PyTorchKR Papers

최신 논문

총 475편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2410.22347

GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reduction

Embedding models can generate high-dimensional vectors whose similarity reflects semantic affinities. Thus, accurately and timely retrieving those vectors in a large collection that are similar to a given query has become a critical component of a wide range of applications. In particular, cross-modal retrieval (e.g., where a text query is used to find images) is gaining momentum rapidly. Here, it is challenging to achieve high accuracy as the queries often have different statistical distributions than the database vectors. Moreover, the high vector dimensionality puts these search systems under compute and memory pressure, leading to subpar performance. In this work, we present new linear and nonlinear methods for dimensionality reduction to accelerate high-dimensional vector search while maintaining accuracy in settings with in-distribution (ID) and out-of-distribution (OOD) queries. The linear LeanVec-Sphering outperforms other linear methods, trains faster, comes with no hyperparameters, and allows to set the target dimensionality more flexibly. The nonlinear Generalized LeanVec (GleanVec) uses a piecewise linear scheme to further improve the search accuracy while remaining computationally nimble. Initial experimental results show that LeanVec-Sphering and GleanVec push the state of the art for vector search.

arXiv:2411.00683공식 코드 · Papers with Code

TaxaBind: A Unified Embedding Space for Ecological Applications

We present TaxaBind, a unified embedding space for characterizing any species of interest. TaxaBind is a multimodal embedding space across six modalities: ground-level images of species, geographic location, satellite image, text, audio, and environmental features, useful for solving ecological problems. To learn this joint embedding space, we leverage ground-level images of species as a binding modality. We propose multimodal patching, a technique for effectively distilling the knowledge from various modalities into the binding modality. We construct two large datasets for pretraining: iSatNat with species images and satellite images, and iSoundNat with species images and audio. Additionally, we introduce TaxaBench-8k, a diverse multimodal dataset with six paired modalities for evaluating deep learning models on ecological tasks. Experiments with TaxaBind demonstrate its strong zero-shot and emergent capabilities on a range of tasks including species classification, cross-model retrieval, and audio classification. The datasets and models are made available at https://github.com/mvrl/TaxaBind.

arXiv:2410.23715공식 코드 · Papers with Code

Towards Cross-Modal Text-Molecule Retrieval with Better Modality Alignment

Cross-modal text-molecule retrieval model aims to learn a shared feature space of the text and molecule modalities for accurate similarity calculation, which facilitates the rapid screening of molecules with specific properties and activities in drug design. However, previous works have two main defects. First, they are inadequate in capturing modality-shared features considering the significant gap between text sequences and molecule graphs. Second, they mainly rely on contrastive learning and adversarial training for cross-modality alignment, both of which mainly focus on the first-order similarity, ignoring the second-order similarity that can capture more structural information in the embedding space. To address these issues, we propose a novel cross-modal text-molecule retrieval model with two-fold improvements. Specifically, on the top of two modality-specific encoders, we stack a memory bank based feature projector that contain learnable memory vectors to extract modality-shared features better. More importantly, during the model training, we calculate four kinds of similarity distributions (text-to-text, text-to-molecule, molecule-to-molecule, and molecule-to-text similarity distributions) for each instance, and then minimize the distance between these similarity distributions (namely second-order similarity losses) to enhance cross-modal alignment. Experimental results and analysis strongly demonstrate the effectiveness of our model. Particularly, our model achieves SOTA performance, outperforming the previously-reported best result by 6.4%.

arXiv:2410.23370공식 코드 · Papers with Code

Multilingual Vision-Language Pre-training for the Remote Sensing Domain

Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific domain has relied on model fine-tuning with the standard contrastive objective, using existing human-labeled image-caption datasets, or using synthetic data corresponding to image-caption pairs derived from other annotations over remote sensing images (e.g., object classes). The use of different pre-training mechanisms has received less attention, and only a few exceptions have considered multilingual inputs. This work proposes a novel vision-and-language model for the remote sensing domain, exploring the fine-tuning of a multilingual CLIP model and testing the use of a self-supervised method based on aligning local and global representations from individual input images, together with the standard CLIP objective. Model training relied on assembling pre-existing datasets of remote sensing images paired with English captions, followed by the use of automated machine translation into nine additional languages. We show that translated data is indeed helpful, e.g. improving performance also on English. Our resulting model, which we named Remote Sensing Multilingual CLIP (RS-M-CLIP), obtains state-of-the-art results in a variety of vision-and-language tasks, including cross-modal and multilingual image-text retrieval, or zero-shot image classification.

