While content-based image retrieval (CBIR) has been extensively studied in natural image retrieval, its application to medical images presents ongoing challenges, primarily due to the 3D nature of medical images. Recent studies have shown the potential use of pre-trained vision embeddings for CBIR in the context of radiology image retrieval. However, a benchmark for the retrieval of 3D volumetric medical images is still lacking, hindering the ability to objectively evaluate and compare the efficiency of proposed CBIR approaches in medical imaging. In this study, we extend previous work and establish a benchmark for region-based and localized multi-organ retrieval using the TotalSegmentator dataset (TS) with detailed multi-organ annotations. We benchmark embeddings derived from pre-trained supervised models on medical images against embeddings derived from pre-trained unsupervised models on non-medical images for 29 coarse and 104 detailed anatomical structures in volume and region levels. For volumetric image retrieval, we adopt a late interaction re-ranking method inspired by text matching. We compare it against the original method proposed for volume and region retrieval and achieve a retrieval recall of 1.0 for diverse anatomical regions with a wide size range. The findings and methodologies presented in this paper provide insights and benchmarks for further development and evaluation of CBIR approaches in the context of medical imaging.
Despite the significant progress of fully-supervised video captioning, zero-shot methods remain much less explored. In this paper, we propose a novel zero-shot video captioning framework named Retrieval-Enhanced Test-Time Adaptation (RETTA), which takes advantage of existing pretrained large-scale vision and language models to directly generate captions with test-time adaptation. Specifically, we bridge video and text using four key models: a general video-text retrieval model XCLIP, a general image-text matching model CLIP, a text alignment model AnglE, and a text generation model GPT-2, due to their source-code availability. The main challenge is how to enable the text generation model to be sufficiently aware of the content in a given video so as to generate corresponding captions. To address this problem, we propose using learnable tokens as a communication medium among these four frozen models GPT-2, XCLIP, CLIP, and AnglE. Different from the conventional way that trains these tokens with training data, we propose to learn these tokens with soft targets of the inference data under several carefully crafted loss functions, which enable the tokens to absorb video information catered for GPT-2. This procedure can be efficiently done in just a few iterations (we use 16 iterations in the experiments) and does not require ground truth data. Extensive experimental results on three widely used datasets, MSR-VTT, MSVD, and VATEX, show absolute 5.1%-32.4% improvements in terms of the main metric CIDEr compared to several state-of-the-art zero-shot video captioning methods.
While vision-language pretrained models (VLMs) excel in various multimodal understanding tasks, their potential in fine-grained audio-visual reasoning, particularly for audio-visual question answering (AVQA), remains largely unexplored. AVQA presents specific challenges for VLMs due to the requirement of visual understanding at the region level and seamless integration with audio modality. Previous VLM-based AVQA methods merely used CLIP as a feature encoder but underutilized its knowledge, and mistreated audio and video as separate entities in a dual-stream framework as most AVQA methods. This paper proposes a new CLIP-powered target-aware single-stream (TASS) network for AVQA using the image-text matching knowledge of the pretrained model through the audio-visual matching characteristic of nature. It consists of two key components: the target-aware spatial grounding module (TSG+) and the single-stream joint temporal grounding module (JTG). Specifically, we propose a TSG+ module to transfer the image-text matching knowledge from CLIP models to our region-text matching process without corresponding ground-truth labels. Moreover, unlike previous separate dual-stream networks that still required an additional audio-visual fusion module, JTG unifies audio-visual fusion and question-aware temporal grounding in a simplified single-stream architecture. It treats audio and video as a cohesive entity and further extends the pretrained image-text knowledge to audio-text matching by preserving their temporal correlation with our proposed cross-modal synchrony (CMS) loss. Extensive experiments conducted on the MUSIC-AVQA benchmark verified the effectiveness of our proposed method over existing state-of-the-art methods.
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.
