for dental research. However, the lack of expert-annotated data and convenient search tools poses challenges. Our primary objective is to design a search tool that uses a user's query for oral-related research. The proposed framework, Contrastive LAnguage Image REtrieval Search for dental research, Dental CLAIRES, utilizes periapical radiographs and associated clinical details such as periodontal diagnosis, demographic information to retrieve the best-matched images based on the text query. We applied a contrastive representation learning method to find images described by the user's text by maximizing the similarity score of positive pairs (true pairs) and minimizing the score of negative pairs (random pairs). Our model achieved a hit@3 ratio of 96% and a Mean Reciprocal Rank (MRR) of 0.82. We also designed a graphical user interface that allows researchers to verify the model's performance with interactions.

arXiv:2306.15368

Mean Field Theory in Deep Metric Learning

In this paper, we explore the application of mean field theory, a technique from statistical physics, to deep metric learning and address the high training complexity commonly associated with conventional metric learning loss functions. By adapting mean field theory for deep metric learning, we develop an approach to design classification-based loss functions from pair-based ones, which can be considered complementary to the proxy-based approach. Applying the mean field theory to two pair-based loss functions, we derive two new loss functions, MeanFieldContrastive and MeanFieldClassWiseMultiSimilarity losses, with reduced training complexity. We extensively evaluate these derived loss functions on three image-retrieval datasets and demonstrate that our loss functions outperform baseline methods in two out of the three datasets.

arXiv:2306.14112

Enhancing Dynamic Image Advertising with Vision-Language Pre-training

In the multimedia era, image is an effective medium in search advertising. Dynamic Image Advertising (DIA), a system that matches queries with ad images and generates multimodal ads, is introduced to improve user experience and ad revenue. The core of DIA is a query-image matching module performing ad image retrieval and relevance modeling. Current query-image matching suffers from limited and inconsistent data, and insufficient cross-modal interaction. Also, the separate optimization of retrieval and relevance models affects overall performance. To address this issue, we propose a vision-language framework consisting of two parts. First, we train a base model on large-scale image-text pairs to learn general multimodal representation. Then, we fine-tune the base model on advertising business data, unifying relevance modeling and retrieval through multi-objective learning. Our framework has been implemented in Baidu search advertising system "Phoneix Nest". Online evaluation shows that it improves cost per mille (CPM) and click-through rate (CTR) by 1.04% and 1.865%.

arXiv:2306.14460공식 코드 · Papers with Code

Hierarchical Matching and Reasoning for Multi-Query Image Retrieval

As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly focus on a single-level similarity between image regions and text queries, which neglects the hierarchical guidance of multi-level similarities and results in incomplete alignments. Besides, the high-level semantic correlations that intrinsically connect different region-query pairs are rarely considered. To address above limitations, we propose a novel Hierarchical Matching and Reasoning Network (HMRN) for MQIR. It disentangles MQIR into three hierarchical semantic representations, which is responsible to capture fine-grained local details, contextual global scopes, and high-level inherent correlations. HMRN comprises two modules: Scalar-based Matching (SM) module and Vector-based Reasoning (VR) module. Specifically, the SM module characterizes the multi-level alignment similarity, which consists of a fine-grained local-level similarity and a context-aware global-level similarity. Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region-query pairs, which further explores the high-level reasoning similarity. Finally, these three-level similarities are aggregated into a joint similarity space to form the ultimate similarity. Extensive experiments on the benchmark dataset demonstrate that our HMRN substantially surpasses the current state-of-the-art methods. For instance, compared with the existing best method Drill-down, the metric R@1 in the last round is improved by 23.4%. Our source codes will be released at https://github.com/LZH-053/HMRN.