arXiv:2410.24114공식 코드 · Papers with Code

Nearest Neighbor Normalization Improves Multimodal Retrieval

Multimodal models leverage large-scale pre-training to achieve strong but still imperfect performance on tasks such as image captioning, visual question answering, and cross-modal retrieval. In this paper, we present a simple and efficient method for correcting errors in trained contrastive image-text retrieval models with no additional training, called Nearest Neighbor Normalization (NNN). We show an improvement on retrieval metrics in both text retrieval and image retrieval for all of the contrastive models that we tested (CLIP, BLIP, ALBEF, SigLIP, BEiT) and for both of the datasets that we used (MS-COCO and Flickr30k). NNN requires a reference database, but does not require any training on this database, and can even increase the retrieval accuracy of a model after finetuning.

arXiv:2410.15387공식 코드 · Papers with Code

Deep Class-guided Hashing for Multi-label Cross-modal Retrieval

Deep hashing, due to its low cost and efficient retrieval advantages, is widely valued in cross-modal retrieval. However, existing cross-modal hashing methods either explore the relationships between data points, which inevitably leads to intra-class dispersion, or explore the relationships between data points and categories while ignoring the preservation of inter-class structural relationships, resulting in the generation of suboptimal hash codes. How to maintain both intra-class aggregation and inter-class structural relationships, In response to this issue, this paper proposes a DCGH method. Specifically, we use proxy loss as the mainstay to maintain intra-class aggregation of data, combined with pairwise loss to maintain inter-class structural relationships, and on this basis, further propose a variance constraint to address the semantic bias issue caused by the combination. A large number of comparative experiments on three benchmark datasets show that the DCGH method has comparable or even better performance compared to existing cross-modal retrieval methods. The code for the implementation of our DCGH framework is available at https://github.com/donnotnormal/DCGH.

arXiv:2410.15624

Test-time Adaptation for Cross-modal Retrieval with Query Shift

The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such an assumption is easily violated in real-world scenarios due to the complexity and diversity of queries, thus leading to the query shift problem. Specifically, query shift refers to the online query stream originating from the domain that follows a different distribution with the source one. In this paper, we observe that query shift would not only diminish the uniformity (namely, within-modality scatter) of the query modality but also amplify the gap between query and gallery modalities. Based on the observations, we propose a novel method dubbed Test-time adaptation for Cross-modal Retrieval (TCR). In brief, TCR employs a novel module to refine the query predictions (namely, retrieval results of the query) and a joint objective to prevent query shift from disturbing the common space, thus achieving online adaptation for the cross-modal retrieval models with query shift. Expensive experiments demonstrate the effectiveness of the proposed TCR against query shift. The code will be released upon acceptance.

arXiv:2410.09733

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling more sophisticated and accurate integration of visual and textual information across various tasks, including image and video captioning, visual question answering, and cross-modal retrieval. Despite VLMs' superior capabilities, researchers lack a comprehensive understanding of their compositionality -- the ability to understand and produce novel combinations of known visual and textual components. Prior benchmarks provide only a relatively rough compositionality evaluation from the perspectives of objects, relations, and attributes while neglecting deeper reasoning about object interactions, counting, and complex compositions. However, compositionality is a critical ability that facilitates coherent reasoning and understanding across modalities for VLMs. To address this limitation, we propose MMCOMPOSITION, a novel human-annotated benchmark for comprehensively and accurately evaluating VLMs' compositionality. Our proposed benchmark serves as a complement to these earlier works. With MMCOMPOSITION, we can quantify and explore the compositionality of the mainstream VLMs. Surprisingly, we find GPT-4o's compositionality inferior to the best open-source model, and we analyze the underlying reasons. Our experimental analysis reveals the limitations of VLMs in fine-grained compositional perception and reasoning, and points to areas for improvement in VLM design and training. Resources available at: https://hanghuacs.github.io/MMComposition/

arXiv:2410.07610

CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features

Multimodal encoders like CLIP excel in tasks such as zero-shot image classification and cross-modal retrieval. However, they require excessive training data. We propose canonical similarity analysis (CSA), which uses two unimodal encoders to replicate multimodal encoders using limited data. CSA maps unimodal features into a multimodal space, using a new similarity score to retain only the multimodal information. CSA only involves the inference of unimodal encoders and a cubic-complexity matrix decomposition, eliminating the need for extensive GPU-based model training. Experiments show that CSA outperforms CLIP while requiring $50,000\times$ fewer multimodal data pairs to bridge the modalities given pre-trained unimodal encoders on ImageNet classification and misinformative news caption detection. CSA surpasses the state-of-the-art method to map unimodal features to multimodal features. We also demonstrate the ability of CSA with modalities beyond image and text, paving the way for future modality pairs with limited paired multimodal data but abundant unpaired unimodal data, such as lidar and text.