Image-text matching remains a challenging task due to heterogeneous semantic diversity across modalities and insufficient distance separability within triplets. Different from previous approaches focusing on enhancing multi-modal representations or exploiting cross-modal correspondence for more accurate retrieval, in this paper we aim to leverage the knowledge transfer between peer branches in a boosting manner to seek a more powerful matching model. Specifically, we propose a brand-new Deep Boosting Learning (DBL) algorithm, where an anchor branch is first trained to provide insights into the data properties, with a target branch gaining more advanced knowledge to develop optimal features and distance metrics. Concretely, an anchor branch initially learns the absolute or relative distance between positive and negative pairs, providing a foundational understanding of the particular network and data distribution. Building upon this knowledge, a target branch is concurrently tasked with more adaptive margin constraints to further enlarge the relative distance between matched and unmatched samples. Extensive experiments validate that our DBL can achieve impressive and consistent improvements based on various recent state-of-the-art models in the image-text matching field, and outperform related popular cooperative strategies, e.g., Conventional Distillation, Mutual Learning, and Contrastive Learning. Beyond the above, we confirm that DBL can be seamlessly integrated into their training scenarios and achieve superior performance under the same computational costs, demonstrating the flexibility and broad applicability of our proposed method. Our code is publicly available at: https://github.com/Paranioar/DBL.
Representation-based Siamese networks have risen to popularity in lightweight text matching due to their low deployment and inference costs. While word-level attention mechanisms have been implemented within Siamese networks to improve performance, we propose Feature Attention (FA), a novel downstream block designed to enrich the modeling of dependencies among embedding features. Employing "squeeze-and-excitation" techniques, the FA block dynamically adjusts the emphasis on individual features, enabling the network to concentrate more on features that significantly contribute to the final classification. Building upon FA, we introduce a dynamic "selection" mechanism called Selective Feature Attention (SFA), which leverages a stacked BiGRU Inception structure. The SFA block facilitates multi-scale semantic extraction by traversing different stacked BiGRU layers, encouraging the network to selectively concentrate on semantic information and embedding features across varying levels of abstraction. Both the FA and SFA blocks offer a seamless integration capability with various Siamese networks, showcasing a plug-and-play characteristic. Experimental evaluations conducted across diverse text matching baselines and benchmarks underscore the indispensability of modeling feature attention and the superiority of the "selection" mechanism.
Recent progress in large-scale pre-training has led to the development of advanced vision-language models (VLMs) with remarkable proficiency in comprehending and generating multimodal content. Despite the impressive ability to perform complex reasoning for VLMs, current models often struggle to effectively and precisely capture the compositional information on both the image and text sides. To address this, we propose FineMatch, a new aspect-based fine-grained text and image matching benchmark, focusing on text and image mismatch detection and correction. This benchmark introduces a novel task for boosting and evaluating the VLMs' compositionality for aspect-based fine-grained text and image matching. In this task, models are required to identify mismatched aspect phrases within a caption, determine the aspect's class, and propose corrections for an image-text pair that may contain between 0 and 3 mismatches. To evaluate the models' performance on this new task, we propose a new evaluation metric named ITM-IoU for which our experiments show a high correlation to human evaluation. In addition, we also provide a comprehensive experimental analysis of existing mainstream VLMs, including fully supervised learning and in-context learning settings. We have found that models trained on FineMatch demonstrate enhanced proficiency in detecting fine-grained text and image mismatches. Moreover, models (e.g., GPT-4V, Gemini Pro Vision) with strong abilities to perform multimodal in-context learning are not as skilled at fine-grained compositional image and text matching analysis. With FineMatch, we are able to build a system for text-to-image generation hallucination detection and correction.
