In this study, we explore an alternative approach to enhance contrastive text-image-3D alignment in the absence of textual descriptions for 3D objects. We introduce two unsupervised methods, $I2I$ and $(I2L)^2$, which leverage CLIP knowledge about textual and 2D data to compute the neural perceived similarity between two 3D samples. We employ the proposed methods to mine 3D hard negatives, establishing a multimodal contrastive pipeline with hard negative weighting via a custom loss function. We train on different configurations of the proposed hard negative mining approach, and we evaluate the accuracy of our models in 3D classification and on the cross-modal retrieval benchmark, testing image-to-shape and shape-to-image retrieval. Results demonstrate that our approach, even without explicit text alignment, achieves comparable or superior performance on zero-shot and standard 3D classification, while significantly improving both image-to-shape and shape-to-image retrieval compared to previous methods.
Most multi-modal tasks can be formulated into problems of either generation or embedding. Existing models usually tackle these two types of problems by decoupling language modules into a text decoder for generation, and a text encoder for embedding. To explore the minimalism of multi-modal paradigms, we attempt to achieve only one model per modality in this work. We propose a Multi-Modal Generative Embedding Model (MM-GEM), whereby the generative and embedding objectives are encapsulated in one Large Language Model. We also propose a PoolAggregator to boost efficiency and enable the ability of fine-grained embedding and generation. A surprising finding is that these two objectives do not significantly conflict with each other. For example, MM-GEM instantiated from ViT-Large and TinyLlama shows competitive performance on benchmarks for multimodal embedding models such as cross-modal retrieval and zero-shot classification, while has good ability of image captioning. Additionally, MM-GEM can seamlessly execute region-level image caption generation and retrieval tasks. Besides, the advanced text model in MM-GEM brings over 5% improvement in Recall@1 for long text and image retrieval.
Composed Image Retrieval (CIR) involves searching for target images based on an image-text pair query. While current methods treat this as a query-target matching problem, we argue that CIR triplets contain additional associations beyond this primary relation. In our paper, we identify two new relations within triplets, treating each triplet as a graph node. Firstly, we introduce the concept of text-bridged image alignment, where the query text serves as a bridge between the query image and the target image. We propose a hinge-based cross-attention mechanism to incorporate this relation into network learning. Secondly, we explore complementary text reasoning, considering CIR as a form of cross-modal retrieval where two images compose to reason about complementary text. To integrate these perspectives effectively, we design a twin attention-based compositor. By combining these complementary associations with the explicit query pair-target image relation, we establish a comprehensive set of constraints for CIR. Our framework, CaLa (Complementary Association Learning for Augmenting Composed Image Retrieval), leverages these insights. We evaluate CaLa on CIRR and FashionIQ benchmarks with multiple backbones, demonstrating its superiority in composed image retrieval.
Known for efficient computation and easy storage, hashing has been extensively explored in cross-modal retrieval. The majority of current hashing models are predicated on the premise of a direct one-to-one mapping between data points. However, in real practice, data correspondence across modalities may be partially provided. In this research, we introduce an innovative unsupervised hashing technique designed for semi-paired cross-modal retrieval tasks, named Reconstruction Relations Embedded Hashing (RREH). RREH assumes that multi-modal data share a common subspace. For paired data, RREH explores the latent consistent information of heterogeneous modalities by seeking a shared representation. For unpaired data, to effectively capture the latent discriminative features, the high-order relationships between unpaired data and anchors are embedded into the latent subspace, which are computed by efficient linear reconstruction. The anchors are sampled from paired data, which improves the efficiency of hash learning. The RREH trains the underlying features and the binary encodings in a unified framework with high-order reconstruction relations preserved. With the well devised objective function and discrete optimization algorithm, RREH is designed to be scalable, making it suitable for large-scale datasets and facilitating efficient cross-modal retrieval. In the evaluation process, the proposed is tested with partially paired data to establish its superiority over several existing methods.
``Learning to hash'' is a practical solution for efficient retrieval, offering fast search speed and low storage cost. It is widely applied in various applications, such as image-text cross-modal search. In this paper, we explore the potential of enhancing the performance of learning to hash with the proliferation of powerful large pre-trained models, such as Vision-Language Pre-training (VLP) models. We introduce a novel method named Distillation for Cross-Modal Quantization (DCMQ), which leverages the rich semantic knowledge of VLP models to improve hash representation learning. Specifically, we use the VLP as a `teacher' to distill knowledge into a `student' hashing model equipped with codebooks. This process involves the replacement of supervised labels, which are composed of multi-hot vectors and lack semantics, with the rich semantics of VLP. In the end, we apply a transformation termed Normalization with Paired Consistency (NPC) to achieve a discriminative target for distillation. Further, we introduce a new quantization method, Product Quantization with Gumbel (PQG) that promotes balanced codebook learning, thereby improving the retrieval performance. Extensive benchmark testing demonstrates that DCMQ consistently outperforms existing supervised cross-modal hashing approaches, showcasing its significant potential.