arXiv:2410.02182공식 코드 · Papers with Code

BadCM: Invisible Backdoor Attack Against Cross-Modal Learning

Despite remarkable successes in unimodal learning tasks, backdoor attacks against cross-modal learning are still underexplored due to the limited generalization and inferior stealthiness when involving multiple modalities. Notably, since works in this area mainly inherit ideas from unimodal visual attacks, they struggle with dealing with diverse cross-modal attack circumstances and manipulating imperceptible trigger samples, which hinders their practicability in real-world applications. In this paper, we introduce a novel bilateral backdoor to fill in the missing pieces of the puzzle in the cross-modal backdoor and propose a generalized invisible backdoor framework against cross-modal learning (BadCM). Specifically, a cross-modal mining scheme is developed to capture the modality-invariant components as target poisoning areas, where well-designed trigger patterns injected into these regions can be efficiently recognized by the victim models. This strategy is adapted to different image-text cross-modal models, making our framework available to various attack scenarios. Furthermore, for generating poisoned samples of high stealthiness, we conceive modality-specific generators for visual and linguistic modalities that facilitate hiding explicit trigger patterns in modality-invariant regions. To the best of our knowledge, BadCM is the first invisible backdoor method deliberately designed for diverse cross-modal attacks within one unified framework. Comprehensive experimental evaluations on two typical applications, i.e., cross-modal retrieval and VQA, demonstrate the effectiveness and generalization of our method under multiple kinds of attack scenarios. Moreover, we show that BadCM can robustly evade existing backdoor defenses. Our code is available at https://github.com/xandery-geek/BadCM.

arXiv:2410.00263

Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation

Surgical video-language pretraining (VLP) faces unique challenges due to the knowledge domain gap and the scarcity of multi-modal data. This study aims to bridge the gap by addressing issues regarding textual information loss in surgical lecture videos and the spatial-temporal challenges of surgical VLP. We propose a hierarchical knowledge augmentation approach and a novel Procedure-Encoded Surgical Knowledge-Augmented Video-Language Pretraining (PeskaVLP) framework to tackle these issues. The knowledge augmentation uses large language models (LLM) for refining and enriching surgical concepts, thus providing comprehensive language supervision and reducing the risk of overfitting. PeskaVLP combines language supervision with visual self-supervision, constructing hard negative samples and employing a Dynamic Time Warping (DTW) based loss function to effectively comprehend the cross-modal procedural alignment. Extensive experiments on multiple public surgical scene understanding and cross-modal retrieval datasets show that our proposed method significantly improves zero-shot transferring performance and offers a generalist visual representation for further advancements in surgical scene understanding.

arXiv:2409.19961공식 코드 · Papers with Code

Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval

Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine translation (MT) to create pseudo-parallel data pairs, establishing correspondence between visual and non-English textual data. However, aligning their representations poses challenges due to the significant semantic gap between vision and text, as well as the lower quality of non-English representations caused by pre-trained encoders and data noise. To overcome these challenges, we propose LECCR, a novel solution that incorporates the multi-modal large language model (MLLM) to improve the alignment between visual and non-English representations. Specifically, we first employ MLLM to generate detailed visual content descriptions and aggregate them into multi-view semantic slots that encapsulate different semantics. Then, we take these semantic slots as internal features and leverage them to interact with the visual features. By doing so, we enhance the semantic information within the visual features, narrowing the semantic gap between modalities and generating local visual semantics for subsequent multi-level matching. Additionally, to further enhance the alignment between visual and non-English features, we introduce softened matching under English guidance. This approach provides more comprehensive and reliable inter-modal correspondences between visual and non-English features. Extensive experiments on four CCR benchmarks, \ie Multi30K, MSCOCO, VATEX, and MSR-VTT-CN, demonstrate the effectiveness of our proposed method. Code: \url{https://github.com/LiJiaBei-7/leccr}.