In this paper, we investigate a new problem called narrative action evaluation (NAE). NAE aims to generate professional commentary that evaluates the execution of an action. Unlike traditional tasks such as score-based action quality assessment and video captioning involving superficial sentences, NAE focuses on creating detailed narratives in natural language. These narratives provide intricate descriptions of actions along with objective evaluations. NAE is a more challenging task because it requires both narrative flexibility and evaluation rigor. One existing possible solution is to use multi-task learning, where narrative language and evaluative information are predicted separately. However, this approach results in reduced performance for individual tasks because of variations between tasks and differences in modality between language information and evaluation information. To address this, we propose a prompt-guided multimodal interaction framework. This framework utilizes a pair of transformers to facilitate the interaction between different modalities of information. It also uses prompts to transform the score regression task into a video-text matching task, thus enabling task interactivity. To support further research in this field, we re-annotate the MTL-AQA and FineGym datasets with high-quality and comprehensive action narration. Additionally, we establish benchmarks for NAE. Extensive experiment results prove that our method outperforms separate learning methods and naive multi-task learning methods. Data and code are released at https://github.com/shiyi-zh0408/NAE_CVPR2024.
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis. We find that Stable Diffusion + DiffusionITM is competitive on many tasks and outperforms CLIP on compositional tasks like like CLEVR and Winoground. We further boost its compositional performance with a transfer setup by fine-tuning on MS-COCO while retaining generative capabilities. We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2.1 is, for the most part, less biased than Stable Diffusion 1.5. Overall, our results point in an exciting direction bringing discriminative and generative model evaluation closer. We will release code and benchmark setup soon.
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a multitasking problem of event localization and event captioning to consider inter-task relations. However, addressing both tasks using only visual input is challenging due to the lack of semantic content. In this study, we address this by proposing a novel framework inspired by the cognitive information processing of humans. Our model utilizes external memory to incorporate prior knowledge. The memory retrieval method is proposed with cross-modal video-to-text matching. To effectively incorporate retrieved text features, the versatile encoder and the decoder with visual and textual cross-attention modules are designed. Comparative experiments have been conducted to show the effectiveness of the proposed method on ActivityNet Captions and YouCook2 datasets. Experimental results show promising performance of our model without extensive pretraining from a large video dataset.
Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval systems project queries and documents into the same embedding space and have demonstrated their success in retrieval and bi-text mining. To match speech and text in many languages, we propose using LLMs to initialize multi-modal DE retrieval systems. Unlike traditional methods, our system doesn't require speech data during LLM pre-training and can exploit LLM's multilingual text understanding capabilities to match speech and text in languages unseen during retrieval training. Our multi-modal LLM-based retrieval system is capable of matching speech and text in 102 languages despite only training on 21 languages. Our system outperforms previous systems trained explicitly on all 102 languages. We achieve a 10% absolute improvement in Recall@1 averaged across these languages. Additionally, our model demonstrates cross-lingual speech and text matching, which is further enhanced by readily available machine translation data.
Vision-language models (VLMs) have made significant strides in cross-modal understanding through large-scale paired datasets. However, in fashion domain, datasets often exhibit a disparity between the information conveyed in image and text. This issue stems from datasets containing multiple images of a single fashion item all paired with one text, leading to cases where some textual details are not visible in individual images. This mismatch, particularly when non-co-occurring elements are masked, undermines the training of conventional VLM objectives like Masked Language Modeling and Masked Image Modeling, thereby hindering the model's ability to accurately align fine-grained visual and textual features. Addressing this problem, we propose Synchronized attentional Masking (SyncMask), which generate masks that pinpoint the image patches and word tokens where the information co-occur in both image and text. This synchronization is accomplished by harnessing cross-attentional features obtained from a momentum model, ensuring a precise alignment between the two modalities. Additionally, we enhance grouped batch sampling with semi-hard negatives, effectively mitigating false negative issues in Image-Text Matching and Image-Text Contrastive learning objectives within fashion datasets. Our experiments demonstrate the effectiveness of the proposed approach, outperforming existing methods in three downstream tasks.
The recent success of Large Language Models (LLMs) has garnered significant attention in both academia and industry. Prior research on LLMs has primarily focused on enhancing or leveraging their generalization capabilities in zero- and few-shot settings. However, there has been limited investigation into effectively fine-tuning LLMs for a specific natural language understanding task in supervised settings. In this study, we conduct an experimental analysis by fine-tuning LLMs for the task of Chinese short text matching. We explore various factors that influence performance when fine-tuning LLMs, including task modeling methods, prompt formats, and output formats.
