PyTorchKR Papers

최신 논문

총 232편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2304.13130

Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining

Named entities are ubiquitous in text that naturally accompanies images, especially in domains such as news or Wikipedia articles. In previous work, named entities have been identified as a likely reason for low performance of image-text retrieval models pretrained on Wikipedia and evaluated on named entities-free benchmark datasets. Because they are rarely mentioned, named entities could be challenging to model. They also represent missed learning opportunities for self-supervised models: the link between named entity and object in the image may be missed by the model, but it would not be if the object were mentioned using a more common term. In this work, we investigate hypernymization as a way to deal with named entities for pretraining grounding-based multi-modal models and for fine-tuning on open-vocabulary detection. We propose two ways to perform hypernymization: (1) a ``manual'' pipeline relying on a comprehensive ontology of concepts, and (2) a ``learned'' approach where we train a language model to learn to perform hypernymization. We run experiments on data from Wikipedia and from The New York Times. We report improved pretraining performance on objects of interest following hypernymization, and we show the promise of hypernymization on open-vocabulary detection, specifically on classes not seen during training.

arXiv:2304.13273공식 코드 · Papers with Code

From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping

With the development of Vision-Language Pre-training Models (VLPMs) represented by CLIP and ALIGN, significant breakthroughs have been achieved for association-based visual tasks such as image classification and image-text retrieval by the zero-shot capability of CLIP without fine-tuning. However, CLIP is hard to apply to generation-based tasks. This is due to the lack of decoder architecture and pre-training tasks for generation. Although previous works have created generation capacity for CLIP through additional language models, a modality gap between the CLIP representations of different modalities and the inability of CLIP to model the offset of this gap, which fails the concept to transfer across modalities. To solve the problem, we try to map images/videos to the language modality and generate captions from the language modality. In this paper, we propose the K-nearest-neighbor Cross-modality Mapping (Knight), a zero-shot method from association to generation. With text-only unsupervised training, Knight achieves State-of-the-Art performance in zero-shot methods for image captioning and video captioning. Our code is available at https://github.com/junyangwang0410/Knight.

arXiv:2304.12570공식 코드 · Papers with Code

Learnable Pillar-based Re-ranking for Image-Text Retrieval

Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the higher-order neighbor relations (i.e., a matching structure among multiple data samples). Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. However, it is ineffective to directly extend existing re-ranking algorithms to image-text retrieval. In this paper, we analyze the reason from four perspectives, i.e., generalization, flexibility, sparsity, and asymmetry, and propose a novel learnable pillar-based re-ranking paradigm. Concretely, we first select top-ranked intra- and inter-modal neighbors as pillars, and then reconstruct data samples with the neighbor relations between them and the pillars. In this way, each sample can be mapped into a multimodal pillar space only using similarities, ensuring generalization. After that, we design a neighbor-aware graph reasoning module to flexibly exploit the relations and excavate the sparse positive items within a neighborhood. We also present a structure alignment constraint to promote cross-modal collaboration and align the asymmetric modalities. On top of various base backbones, we carry out extensive experiments on two benchmark datasets, i.e., Flickr30K and MS-COCO, demonstrating the effectiveness, superiority, generalization, and transferability of our proposed re-ranking paradigm.

