Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of modalities via contrastive learning, their solutions are unsuitable when scaling to multiple modalities. These models typically align each modality to a designated anchor without ensuring the alignment of all modalities with each other, leading to suboptimal performance in tasks requiring a joint understanding of multiple modalities. In this paper, we structurally rethink the pairwise conventional approach to multimodal learning and we present the novel Gramian Representation Alignment Measure (GRAM), which overcomes the above-mentioned limitations. GRAM learns and then aligns $n$ modalities directly in the higher-dimensional space in which modality embeddings lie by minimizing the Gramian volume of the $k$-dimensional parallelotope spanned by the modality vectors, ensuring the geometric alignment of all modalities simultaneously. GRAM can replace cosine similarity in any downstream method, holding for 2 to $n$ modality and providing more meaningful alignment with respect to previous similarity measures. The novel GRAM-based contrastive loss function enhances the alignment of multimodal models in the higher-dimensional embedding space, leading to new state-of-the-art performance in downstream tasks such as video-audio-text retrieval and audio-video classification. The project page, the code, and the pretrained models are available at https://ispamm.github.io/GRAM/.
Contrastive Language-Image Pretraining (CLIP) has been widely used for crossmodal information retrieval and multimodal understanding tasks. However, CLIP models are mainly optimized for crossmodal vision-language tasks and underperform in single-mode text tasks. Moreover, these models are often trained on English datasets and therefore lack multilingual understanding. Additionally, from a visual understanding perspective, previous CLIP-based models exhibit insufficient understanding of visually rich documents. In this work, we propose jina-clip-v2, a contrastive vision-language model trained on text pairs, triplets and image-text pairs via a multi-task and multi-stage contrastive learning paradigm in order to support both text-only and crossmodal tasks. We employ a multilingual text encoder and expand the training dataset to include multilingual texts from 29 non-English languages, including Hindi, Chinese, German, French, and others, as well as images of visually rich documents. We evaluate the model's performance and show that jina-clip-v2 achieves notable improvements over state-of-the-art CLIP-based models in zero-shot text-only retrieval, semantic textual similarity, and crossmodal retrieval tasks in both English and multilingual settings. jina-clip-v2 also provides for flexibility in embedding dimensionality, enabling users to select the granularity of the representations. jina-clip-v2 is publicly available at https://huggingface.co/jinaai/jina-clip-v2.
Vision-Language Models (VLMs) implicitly learn to associate image regions with words from large-scale training data, demonstrating an emergent capability for grounding concepts without dense annotations[14,18,51]. However, the coarse-grained supervision from image-caption pairs is often insufficient to resolve ambiguities in object-concept correspondence, even with enormous data volume. Rich semantic and syntactic structures within the text modality have been overlooked as sources of supervision. Starting from contrastive architectures (BLIP and ALBEF) that show strong intrinsic grounding abilities, we propose HIerarchically STructured Learning (HIST). HIST enhances spatial vision-language alignment without using additional human annotations, by hierarchically decomposing captions into the constituent Subjects, Phrases, and Composite Phrases, and enforcing entailment relation between a parent and its children in the hierarchy. Specifically, we introduce two novel loss functions: (1) Subject Loss, which aligns image content with the subject of the corresponding phrase, acting as an entailment of standard contrastive/matching losses at the Phrase level; (2) Composition Loss, to balance attention across multiple objects. HIST is general, and can be applied to any VLM for which attention between vision and language can be computed. Compared to baseline VLMs, HIST achieves up to +9.8% improvement in visual grounding and +6.3% in multi-object referring segmentation. Surprisingly, the improved spatial grounding leads to improvements in other downstream VLM tasks: +1.1% in image-text retrieval, and +0.2% in visual question answering.
Multimodal learning has recently gained significant popularity, demonstrating impressive performance across various zero-shot classification tasks and a range of perceptive and generative applications. Models such as Contrastive Language-Image Pretraining (CLIP) are designed to bridge different modalities, such as images and text, by learning a shared representation space through contrastive learning. Despite their success, the working mechanisms underlying multimodal learning are not yet well understood. Notably, these models often exhibit a modality gap, where different modalities occupy distinct regions within the shared representation space. In this work, we conduct an in-depth analysis of the emergence of modality gap by characterizing the gradient flow learning dynamics. Specifically, we identify the critical roles of mismatched data pairs and a learnable temperature parameter in causing and perpetuating the modality gap during training. Furthermore, our theoretical insights are validated through experiments on practical CLIP models. These findings provide principled guidance for mitigating the modality gap, including strategies such as appropriate temperature scheduling and modality swapping. Additionally, we demonstrate that closing the modality gap leads to improved performance on tasks such as image-text retrieval.
Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag of words" behavior. At the same time, Large Vision-Language Models (LVLMs), which combine vision encoders with LLMs, have been shown to be capable of detailed vision-language reasoning, yet their autoregressive nature renders them less suitable for discriminative tasks. In this work, we propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs that results in strong discriminative and compositional capabilities. Essentially, our approach converts a generative LVLM into a discriminative one, unlocking its capability for powerful image-text discrimination combined with enhanced language understanding. Our contributions include (1) a carefully designed training/optimization framework that utilizes image-text pairs of variable length and granularity for training the model with both contrastive and next-token prediction losses. This is accompanied by ablation studies that justify the necessity of our framework's components; (2) a parameter-efficient adaptation method using a combination of soft prompting and LoRA adapters; (3) significant improvements over state-of-the-art CLIP-like models of similar size, including standard image-text retrieval benchmarks and notable gains in compositionality.
This report explores the enhancement of text retrieval performance using advanced data refinement techniques. We develop Linq-Embed-Mistral\footnote{\url{https://huggingface.co/Linq-AI-Research/Linq-Embed-Mistral}} by building on the E5-mistral and Mistral-7B-v0.1 models, focusing on sophisticated data crafting, data filtering, and negative mining methods, which are highly tailored to each task, applied to both existing benchmark dataset and highly tailored synthetic dataset generated via large language models (LLMs). Linq-Embed-Mistral excels in the MTEB benchmarks (as of May 29, 2024), achieving an average score of 68.2 across 56 datasets, and ranks 1st among all models for retrieval tasks on the MTEB leaderboard with a performance score of 60.2. This performance underscores its superior capability in enhancing search precision and reliability. Our contributions include advanced data refinement methods that significantly improve model performance on benchmark and synthetic datasets, techniques for homogeneous task ordering and mixed task fine-tuning to enhance model generalization and stability, and a streamlined evaluation process using 4-bit precision and a light retrieval evaluation set, which accelerates validation without sacrificing accuracy.
Multimodal tasks, such as image-text retrieval and generation, require embedding data from diverse modalities into a shared representation space. Aligning embeddings from heterogeneous sources while preserving shared and modality-specific information is a fundamental challenge. This paper provides an initial attempt to integrate algebraic geometry into multimodal representation learning, offering a foundational perspective for further exploration. We model image and text data as polynomials over discrete rings, \( \mathbb{Z}_{256}[x] \) and \( \mathbb{Z}_{|V|}[x] \), respectively, enabling the use of algebraic tools like fiber products to analyze alignment properties. To accommodate real-world variability, we extend the classical fiber product to an approximate fiber product with a tolerance parameter \( \epsilon \), balancing precision and noise tolerance. We study its dependence on \( \epsilon \), revealing asymptotic behavior, robustness to perturbations, and sensitivity to embedding dimensionality. Additionally, we propose a decomposition of the shared embedding space into orthogonal subspaces, \( Z = Z_s \oplus Z_I \oplus Z_T \), where \( Z_s \) captures shared semantics, and \( Z_I \), \( Z_T \) encode modality-specific features. This decomposition is geometrically interpreted via manifolds and fiber bundles, offering insights into embedding structure and optimization. This framework establishes a principled foundation for analyzing multimodal alignment, uncovering connections between robustness, dimensionality allocation, and algebraic structure. It lays the groundwork for further research on embedding spaces in multimodal learning using algebraic geometry.
Image captioning models often suffer from performance degradation when applied to novel datasets, as they are typically trained on domain-specific data. To enhance generalization in out-of-domain scenarios, retrieval-augmented approaches have garnered increasing attention. However, current methods face two key challenges: (1) image features used for retrieval are often optimized based on ground-truth (GT) captions, which represent the image from a specific perspective and are influenced by annotator biases, and (2) they underutilize the full potential of retrieved text, typically relying on raw captions or parsed objects, which fail to capture the full semantic richness of the data. In this paper, we propose Dive Into Retrieval (DIR), a method designed to enhance both the image-to-text retrieval process and the utilization of retrieved text to achieve a more comprehensive understanding of the visual content. Our approach introduces two key innovations: (1) diffusion-guided retrieval enhancement, where a pretrained diffusion model guides image feature learning by reconstructing noisy images, allowing the model to capture more comprehensive and fine-grained visual information beyond standard annotated captions; and (2) a high-quality retrieval database, which provides comprehensive semantic information to enhance caption generation, especially in out-of-domain scenarios. Extensive experiments demonstrate that DIR not only maintains competitive in-domain performance but also significantly improves out-of-domain generalization, all without increasing inference costs.