Multi-modal reasoning plays a vital role in bridging the gap between textual and visual information, enabling a deeper understanding of the context. This paper presents the Feature Swapping Multi-modal Reasoning (FSMR) model, designed to enhance multi-modal reasoning through feature swapping. FSMR leverages a pre-trained visual-language model as an encoder, accommodating both text and image inputs for effective feature representation from both modalities. It introduces a unique feature swapping module, enabling the exchange of features between identified objects in images and corresponding vocabulary words in text, thereby enhancing the model's comprehension of the interplay between images and text. To further bolster its multi-modal alignment capabilities, FSMR incorporates a multi-modal cross-attention mechanism, facilitating the joint modeling of textual and visual information. During training, we employ image-text matching and cross-entropy losses to ensure semantic consistency between visual and language elements. Extensive experiments on the PMR dataset demonstrate FSMR's superiority over state-of-the-art baseline models across various performance metrics.
In this paper, we present and study a new instance-level retrieval task: PointCloud-Text Matching~(PTM), which aims to find the exact cross-modal instance that matches a given point-cloud query or text query. PTM could be applied to various scenarios, such as indoor/urban-canyon localization and scene retrieval. However, there exists no suitable and targeted dataset for PTM in practice. Therefore, we construct three new PTM benchmark datasets, namely 3D2T-SR, 3D2T-NR, and 3D2T-QA. We observe that the data is challenging and with noisy correspondence due to the sparsity, noise, or disorder of point clouds and the ambiguity, vagueness, or incompleteness of texts, which make existing cross-modal matching methods ineffective for PTM. To tackle these challenges, we propose a PTM baseline, named Robust PointCloud-Text Matching method (RoMa). RoMa consists of two modules: a Dual Attention Perception module (DAP) and a Robust Negative Contrastive Learning module (RNCL). Specifically, DAP leverages token-level and feature-level attention to adaptively focus on useful local and global features, and aggregate them into common representations, thereby reducing the adverse impact of noise and ambiguity. To handle noisy correspondence, RNCL divides negative pairs, which are much less error-prone than positive pairs, into clean and noisy subsets, and assigns them forward and reverse optimization directions respectively, thus enhancing robustness against noisy correspondence. We conduct extensive experiments on our benchmarks and demonstrate the superiority of our RoMa.
The integration of artificial intelligence (AI) with radiology marks a transformative era in medicine. Vision foundation models have been adopted to enhance radiologic imaging analysis. However, the distinct complexities of radiologic 2D and 3D radiologic data pose unique challenges that existing models, pre-trained on general non-medical images, fail to address adequately. To bridge this gap and capitalize on the diagnostic precision required in radiologic imaging, we introduce Radiologic Contrastive Language-Image Pre-training (RadCLIP): a cross-modal vision-language foundational model that harnesses Vision Language Pre-training (VLP) framework to improve radiologic image analysis. Building upon Contrastive Language-Image Pre-training (CLIP), RadCLIP incorporates a slice pooling mechanism tailored for volumetric image analysis and is pre-trained using a large and diverse dataset of radiologic image-text pairs. The RadCLIP was pre-trained to effectively align radiologic images with their corresponding text annotations, creating a robust vision backbone for radiologic images. Extensive experiments demonstrate RadCLIP's superior performance in both uni-modal radiologic image classification and cross-modal image-text matching, highlighting its significant promise for improving diagnostic accuracy and efficiency in clinical settings. Our Key contributions include curating a large dataset with diverse radiologic 2D/3D radiologic image-text pairs, a slice pooling adapter using an attention mechanism for integrating 2D images, and comprehensive evaluations of RadCLIP on various radiologic downstream tasks.