arXiv:2304.10824공식 코드 · Papers with Code

Rethinking Benchmarks for Cross-modal Image-text Retrieval

Image-text retrieval, as a fundamental and important branch of information retrieval, has attracted extensive research attentions. The main challenge of this task is cross-modal semantic understanding and matching. Some recent works focus more on fine-grained cross-modal semantic matching. With the prevalence of large scale multimodal pretraining models, several state-of-the-art models (e.g. X-VLM) have achieved near-perfect performance on widely-used image-text retrieval benchmarks, i.e. MSCOCO-Test-5K and Flickr30K-Test-1K. In this paper, we review the two common benchmarks and observe that they are insufficient to assess the true capability of models on fine-grained cross-modal semantic matching. The reason is that a large amount of images and texts in the benchmarks are coarse-grained. Based on the observation, we renovate the coarse-grained images and texts in the old benchmarks and establish the improved benchmarks called MSCOCO-FG and Flickr30K-FG. Specifically, on the image side, we enlarge the original image pool by adopting more similar images. On the text side, we propose a novel semi-automatic renovation approach to refine coarse-grained sentences into finer-grained ones with little human effort. Furthermore, we evaluate representative image-text retrieval models on our new benchmarks to demonstrate the effectiveness of our method. We also analyze the capability of models on fine-grained semantic comprehension through extensive experiments. The results show that even the state-of-the-art models have much room for improvement in fine-grained semantic understanding, especially in distinguishing attributes of close objects in images. Our code and improved benchmark datasets are publicly available at: https://github.com/cwj1412/MSCOCO-Flikcr30K_FG, which we hope will inspire further in-depth research on cross-modal retrieval.

arXiv:2304.10254공식 코드 · Papers with Code

Image-text Retrieval via Preserving Main Semantics of Vision

Image-text retrieval is one of the major tasks of cross-modal retrieval. Several approaches for this task map images and texts into a common space to create correspondences between the two modalities. However, due to the content (semantics) richness of an image, redundant secondary information in an image may cause false matches. To address this issue, this paper presents a semantic optimization approach, implemented as a Visual Semantic Loss (VSL), to assist the model in focusing on an image's main content. This approach is inspired by how people typically annotate the content of an image by describing its main content. Thus, we leverage the annotated texts corresponding to an image to assist the model in capturing the main content of the image, reducing the negative impact of secondary content. Extensive experiments on two benchmark datasets (MSCOCO and Flickr30K) demonstrate the superior performance of our method. The code is available at: https://github.com/ZhangXu0963/VSL.

arXiv:2304.09172공식 코드 · Papers with Code

Hyperbolic Image-Text Representations

Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP do not explicitly capture such hierarchy. We propose MERU, a contrastive model that yields hyperbolic representations of images and text. Hyperbolic spaces have suitable geometric properties to embed tree-like data, so MERU can better capture the underlying hierarchy in image-text datasets. Our results show that MERU learns a highly interpretable and structured representation space while being competitive with CLIP's performance on standard multi-modal tasks like image classification and image-text retrieval. Our code and models are available at https://www.github.com/facebookresearch/meru

arXiv:2304.06028

RECLIP: Resource-efficient CLIP by Training with Small Images

We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small images to learn from large-scale language supervision efficiently, and finetune the model with high-resolution data in the end. Since the complexity of the vision transformer heavily depends on input image size, our approach significantly reduces the training resource requirements both in theory and in practice. Using the same batch size and training epoch, RECLIP achieves highly competitive zero-shot classification and image-text retrieval accuracy with 6 to 8x less computational resources and 7 to 9x fewer FLOPs than the baseline. Compared to the state-of-the-art contrastive learning methods, RECLIP demonstrates 5 to 59x training resource savings while maintaining highly competitive zero-shot classification and retrieval performance. Finally, RECLIP matches the state of the art in transfer learning to open-vocabulary detection tasks, achieving 32 APr on LVIS. We hope this work will pave the path for the broader research community to explore language supervised pretraining in resource-friendly settings.

arXiv:2304.03391

Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval

Cross-modal retrieval methods are the preferred tool to search databases for the text that best matches a query image and vice versa. However, image-text retrieval models commonly learn to memorize spurious correlations in the training data, such as frequent object co-occurrence, instead of looking at the actual underlying reasons for the prediction in the image. For image-text retrieval, this manifests in retrieved sentences that mention objects that are not present in the query image. In this work, we introduce ODmAP@k, an object decorrelation metric that measures a model's robustness to spurious correlations in the training data. We use automatic image and text manipulations to control the presence of such object correlations in designated test data. Additionally, our data synthesis technique is used to tackle model biases due to spurious correlations of semantically unrelated objects in the training data. We apply our proposed pipeline, which involves the finetuning of image-text retrieval frameworks on carefully designed synthetic data, to three state-of-the-art models for image-text retrieval. This results in significant improvements for all three models, both in terms of the standard retrieval performance and in terms of our object decorrelation metric. The code is available at https://github.com/ExplainableML/Spurious_CM_Retrieval.