With the emergence of audio-language models, constructing large-scale paired audio-language datasets has become essential yet challenging for model development, primarily due to the time-intensive and labour-heavy demands involved. While large language models (LLMs) have improved the efficiency of synthetic audio caption generation, current approaches struggle to effectively extract and incorporate detailed audio information. In this paper, we propose an automated pipeline that integrates audio-language models for fine-grained content extraction, LLMs for synthetic caption generation, and a contrastive language-audio pretraining (CLAP) model-based refinement process to improve the quality of captions. Specifically, we employ prompt chaining techniques in the content extraction stage to obtain accurate and fine-grained audio information, while we use the refinement process to mitigate potential hallucinations in the generated captions. Leveraging the AudioSet dataset and the proposed approach, we create AudioSetCaps, a dataset comprising 1.9 million audio-caption pairs, the largest audio-caption dataset at the time of writing. The models trained with AudioSetCaps achieve state-of-the-art performance on audio-text retrieval with R@1 scores of 46.3% for text-to-audio and 59.7% for audio-to-text retrieval and automated audio captioning with the CIDEr score of 84.8. As our approach has shown promising results with AudioSetCaps, we create another dataset containing 4.1 million synthetic audio-language pairs based on the Youtube-8M and VGGSound datasets. To facilitate research in audio-language learning, we have made our pipeline, datasets with 6 million audio-language pairs, and pre-trained models publicly available at https://github.com/JishengBai/AudioSetCaps.
Grounding the instruction in the environment is a key step in solving language-guided goal-reaching reinforcement learning problems. In automated reinforcement learning, a key concern is to enhance the model's ability to generalize across various tasks and environments. In goal-reaching scenarios, the agent must comprehend the different parts of the instructions within the environmental context in order to complete the overall task successfully. In this work, we propose CAREL (Cross-modal Auxiliary REinforcement Learning) as a new framework to solve this problem using auxiliary loss functions inspired by video-text retrieval literature and a novel method called instruction tracking, which automatically keeps track of progress in an environment. The results of our experiments suggest superior sample efficiency and systematic generalization for this framework in multi-modal reinforcement learning problems. Our code base is available here.
Recent advancements in vision-language pre-training via contrastive learning have significantly improved performance across computer vision tasks. However, in the medical domain, obtaining multimodal data is often costly and challenging due to privacy, sensitivity, and annotation complexity. To mitigate data scarcity while boosting model performance, we introduce \textbf{Uni-Mlip}, a unified self-supervision framework specifically designed to enhance medical vision-language pre-training. Uni-Mlip seamlessly integrates cross-modality, uni-modality, and fused-modality self-supervision techniques at the data-level and the feature-level. Additionally, Uni-Mlip tailors uni-modal image self-supervision to accommodate the unique characteristics of medical images. Our experiments across datasets of varying scales demonstrate that Uni-Mlip significantly surpasses current state-of-the-art methods in three key downstream tasks: image-text retrieval, image classification, and visual question answering (VQA).
We present a way to learn novel concepts by only using their textual description. We call this method Knowledge Transfer. Similarly to human perception, we leverage cross-modal interaction to introduce new concepts. We hypothesize that in a pre-trained visual encoder there are enough low-level features already learned (e.g. shape, appearance, color) that can be used to describe previously unknown high-level concepts. Provided with a textual description of the novel concept, our method works by aligning the known low-level features of the visual encoder to its high-level textual description. We show that Knowledge Transfer can successfully introduce novel concepts in multimodal models, in a very efficient manner, by only requiring a single description of the target concept. Our approach is compatible with both separate textual and visual encoders (e.g. CLIP) and shared parameters across modalities. We also show that, following the same principle, Knowledge Transfer can improve concepts already known by the model. Leveraging Knowledge Transfer we improve zero-shot performance across different tasks such as classification, segmentation, image-text retrieval, and captioning.