This paper introduces a novel neuro-symbolic architecture for relation classification (RC) that combines rule-based methods with contemporary deep learning techniques. This approach capitalizes on the strengths of both paradigms: the adaptability of rule-based systems and the generalization power of neural networks. Our architecture consists of two components: a declarative rule-based model for transparent classification and a neural component to enhance rule generalizability through semantic text matching. Notably, our semantic matcher is trained in an unsupervised domain-agnostic way, solely with synthetic data. Further, these components are loosely coupled, allowing for rule modifications without retraining the semantic matcher. In our evaluation, we focused on two few-shot relation classification datasets: Few-Shot TACRED and a Few-Shot version of NYT29. We show that our proposed method outperforms previous state-of-the-art models in three out of four settings, despite not seeing any human-annotated training data. Further, we show that our approach remains modular and pliable, i.e., the corresponding rules can be locally modified to improve the overall model. Human interventions to the rules for the TACRED relation \texttt{org:parents} boost the performance on that relation by as much as 26\% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component.
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous approaches augment textual dialogues with retrieved images, posing privacy, diversity, and quality constraints. In this work, we introduce Multimodal Augmented Generative Images Dialogues (MAGID), a framework to augment text-only dialogues with diverse and high-quality images. Subsequently, a diffusion model is applied to craft corresponding images, ensuring alignment with the identified text. Finally, MAGID incorporates an innovative feedback loop between an image description generation module (textual LLM) and image quality modules (addressing aesthetics, image-text matching, and safety), that work in tandem to generate high-quality and multi-modal dialogues. We compare MAGID to other SOTA baselines on three dialogue datasets, using automated and human evaluation. Our results show that MAGID is comparable to or better than baselines, with significant improvements in human evaluation, especially against retrieval baselines where the image database is small.
Existing two-stream models for image-text matching show good performance while ensuring retrieval speed and have received extensive attention from industry and academia. These methods use a single representation to encode image and text separately and get a matching score with cosine similarity or the inner product of vectors. However, the performance of the two-stream model is often sub-optimal. On the one hand, a single representation is challenging to cover complex content comprehensively. On the other hand, in this framework of lack of interaction, it is challenging to match multiple meanings which leads to information being ignored. To address the problems mentioned above and facilitate the performance of the two-stream model, we propose a multi-view attention approach for two-stream image-text matching MVAM (\textbf{M}ulti-\textbf{V}iew \textbf{A}ttention \textbf{M}odel). It first learns multiple image and text representations by diverse attention heads with different view codes. And then concatenate these representations into one for matching. A diversity objective is also used to promote diversity between attention heads. With this method, models are able to encode images and text from different views and attend to more key points. So we can get representations that contain more information. When doing retrieval tasks, the matching scores between images and texts can be calculated from different aspects, leading to better matching performance. Experiment results on MSCOCO and Flickr30K show that our proposed model brings improvements over existing models. Further case studies show that different attention heads can focus on different contents and finally obtain a more comprehensive representation.
Text matching systems have become a fundamental service in most searching platforms. For instance, they are responsible for matching user queries to relevant candidate items, or rewriting the user-input query to a pre-selected high-performing one for a better search experience. In practice, both the queries and items often contain multiple attributes, such as the category of the item and the location mentioned in the query, which represent condensed key information that is helpful for matching. However, most of the existing works downplay the effectiveness of attributes by integrating them into text representations as supplementary information. Hence, in this work, we focus on exploring the relationship between the attributes from two sides. Since attributes from two ends are often not aligned in terms of number and type, we propose to exploit the benefit of attributes by multiple-intent modeling. The intents extracted from attributes summarize the diverse needs of queries and provide rich content of items, which are more refined and abstract, and can be aligned for paired inputs. Concretely, we propose a multi-intent attribute-aware matching model (MIM), which consists of three main components: attribute-aware encoder, multi-intent modeling, and intent-aware matching. In the attribute-aware encoder, the text and attributes are weighted and processed through a scaled attention mechanism with regard to the attributes' importance. Afterward, the multi-intent modeling extracts intents from two ends and aligns them. Herein, we come up with a distribution loss to ensure the learned intents are diverse but concentrated, and a kullback-leibler divergence loss that aligns the learned intents. Finally, in the intent-aware matching, the intents are evaluated by a self-supervised masking task, and then incorporated to output the final matching result.