arXiv:2304.01961공식 코드 · Papers with Code

AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation

This paper presents the AToMiC (Authoring Tools for Multimedia Content) dataset, designed to advance research in image/text cross-modal retrieval. While vision-language pretrained transformers have led to significant improvements in retrieval effectiveness, existing research has relied on image-caption datasets that feature only simplistic image-text relationships and underspecified user models of retrieval tasks. To address the gap between these oversimplified settings and real-world applications for multimedia content creation, we introduce a new approach for building retrieval test collections. We leverage hierarchical structures and diverse domains of texts, styles, and types of images, as well as large-scale image-document associations embedded in Wikipedia. We formulate two tasks based on a realistic user model and validate our dataset through retrieval experiments using baseline models. AToMiC offers a testbed for scalable, diverse, and reproducible multimedia retrieval research. Finally, the dataset provides the basis for a dedicated track at the 2023 Text Retrieval Conference (TREC), and is publicly available at https://github.com/TREC-AToMiC/AToMiC.

arXiv:2303.14465공식 코드 · Papers with Code

Equivariant Similarity for Vision-Language Foundation Models

This study explores the concept of equivariance in vision-language foundation models (VLMs), focusing specifically on the multimodal similarity function that is not only the major training objective but also the core delivery to support downstream tasks. Unlike the existing image-text similarity objective which only categorizes matched pairs as similar and unmatched pairs as dissimilar, equivariance also requires similarity to vary faithfully according to the semantic changes. This allows VLMs to generalize better to nuanced and unseen multimodal compositions. However, modeling equivariance is challenging as the ground truth of semantic change is difficult to collect. For example, given an image-text pair about a dog, it is unclear to what extent the similarity changes when the pixel is changed from dog to cat? To this end, we propose EqSim, a regularization loss that can be efficiently calculated from any two matched training pairs and easily pluggable into existing image-text retrieval fine-tuning. Meanwhile, to further diagnose the equivariance of VLMs, we present a new challenging benchmark EqBen. Compared to the existing evaluation sets, EqBen is the first to focus on "visual-minimal change". Extensive experiments show the lack of equivariance in current VLMs and validate the effectiveness of EqSim. Code is available at https://github.com/Wangt-CN/EqBen.

arXiv:2303.11090

Scene Graph Based Fusion Network For Image-Text Retrieval

A critical challenge to image-text retrieval is how to learn accurate correspondences between images and texts. Most existing methods mainly focus on coarse-grained correspondences based on co-occurrences of semantic objects, while failing to distinguish the fine-grained local correspondences. In this paper, we propose a novel Scene Graph based Fusion Network (dubbed SGFN), which enhances the images'/texts' features through intra- and cross-modal fusion for image-text retrieval. To be specific, we design an intra-modal hierarchical attention fusion to incorporate semantic contexts, such as objects, attributes, and relationships, into images'/texts' feature vectors via scene graphs, and a cross-modal attention fusion to combine the contextual semantics and local fusion via contextual vectors. Extensive experiments on public datasets Flickr30K and MSCOCO show that our SGFN performs better than quite a few SOTA image-text retrieval methods.

arXiv:2303.07740

Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening

Under the flourishing development in performance, current image-text retrieval methods suffer from $N$-related time complexity, which hinders their application in practice. Targeting at efficiency improvement, this paper presents a simple and effective keyword-guided pre-screening framework for the image-text retrieval. Specifically, we convert the image and text data into the keywords and perform the keyword matching across modalities to exclude a large number of irrelevant gallery samples prior to the retrieval network. For the keyword prediction, we transfer it into a multi-label classification problem and propose a multi-task learning scheme by appending the multi-label classifiers to the image-text retrieval network to achieve a lightweight and high-performance keyword prediction. For the keyword matching, we introduce the inverted index in the search engine and create a win-win situation on both time and space complexities for the pre-screening. Extensive experiments on two widely-used datasets, i.e., Flickr30K and MS-COCO, verify the effectiveness of the proposed framework. The proposed framework equipped with only two embedding layers achieves $O(1)$ querying time complexity, while improving the retrieval efficiency and keeping its performance, when applied prior to the common image-text retrieval methods. Our code will be released.