Remote sensing cross-modal text-image retrieval (RSCTIR) has gained attention for its utility in information mining. However, challenges remain in effectively integrating global and local information due to variations in remote sensing imagery and ensuring proper feature pre-alignment before modal fusion, which affects retrieval accuracy and efficiency. To address these issues, we propose CMPAGL, a cross-modal pre-aligned method leveraging global and local information. Our Gswin transformer block combines local window self-attention and global-local window cross-attention to capture multi-scale features. A pre-alignment mechanism simplifies modal fusion training, improving retrieval performance. Additionally, we introduce a similarity matrix reweighting (SMR) algorithm for reranking, and enhance the triplet loss function with an intra-class distance term to optimize feature learning. Experiments on four datasets, including RSICD and RSITMD, validate CMPAGL's effectiveness, achieving up to 4.65% improvement in R@1 and 2.28% in mean Recall (mR) over state-of-the-art methods.
This article presents a comprehensive evaluation of 7 off-the-shelf document retrieval models: Splade, Plaid, Plaid-X, SimCSE, Contriever, OpenAI ADA and Gemma2 chosen to determine their performance on the Czech retrieval dataset DaReCzech. The primary objective of our experiments is to estimate the quality of modern retrieval approaches in the Czech language. Our analyses include retrieval quality, speed, and memory footprint. Secondly, we analyze whether it is better to use the model directly in Czech text, or to use machine translation into English, followed by retrieval in English. Our experiments identify the most effective option for Czech information retrieval. The findings revealed notable performance differences among the models, with Gemma22 achieving the highest precision and recall, while Contriever performing poorly. Conclusively, SPLADE and PLAID models offered a balance of efficiency and performance.
Dense retrieval, which aims to encode the semantic information of arbitrary text into dense vector representations or embeddings, has emerged as an effective and efficient paradigm for text retrieval, consequently becoming an essential component in various natural language processing systems. These systems typically focus on optimizing the embedding space by attending to the relevance of text pairs, while overlooking the Boolean logic inherent in language, which may not be captured by current training objectives. In this work, we first investigate whether current retrieval systems can comprehend the Boolean logic implied in language. To answer this question, we formulate the task of Boolean Dense Retrieval and collect a benchmark dataset, BoolQuestions, which covers complex queries containing basic Boolean logic and corresponding annotated passages. Through extensive experimental results on the proposed task and benchmark dataset, we draw the conclusion that current dense retrieval systems do not fully understand Boolean logic in language, and there is a long way to go to improve our dense retrieval systems. Furthermore, to promote further research on enhancing the understanding of Boolean logic for language models, we explore Boolean operation on decomposed query and propose a contrastive continual training method that serves as a strong baseline for the research community.
Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Their applications are versatile and have the potential to improve diagnostic accuracy and decision-making for individual patients while also contributing to enhanced public health monitoring, disease surveillance, and policy-making through more efficient analysis of large data sets. MVLMS integrate natural language processing with medical images to enable a more comprehensive and contextual understanding of medical images alongside their corresponding textual information. Unlike general vision-and-language models trained on diverse, non-specialized datasets, MVLMs are purpose-built for the medical domain, automatically extracting and interpreting critical information from medical images and textual reports to support clinical decision-making. Popular clinical applications of MVLMs include automated medical report generation, medical visual question answering, medical multimodal segmentation, diagnosis and prognosis and medical image-text retrieval. Here, we provide a comprehensive overview of MVLMs and the various medical tasks to which they have been applied. We conduct a detailed analysis of various vision-and-language model architectures, focusing on their distinct strategies for cross-modal integration/exploitation of medical visual and textual features. We also examine the datasets used for these tasks and compare the performance of different models based on standardized evaluation metrics. Furthermore, we highlight potential challenges and summarize future research trends and directions. The full collection of papers and codes is available at: https://github.com/YtongXie/Medical-Vision-and-Language-Tasks-and-Methodologies-A-Survey.
Despite the success of text retrieval in many NLP tasks, code retrieval remains a largely underexplored area. Most text retrieval systems are tailored for natural language queries, often neglecting the specific challenges of retrieving code. This gap leaves existing models unable to effectively capture the diversity of programming languages and tasks across different domains, highlighting the need for more focused research in code retrieval. To address this, we introduce CodeXEmbed, a family of large-scale code embedding models ranging from 400M to 7B parameters. Our novel training pipeline unifies multiple programming languages and transforms various code-related tasks into a common retrieval framework, enhancing model generalizability and retrieval performance. Our 7B model sets a new state-of-the-art (SOTA) in code retrieval, outperforming the previous leading model, Voyage-Code, by over 20% on CoIR benchmark. In addition to excelling in code retrieval, our models demonstrate competitive performance on the widely adopted BeIR text retrieval benchmark, offering versatility across domains. Experimental results demonstrate that improving retrieval performance significantly enhances end-to-end Retrieval-Augmented Generation (RAG) performance for code-related tasks.