Modern retrieval systems often struggle with upgrading to new and more powerful models due to the incompatibility of embeddings between the old and new models. This necessitates a costly process known as backfilling, which involves re-computing the embeddings for a large number of data samples. In vision, Backward-compatible Training (BT) has been proposed to ensure that the new model aligns with the old model's embeddings. This paper extends the concept of vision-only BT to the field of cross-modal retrieval, marking the first attempt to address Cross-modal BT (XBT). Our goal is to achieve backward-compatibility between Vision-Language Pretraining (VLP) models, such as CLIP, for the cross-modal retrieval task. To address XBT challenges, we propose an efficient solution: a projection module that maps the new model's embeddings to those of the old model. This module, pretrained solely with text data, significantly reduces the number of image-text pairs required for XBT learning, and, once it is pretrained, it avoids using the old model during training. Furthermore, we utilize parameter-efficient training strategies that improve efficiency and preserve the off-the-shelf new model's knowledge by avoiding any modifications. Experimental results on cross-modal retrieval datasets demonstrate the effectiveness of XBT and its potential to enable backfill-free upgrades when a new VLP model emerges.
Recent years have witnessed the rapid development of short videos, which usually contain both visual and audio modalities. Background music is important to the short videos, which can significantly influence the emotions of the viewers. However, at present, the background music of short videos is generally chosen by the video producer, and there is a lack of automatic music recommendation methods for short videos. This paper introduces MVBind, an innovative Music-Video embedding space Binding model for cross-modal retrieval. MVBind operates as a self-supervised approach, acquiring inherent knowledge of intermodal relationships directly from data, without the need of manual annotations. Additionally, to compensate the lack of a corresponding musical-visual pair dataset for short videos, we construct a dataset, SVM-10K(Short Video with Music-10K), which mainly consists of meticulously selected short videos. On this dataset, MVBind manifests significantly improved performance compared to other baseline methods. The constructed dataset and code will be released to facilitate future research.
In Re-identification (ReID), recent advancements yield noteworthy progress in both unimodal and cross-modal retrieval tasks. However, the challenge persists in developing a unified framework that could effectively handle varying multimodal data, including RGB, infrared, sketches, and textual information. Additionally, the emergence of large-scale models shows promising performance in various vision tasks but the foundation model in ReID is still blank. In response to these challenges, a novel multimodal learning paradigm for ReID is introduced, referred to as All-in-One (AIO), which harnesses a frozen pre-trained big model as an encoder, enabling effective multimodal retrieval without additional fine-tuning. The diverse multimodal data in AIO are seamlessly tokenized into a unified space, allowing the modality-shared frozen encoder to extract identity-consistent features comprehensively across all modalities. Furthermore, a meticulously crafted ensemble of cross-modality heads is designed to guide the learning trajectory. AIO is the \textbf{first} framework to perform all-in-one ReID, encompassing four commonly used modalities. Experiments on cross-modal and multimodal ReID reveal that AIO not only adeptly handles various modal data but also excels in challenging contexts, showcasing exceptional performance in zero-shot and domain generalization scenarios.
In this paper, we investigate an open research task of cross-modal retrieval between 3D shapes and textual descriptions. Previous approaches mainly rely on point cloud encoders for feature extraction, which may ignore key inherent features of 3D shapes, including depth, spatial hierarchy, geometric continuity, etc. To address this issue, we propose COM3D, making the first attempt to exploit the cross-view correspondence and cross-modal mining to enhance the retrieval performance. Notably, we augment the 3D features through a scene representation transformer, to generate cross-view correspondence features of 3D shapes, which enrich the inherent features and enhance their compatibility with text matching. Furthermore, we propose to optimize the cross-modal matching process based on the semi-hard negative example mining method, in an attempt to improve the learning efficiency. Extensive quantitative and qualitative experiments demonstrate the superiority of our proposed COM3D, achieving state-of-the-art results on the Text2Shape dataset.
Pre-trained contrastive vision-language models have demonstrated remarkable performance across a wide range of tasks. However, they often struggle on fine-trained datasets with categories not adequately represented during pre-training, which makes adaptation necessary. Recent works have shown promising results by utilizing samples from web-scale databases for retrieval-augmented adaptation, especially in low-data regimes. Despite the empirical success, understanding how retrieval impacts the adaptation of vision-language models remains an open research question. In this work, we adopt a reflective perspective by presenting a systematic study to understand the roles of key components in retrieval-augmented adaptation. We unveil new insights on uni-modal and cross-modal retrieval and highlight the critical role of logit ensemble for effective adaptation. We further present theoretical underpinnings that directly support our empirical observations.