arXiv:2409.06644공식 코드 · Papers with Code

EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis

Early detection of eye diseases like glaucoma, macular degeneration, and diabetic retinopathy is crucial for preventing vision loss. While artificial intelligence (AI) foundation models hold significant promise for addressing these challenges, existing ophthalmic foundation models primarily focus on a single modality, whereas diagnosing eye diseases requires multiple modalities. A critical yet often overlooked aspect is harnessing the multi-view information across various modalities for the same patient. Additionally, due to the long-tail nature of ophthalmic diseases, standard fully supervised or unsupervised learning approaches often struggle. Therefore, it is essential to integrate clinical text to capture a broader spectrum of diseases. We propose EyeCLIP, a visual-language foundation model developed using over 2.77 million multi-modal ophthalmology images with partial text data. To fully leverage the large multi-modal unlabeled and labeled data, we introduced a pretraining strategy that combines self-supervised reconstructions, multi-modal image contrastive learning, and image-text contrastive learning to learn a shared representation of multiple modalities. Through evaluation using 14 benchmark datasets, EyeCLIP can be transferred to a wide range of downstream tasks involving ocular and systemic diseases, achieving state-of-the-art performance in disease classification, visual question answering, and cross-modal retrieval. EyeCLIP represents a significant advancement over previous methods, especially showcasing few-shot, even zero-shot capabilities in real-world long-tail scenarios.

arXiv:2409.05929공식 코드 · Papers with Code

M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework

Current multimodal alignment strategies primarily use single or unified modality encoders, while optimizing the alignment on the original token space. Such a framework is easy to implement and incorporate with the pretrained knowledge, but might result in information bias. To deal with such issues, the joint encoding predictive architecture (JEPA) learns the alignment loss on the latent space, with a predictor to convert the input encoding to the output latent space. However, the application of JEPA in multimodal scenarios is limited so far. In this paper, we introduce M3-Jepa, a scalable multimodal alignment framework, with the predictor implemented by a multi-directional mixture of experts (MoE). We demonstrate the framework can maximize the mutual information with information theory derivations, by alternating the optimization between different uni-directional tasks. By thoroughly designed experiments, we show that M3-Jepa can obtain state-of-the-art performance on different modalities and tasks, generalize to unseen datasets and domains, and is computationally efficient in training and inference. Our study indicates that M3-Jepa might provide a new paradigm to self-supervised learning and open-world modeling.

논문 ID: document/1053028

Global–Local Information Soft-Alignment for Cross-Modal Remote-Sensing Image–Text Retrieval

Cross-modal remote-sensing image–text retrieval (CMRSITR) is a challenging task that aims to retrieve target remote-sensing (RS) images based on textual descriptions. However, the modal gap between texts and RS images poses a significant challenge. RS images comprise multiple targets and complex backgrounds, necessitating the mining of both global and local information (GaLR) for effective CMRSITR. Existing approaches primarily focus on local image features while disregarding the local features of the text and their correspondence. These methods typically fuse global and local image features and align them with global text features. However, they struggle to eliminate the influence of cluttered backgrounds and may overlook crucial targets. To address these limitations, we propose a novel framework for CMRSITR based on a transformer architecture, which leverages global–local information soft alignment (GLISA) to enhance retrieval performance. Our framework incorporates a global image extraction module, which captures the global semantic features of image–text pairs and effectively represents the relationships among multiple targets in RS images. In addition, we introduce an adaptive local information extraction (ALIE) module that adaptively mines discriminative local clues from both RS images and texts, aligning the corresponding fine-grained information. To mitigate semantic ambiguities during the alignment of local features, we design a local information soft-alignment (LISA) module. In comparative evaluations using two public CMRSITR datasets, our proposed method achieves state-of-the-art results, surpassing not only traditional cross-modal retrieval methods by a substantial margin but also other contrastive language-image pretraining (CLIP)-based methods.

arXiv:2408.14723

Snap and Diagnose: An Advanced Multimodal Retrieval System for Identifying Plant Diseases in the Wild

Plant disease recognition is a critical task that ensures crop health and mitigates the damage caused by diseases. A handy tool that enables farmers to receive a diagnosis based on query pictures or the text description of suspicious plants is in high demand for initiating treatment before potential diseases spread further. In this paper, we develop a multimodal plant disease image retrieval system to support disease search based on either image or text prompts. Specifically, we utilize the largest in-the-wild plant disease dataset PlantWild, which includes over 18,000 images across 89 categories, to provide a comprehensive view of potential diseases relating to the query. Furthermore, cross-modal retrieval is achieved in the developed system, facilitated by a novel CLIP-based vision-language model that encodes both disease descriptions and disease images into the same latent space. Built on top of the retriever, our retrieval system allows users to upload either plant disease images or disease descriptions to retrieve the corresponding images with similar characteristics from the disease dataset to suggest candidate diseases for end users' consideration.