arXiv:2303.07240공식 코드 · Papers with Code

PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents

Foundation models trained on large-scale dataset gain a recent surge in CV and NLP. In contrast, development in biomedical domain lags far behind due to data scarcity. To address this issue, we build and release PMC-OA, a biomedical dataset with 1.6M image-caption pairs collected from PubMedCentral's OpenAccess subset, which is 8 times larger than before. PMC-OA covers diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption. While pretraining a CLIP-style model on PMC-OA, our model named PMC-CLIP achieves state-of-the-art results on various downstream tasks, including image-text retrieval on ROCO, MedMNIST image classification, Medical VQA, i.e. +8.1% R@10 on image-text retrieval, +3.9% accuracy on image classification.

arXiv:2303.05692공식 코드 · Papers with Code

Semantic-Preserving Augmentation for Robust Image-Text Retrieval

Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image and text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model decision quality substantially. In this paper, we propose a novel image text retrieval technique, referred to as robust visual semantic embedding (RVSE), which consists of novel image-based and text-based augmentation techniques called semantic preserving augmentation for image (SPAugI) and text (SPAugT). Since SPAugI and SPAugT change the original data in a way that its semantic information is preserved, we enforce the feature extractors to generate semantic aware embedding vectors regardless of the corruption, improving the model robustness significantly. From extensive experiments using benchmark datasets, we show that RVSE outperforms conventional retrieval schemes in terms of image-text retrieval performance.

arXiv:2303.05952

Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning

Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open question how the modality alignment affects the downstream task performance. In this paper, based on an information-theoretic argument, we first prove that exact modality alignment is sub-optimal in general for downstream prediction tasks. Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect modality alignment. To this end, we propose three general approaches to construct latent modality structures. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization. Extensive experiments are conducted on two popular multi-modal representation learning frameworks: the CLIP-based two-tower model and the ALBEF-based fusion model. We test our model on a variety of tasks including zero/few-shot image classification, image-text retrieval, visual question answering, visual reasoning, and visual entailment. Our method achieves consistent improvements over existing methods, demonstrating the effectiveness and generalizability of our proposed approach on latent modality structure regularization.

arXiv:2303.00448

The style transformer with common knowledge optimization for image-text retrieval

Image-text retrieval which associates different modalities has drawn broad attention due to its excellent research value and broad real-world application. However, most of the existing methods haven't taken the high-level semantic relationships ("style embedding") and common knowledge from multi-modalities into full consideration. To this end, we introduce a novel style transformer network with common knowledge optimization (CKSTN) for image-text retrieval. The main module is the common knowledge adaptor (CKA) with both the style embedding extractor (SEE) and the common knowledge optimization (CKO) modules. Specifically, the SEE uses the sequential update strategy to effectively connect the features of different stages in SEE. The CKO module is introduced to dynamically capture the latent concepts of common knowledge from different modalities. Besides, to get generalized temporal common knowledge, we propose a sequential update strategy to effectively integrate the features of different layers in SEE with previous common feature units. CKSTN demonstrates the superiorities of the state-of-the-art methods in image-text retrieval on MSCOCO and Flickr30K datasets. Moreover, CKSTN is constructed based on the lightweight transformer which is more convenient and practical for the application of real scenes, due to the better performance and lower parameters.