With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by fine-tuning. Although this paradigm has demonstrated potential in various multimodal downstream tasks, its implementation in the remote sensing domain encounters some obstacles. Specifically, the tendency for same-modality embeddings to cluster together impedes efficient transfer learning. To tackle this issue, we review the aim of multimodal transfer learning for downstream tasks from a unified perspective, and rethink the optimization process based on three distinct objectives. We propose "Harmonized Transfer Learning and Modality Alignment (HarMA)", a method that simultaneously satisfies task constraints, modality alignment, and single-modality uniform alignment, while minimizing training overhead through parameter-efficient fine-tuning. Remarkably, without the need for external data for training, HarMA achieves state-of-the-art performance in two popular multimodal retrieval tasks in the field of remote sensing. Our experiments reveal that HarMA achieves competitive and even superior performance to fully fine-tuned models with only minimal adjustable parameters. Due to its simplicity, HarMA can be integrated into almost all existing multimodal pretraining models. We hope this method can facilitate the efficient application of large models to a wide range of downstream tasks while significantly reducing the resource consumption. Code is available at https://github.com/seekerhuang/HarMA.
In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image-sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics-spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%. Data and code are available at https://github.com/XuriGe1995/3SHNet.
Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across individuals has prompted the development of deep learning models tailored to each subject. The personalization limits the broader applicability of brain visual decoding in real-world scenarios. To address this issue, we introduce Wills Aligner, a novel approach designed to achieve multi-subject collaborative brain visual decoding. Wills Aligner begins by aligning the fMRI data from different subjects at the anatomical level. It then employs delicate mixture-of-brain-expert adapters and a meta-learning strategy to account for individual fMRI pattern differences. Additionally, Wills Aligner leverages the semantic relation of visual stimuli to guide the learning of inter-subject commonality, enabling visual decoding for each subject to draw insights from other subjects' data. We rigorously evaluate our Wills Aligner across various visual decoding tasks, including classification, cross-modal retrieval, and image reconstruction. The experimental results demonstrate that Wills Aligner achieves promising performance.
Metric learning minimizes the gap between similar (positive) pairs of data points and increases the separation of dissimilar (negative) pairs, aiming at capturing the underlying data structure and enhancing the performance of tasks like audio-visual cross-modal retrieval (AV-CMR). Recent works employ sampling methods to select impactful data points from the embedding space during training. However, the model training fails to fully explore the space due to the scarcity of training data points, resulting in an incomplete representation of the overall positive and negative distributions. In this paper, we propose an innovative Anchor-aware Deep Metric Learning (AADML) method to address this challenge by uncovering the underlying correlations among existing data points, which enhances the quality of the shared embedding space. Specifically, our method establishes a correlation graph-based manifold structure by considering the dependencies between each sample as the anchor and its semantically similar samples. Through dynamic weighting of the correlations within this underlying manifold structure using an attention-driven mechanism, Anchor Awareness (AA) scores are obtained for each anchor. These AA scores serve as data proxies to compute relative distances in metric learning approaches. Extensive experiments conducted on two audio-visual benchmark datasets demonstrate the effectiveness of our proposed AADML method, significantly surpassing state-of-the-art models. Furthermore, we investigate the integration of AA proxies with various metric learning methods, further highlighting the efficacy of our approach.
Aiming at the problem that existing image text cross-modal retrieval is difficult to fully exploit the local consistency in the mode in the common subspace, a cross-modal retrieval method based on improved graph convolution was proposed. In order to improve the local consistency within each mode, the modal diagram is constructed with a single sample as a node, fully mining the interactive information between features. In order to solve the problem that graph convolution network can only do shallow learning, the method of adding initial residual link and weight identity map in each layer of graph convolution is adopted to alleviate this phenomenon. In order to jointly update the central node features through higher-order and lower-order neighbor information, an improvement is proposed to reduce neighbor nodes and increase the number of layers in graph convolution network. In order to learn highly locally consistent and semantically consistent public representation, shared common representation learning layer weight, and jointly optimize the semantic constraints within the modes and the modal invariant constraints between modes in the common subspace. The experimental results show that on the two cross-modal data sets of Wikipedia and Pascal Sentence, the average mAP values of different retrieval tasks are 2.2%-42.1% and 3.0%-54.0% higher than the 11 existing methods.