arXiv:2408.12023

Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them

Cross-modal contrastive pre-training between natural language and other modalities, e.g., vision and audio, has demonstrated astonishing performance and effectiveness across a diverse variety of tasks and domains. In this paper, we investigate whether such natural language supervision can be used for wearable sensor based Human Activity Recognition (HAR), and discover that-surprisingly-it performs substantially worse than standard end-to-end training and self-supervision. We identify the primary causes for this as: sensor heterogeneity and the lack of rich, diverse text descriptions of activities. To mitigate their impact, we also develop strategies and assess their effectiveness through an extensive experimental evaluation. These strategies lead to significant increases in activity recognition, bringing performance closer to supervised and self-supervised training, while also enabling the recognition of unseen activities and cross modal retrieval of videos. Overall, our work paves the way for better sensor-language learning, ultimately leading to the development of foundational models for HAR using wearables.

arXiv:2408.11793

Leveraging Chemistry Foundation Models to Facilitate Structure Focused Retrieval Augmented Generation in Multi-Agent Workflows for Catalyst and Materials Design

Molecular property prediction and generative design via deep learning models has been the subject of intense research given its potential to accelerate development of new, high-performance materials. More recently, these workflows have been significantly augmented with the advent of large language models (LLMs) and systems of autonomous agents capable of utilizing pre-trained models to make predictions in the context of more complex research tasks. While effective, there is still room for substantial improvement within agentic systems on the retrieval of salient information for material design tasks. Within this context, alternative uses of predictive deep learning models, such as leveraging their latent representations to facilitate cross-modal retrieval augmented generation within agentic systems for task-specific materials design, has remained unexplored. Herein, we demonstrate that large, pre-trained chemistry foundation models can serve as a basis for enabling structure-focused, semantic chemistry information retrieval for both small-molecules, complex polymeric materials, and reactions. Additionally, we show the use of chemistry foundation models in conjunction with multi-modal models such as OpenCLIP facilitate unprecedented queries and information retrieval across multiple characterization data domains. Finally, we demonstrate the integration of these models within multi-agent systems to facilitate structure and topological-based natural language queries and information retrieval for different research tasks.

arXiv:2408.07249

Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach

As online video content rapidly grows, the task of text-video retrieval (TVR) becomes increasingly important. A key challenge in TVR is the information asymmetry between video and text: videos are inherently richer in information, while their textual descriptions often capture only fragments of this complexity. This paper introduces a novel, data-centric framework to bridge this gap by enriching textual representations to better match the richness of video content. During training, videos are segmented into event-level clips and captioned to ensure comprehensive coverage. During retrieval, a large language model (LLM) generates semantically diverse queries to capture a broader range of possible matches. To enhance retrieval efficiency, we propose a query selection mechanism that identifies the most relevant and diverse queries, reducing computational cost while improving accuracy. Our method achieves state-of-the-art results across multiple benchmarks, demonstrating the power of data-centric approaches in addressing information asymmetry in TVR. This work paves the way for new research focused on leveraging data to improve cross-modal retrieval.

논문 ID: 6772.36578

UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching

Cross-modal matching has recently gained significant popularity to facilitate retrieval across multi-modal data, and existing works are highly relied on an implicit assumption that the training data pairs are perfectly aligned. However, such an ideal assumption is extremely impossible due to the inevitably mismatched data pairs, a.k.a. noisy correspondence, which can wrongly enforce the mismatched data to be similar and thus induces the performance degradation. Although some recent methods have attempted to address this problem, they still face two challenging issues: 1) un- reliable data division for training inefficiency and 2) unstable pre- diction for matching failure. To address these problems, we pro- pose an efficient Uncertainty-Guided Noisy Correspondence Learning (UGNCL) framework to achieve noise-robust cross-modal matching. Specifically, a novel Uncertainty Guided Division (UGD) algorithm is reliably designed leverage the potential benefits of derived un- certainty to divide the data into clean, noisy and hard partitions, which can effortlessly mitigate the impact of easily-determined noisy pairs. Meanwhile, an efficient Trusted Robust Loss (TRL) is explicitly designed to recast the soft margins, calibrated by confi- dent yet error soft correspondence labels, for the data pairs in the hard partition through the uncertainty, leading to increase/decrease the importance of matched/mismatched pairs and further alleviate the impact of noisy pairs for robustness improvement. Extensive experiments conducted on three public datasets highlight the su- periorities of the proposed framework, and show its competitive performance compared with the state-of-the-arts. The code is avail- able at https://github.com/qxzha/UGNCL.