arXiv:2302.08888공식 코드 · Papers with Code

Multimodal Federated Learning via Contrastive Representation Ensemble

With the increasing amount of multimedia data on modern mobile systems and IoT infrastructures, harnessing these rich multimodal data without breaching user privacy becomes a critical issue. Federated learning (FL) serves as a privacy-conscious alternative to centralized machine learning. However, existing FL methods extended to multimodal data all rely on model aggregation on single modality level, which restrains the server and clients to have identical model architecture for each modality. This limits the global model in terms of both model complexity and data capacity, not to mention task diversity. In this work, we propose Contrastive Representation Ensemble and Aggregation for Multimodal FL (CreamFL), a multimodal federated learning framework that enables training larger server models from clients with heterogeneous model architectures and data modalities, while only communicating knowledge on public dataset. To achieve better multimodal representation fusion, we design a global-local cross-modal ensemble strategy to aggregate client representations. To mitigate local model drift caused by two unprecedented heterogeneous factors stemming from multimodal discrepancy (modality gap and task gap), we further propose two inter-modal and intra-modal contrasts to regularize local training, which complements information of the absent modality for uni-modal clients and regularizes local clients to head towards global consensus. Thorough evaluations and ablation studies on image-text retrieval and visual question answering tasks showcase the superiority of CreamFL over state-of-the-art FL methods and its practical value.

arXiv:2302.05608공식 코드 · Papers with Code

Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis

Often, deep network models are purely inductive during training and while performing inference on unseen data. Thus, when such models are used for predictions, it is well known that they often fail to capture the semantic information and implicit dependencies that exist among objects (or concepts) on a population level. Moreover, it is still unclear how domain or prior modal knowledge can be specified in a backpropagation friendly manner, especially in large-scale and noisy settings. In this work, we propose an end-to-end vision and language model incorporating explicit knowledge graphs. We also introduce an interactive out-of-distribution (OOD) layer using implicit network operator. The layer is used to filter noise that is brought by external knowledge base. In practice, we apply our model on several vision and language downstream tasks including visual question answering, visual reasoning, and image-text retrieval on different datasets. Our experiments show that it is possible to design models that perform similarly to state-of-art results but with significantly fewer samples and training time.

arXiv:2302.06605공식 코드 · Papers with Code

UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes unsustainable due to heavy computational and storage costs. This paper proposes UniAdapter, which unifies unimodal and multimodal adapters for parameter-efficient cross-modal adaptation on pre-trained vision-language models. Specifically, adapters are distributed to different modalities and their interactions, with the total number of tunable parameters reduced by partial weight sharing. The unified and knowledge-sharing design enables powerful cross-modal representations that can benefit various downstream tasks, requiring only 1.0%-2.0% tunable parameters of the pre-trained model. Extensive experiments on 6 cross-modal downstream benchmarks (including video-text retrieval, image-text retrieval, VideoQA, and VQA) show that in most cases, UniAdapter not only outperforms the state-of-the-arts, but even beats the full fine-tuning strategy. Particularly, on the MSRVTT retrieval task, UniAdapter achieves 49.7% recall@1 with 2.2% model parameters, outperforming the latest competitors by 2.0%. The code and models are available at https://github.com/RERV/UniAdapter.

arXiv:2302.02908

LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval

Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from another modality. The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream encoders, however, it faces challenges with low retrieval speed in large-scale retrieval scenarios. In this work, we propose the lexicon-weighting paradigm, where sparse representations in vocabulary space are learned for images and texts to take advantage of the bag-of-words models and efficient inverted indexes, resulting in significantly reduced retrieval latency. A crucial gap arises from the continuous nature of image data, and the requirement for a sparse vocabulary space representation. To bridge this gap, we introduce a novel pre-training framework, Lexicon-Bottlenecked Language-Image Pre-Training (LexLIP), that learns importance-aware lexicon representations. This framework features lexicon-bottlenecked modules between the dual-stream encoders and weakened text decoders, allowing for constructing continuous bag-of-words bottlenecks to learn lexicon-importance distributions. Upon pre-training with same-scale data, our LexLIP achieves state-of-the-art performance on two benchmark ITR datasets, MSCOCO and Flickr30k. Furthermore, in large-scale retrieval scenarios, LexLIP outperforms CLIP with a 5.5 ~ 221.3X faster retrieval speed and 13.2 ~ 48.8X less index storage memory.