In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required for their training present significant hurdles for deployment in environments with limited computational resources. To address this challenge, we propose a novel dynamic self-adaptive multiscale distillation from pre-trained multimodal large model for efficient cross-modal representation learning for the first time. Unlike existing distillation methods, our strategy employs a multiscale perspective, enabling the extraction structural knowledge across from the pre-trained multimodal large model. Ensuring that the student model inherits a comprehensive and nuanced understanding of the teacher knowledge. To optimize each distillation loss in a balanced and efficient manner, we propose a dynamic self-adaptive distillation loss balancer, a novel component eliminating the need for manual loss weight adjustments and dynamically balances each loss item during the distillation process. Our methodology streamlines pre-trained multimodal large models using only their output features and original image-level information, requiring minimal computational resources. This efficient approach is suited for various applications and allows the deployment of advanced multimodal technologies even in resource-limited settings. Extensive experiments has demonstrated that our method maintains high performance while significantly reducing model complexity and training costs. Moreover, our distilled student model utilizes only image-level information to achieve state-of-the-art performance on cross-modal retrieval tasks, surpassing previous methods that relied on region-level information.
In this paper, we consider the problem of visual representation learning for computational pathology, by exploiting large-scale image-text pairs gathered from public resources, along with the domain-specific knowledge in pathology. Specifically, we make the following contributions: (i) We curate a pathology knowledge tree that consists of 50,470 informative attributes for 4,718 diseases requiring pathology diagnosis from 32 human tissues. To our knowledge, this is the first comprehensive structured pathology knowledge base; (ii) We develop a knowledge-enhanced visual-language pretraining approach, where we first project pathology-specific knowledge into latent embedding space via a language model, and use it to guide the visual representation learning; (iii) We conduct thorough experiments to validate the effectiveness of our proposed components, demonstrating significant performance improvement on various downstream tasks, including cross-modal retrieval, zero-shot classification on pathology patches, and zero-shot tumor subtyping on whole slide images (WSIs).
This paper introduces VLAP, a novel approach that bridges pretrained vision models and large language models (LLMs) to make frozen LLMs understand the visual world. VLAP transforms the embedding space of pretrained vision models into the LLMs' word embedding space using a single linear layer for efficient and general-purpose visual and language understanding. Specifically, we harness well-established word embeddings to bridge two modality embedding spaces. The visual and text representations are simultaneously assigned to a set of word embeddings within pretrained LLMs by formulating the assigning procedure as an optimal transport problem. We predict the assignment of one modality from the representation of another modality data, enforcing consistent assignments for paired multimodal data. This allows vision and language representations to contain the same information, grounding the frozen LLMs' word embedding space in visual data. Moreover, a robust semantic taxonomy of LLMs can be preserved with visual data since the LLMs interpret and reason linguistic information from correlations between word embeddings. Experimental results show that VLAP achieves substantial improvements over the previous linear transformation-based approaches across a range of vision-language tasks, including image captioning, visual question answering, and cross-modal retrieval. We also demonstrate the learned visual representations hold a semantic taxonomy of LLMs, making visual semantic arithmetic possible.
Cross-modal place recognition methods are flexible GPS-alternatives under varying environment conditions and sensor setups. However, this task is non-trivial since extracting consistent and robust global descriptors from different modalities is challenging. To tackle this issue, we propose Voxel-Cross-Pixel (VXP), a novel camera-to-LiDAR place recognition framework that enforces local similarities in a self-supervised manner and effectively brings global context from images and LiDAR scans into a shared feature space. Specifically, VXP is trained in three stages: first, we deploy a visual transformer to compactly represent input images. Secondly, we establish local correspondences between image-based and point cloud-based feature spaces using our novel geometric alignment module. We then aggregate local similarities into an expressive shared latent space. Extensive experiments on the three benchmarks (Oxford RobotCar, ViViD++ and KITTI) demonstrate that our method surpasses the state-of-the-art cross-modal retrieval by a large margin. Our evaluations show that the proposed method is accurate, efficient and light-weight. Our project page is available at: https://yunjinli.github.io/projects-vxp/
Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data. However, even for unimodal data, precise annotation is expensive and time-consuming, and it becomes more challenging with the multimodal scenario. In practice, massive multimodal data are collected from the Internet with coarse annotation, which inevitably introduces noisy labels. Training with such misleading labels would bring two key challenges -- enforcing the multimodal samples to \emph{align incorrect semantics} and \emph{widen the heterogeneous gap}, resulting in poor retrieval performance. To tackle these challenges, this work proposes UOT-RCL, a Unified framework based on Optimal Transport (OT) for Robust Cross-modal Retrieval. First, we propose a semantic alignment based on partial OT to progressively correct the noisy labels, where a novel cross-modal consistent cost function is designed to blend different modalities and provide precise transport cost. Second, to narrow the discrepancy in multi-modal data, an OT-based relation alignment is proposed to infer the semantic-level cross-modal matching. Both of these two components leverage the inherent correlation among multi-modal data to facilitate effective cost function. The experiments on three widely-used cross-modal retrieval datasets demonstrate that our UOT-RCL surpasses the state-of-the-art approaches and significantly improves the robustness against noisy labels.