The task of partial scene text retrieval involves localizing and searching for text instances that are the same or similar to a given query text from an image gallery. However, existing methods can only handle text-line instances, leaving the problem of searching for partial patches within these text-line instances unsolved due to a lack of patch annotations in the training data. To address this issue, we propose a network that can simultaneously retrieve both text-line instances and their partial patches. Our method embeds the two types of data (query text and scene text instances) into a shared feature space and measures their cross-modal similarities. To handle partial patches, our proposed approach adopts a Multiple Instance Learning (MIL) approach to learn their similarities with query text, without requiring extra annotations. However, constructing bags, which is a standard step of conventional MIL approaches, can introduce numerous noisy samples for training, and lower inference speed. To address this issue, we propose a Ranking MIL (RankMIL) approach to adaptively filter those noisy samples. Additionally, we present a Dynamic Partial Match Algorithm (DPMA) that can directly search for the target partial patch from a text-line instance during the inference stage, without requiring bags. This greatly improves the search efficiency and the performance of retrieving partial patches. The source code and dataset are available at https://github.com/lanfeng4659/PSTR.
State-of-the-art retrieval models typically address a straightforward search scenario, in which retrieval tasks are fixed (e.g., finding a passage to answer a specific question) and only a single modality is supported for both queries and retrieved results. This paper introduces techniques for advancing information retrieval with multimodal large language models (MLLMs), enabling a broader search scenario, termed universal multimodal retrieval, where multiple modalities and diverse retrieval tasks are accommodated. To this end, we first study fine-tuning an MLLM as a bi-encoder retriever on 10 datasets with 16 retrieval tasks. Our empirical results show that the fine-tuned MLLM retriever is capable of understanding challenging queries, composed of both text and image, but it underperforms compared to a smaller CLIP retriever in cross-modal retrieval tasks due to the modality bias exhibited by MLLMs. To address the issue, we propose modality-aware hard negative mining to mitigate the modality bias exhibited by MLLM retrievers. Second, we propose continuously fine-tuning the universal multimodal retriever to enhance its text retrieval capability while preserving multimodal retrieval capability. As a result, our model, MM-Embed, achieves state-of-the-art performance on the multimodal retrieval benchmark M-BEIR, which spans multiple domains and tasks, while also surpassing the state-of-the-art text retrieval model, NV-Embed-v1, on the MTEB retrieval benchmark. We also explore prompting the off-the-shelf MLLMs as zero-shot rerankers to refine the ranking of the candidates from the multimodal retriever. We find that, through prompt-and-reranking, MLLMs can further improve multimodal retrieval when the user queries (e.g., text-image composed queries) are more complex and challenging to understand. These findings also pave the way for advancing universal multimodal retrieval in the future.
Capturing a video's meaning and critical concepts by analyzing the subtle details is a fundamental yet challenging task in video captioning. Identifying the dominant emotional tone in a video significantly enhances the perception of its context. Despite a strong emphasis on video captioning, existing models often need to adequately address emotional themes, resulting in suboptimal captioning results. To address these limitations, this paper proposes a novel Semantic Processing and Emotion-informed video-Captioning Through Retrieval and Understanding Modalities (SPECTRUM) framework to empower the generation of emotionally and semantically credible captions. Leveraging our pioneering structure, SPECTRUM discerns multimodal semantics and emotional themes using Visual Text Attribute Investigation (VTAI) and determines the orientation of descriptive captions through a Holistic Concept-Oriented Theme (HCOT), expressing emotionally-informed and field-acquainted references. They exploit video-to-text retrieval capabilities and the multifaceted nature of video content to estimate the emotional probabilities of candidate captions. Then, the dominant theme of the video is determined by appropriately weighting embedded attribute vectors and applying coarse- and fine-grained emotional concepts, which define the video's contextual alignment. Furthermore, using two loss functions, SPECTRUM is optimized to integrate emotional information and minimize prediction errors. Extensive experiments on the EmVidCap, MSVD, and MSRVTT video captioning datasets demonstrate that our model significantly surpasses state-of-the-art methods. Quantitative and qualitative evaluations highlight the model's ability to accurately capture and convey video emotions and multimodal attributes.