This paper presents GPSM4K, a comprehensive geometry multimodal dataset tailored to augment the problem-solving capabilities of Large Vision Language Models (LVLMs). GPSM4K encompasses 2157 multimodal question-answer pairs manually extracted from mathematics textbooks spanning grades 7-12 and is further augmented to 5340 problems, consisting of both numerical and theorem-proving questions. In contrast to PGPS9k, Geometry3K, and Geo170K which feature only objective-type questions, GPSM4K offers detailed step-by-step solutions in a consistent format, facilitating a comprehensive evaluation of problem-solving approaches. This dataset serves as an excellent benchmark for assessing the geometric reasoning capabilities of LVLMs. Evaluation of our test set shows that there is scope for improvement needed in open-source language models in geometry problem-solving. Finetuning on our training set increases the geometry problem-solving capabilities of models. Further, We also evaluate the effectiveness of techniques such as image captioning and Retrieval Augmentation generation (RAG) on model performance. We leveraged LLM to automate the task of final answer evaluation by providing ground truth and predicted solutions. This research will help to assess and improve the geometric reasoning capabilities of LVLMs.
This paper analyzes the performance of Small Language Models (SLMs) and Vision Language Models (VLMs) and evaluates the trade-off between model performance and carbon emissions across 4 essential tasks: Image Captioning, Visual Question Answering (VQA), Dialogue Summarization and Text-to-SQL conversion. Various SLMs and VLMs belonging to the Qwen and LLaMA architecture family are chosen and variants based on model size in terms of the number of parameters, quantization level and fine-tuning parameters are evaluated. The model variant's performance and carbon emissions are calculated. To quantify the trade-off between model performance and carbon emissions, we introduce a novel metric called CEGI (Carbon Efficient Gain Index). This metric represents the carbon emission per unit percentage gain per million trainable parameters . This metric provides a normalized measure to compare model's efficiency in terms of performance improvement relative to their environmental cost. The experiment's outcome demonstrates that fine-tuning SLMs and VLMs can achieve performance levels comparable to Large Language Models (LLMs) while producing significantly less carbon emissions. Our findings suggest that the marginal gains in accuracy from larger models do not justify the substantial increase in carbon emissions. Leveraging lower-bit quantization levels, the proposed metric further enhances energy efficiency without compromising performance. This study highlights balancing high performance and environmental sustainability. It offers a valuable metric for selecting models suitable for environmentally-friendly AI development.
Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight inheritance. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations. Further, we find such an active data curation strategy to in fact be complementary to standard KD, and can be effectively combined to train highly performant inference-efficient models. Our simple and scalable pretraining framework, ACED, achieves state-of-the-art results across 27 zero-shot classification and retrieval tasks with upto 11% less inference FLOPs. We further demonstrate that our ACED models yield strong vision-encoders for training generative multimodal models in the LiT-Decoder setting, outperforming larger vision encoders for image-captioning and visual question-answering tasks.
The development of Multi-modal Large Language Models (MLLMs) enhances Large Language Models (LLMs) with the ability to perceive data formats beyond text, significantly advancing a range of downstream applications, such as visual question answering and image captioning. However, the substantial computational costs associated with processing high-resolution images and videos pose a barrier to their broader adoption. To address this challenge, compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs. While existing methods conduct token reduction in the feature alignment phase. In this paper, we introduce VisToG, a novel grouping mechanism that leverages the capabilities of pre-trained vision encoders to group similar image segments without the need for segmentation masks. Specifically, we concatenate semantic tokens to represent image semantic segments after the linear projection layer before feeding into the vision encoder. Besides, with the isolated attention we adopt, VisToG can identify and eliminate redundant visual tokens utilizing the prior knowledge in the pre-trained vision encoder, which effectively reduces computational demands. Extensive experiments demonstrate the effectiveness of VisToG, maintaining 98.1% of the original performance while achieving a reduction of over 27\% inference time.
In the current paradigm of image captioning, deep learning models are trained to generate text from image embeddings of latent features. We challenge the assumption that these latent features ought to be high-dimensional vectors which require model fine tuning to handle. Here we propose Label Boosted Retrieval Augmented Generation (LaB-RAG), a text-based approach to image captioning that leverages image descriptors in the form of categorical labels to boost standard retrieval augmented generation (RAG) with pretrained large language models (LLMs). We study our method in the context of radiology report generation (RRG), where the task is to generate a clinician's report detailing their observations from a set of radiological images, such as X-rays. We argue that simple linear classifiers over extracted image embeddings can effectively transform X-rays into text-space as radiology-specific labels. In combination with standard RAG, we show that these derived text labels can be used with general-domain LLMs to generate radiology reports. Without ever training our generative language model or image feature encoder models, and without ever directly "showing" the LLM an X-ray, we demonstrate that LaB-RAG achieves better results across natural language and radiology language metrics compared with other retrieval-based RRG methods, while attaining competitive results compared to other fine-tuned vision-language RRG models. We further present results of our experiments with various components of LaB-RAG to better understand our method. Finally, we critique the use of a popular RRG metric, arguing it is possible to artificially inflate its results without true data-leakage.
The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal tasks, enabling more sophisticated and accurate reasoning across various applications, including image and video captioning, visual question answering, and cross-modal retrieval. Despite their superior capabilities, VLMs struggle with fine-grained image regional composition information perception. Specifically, they have difficulty accurately aligning the segmentation masks with the corresponding semantics and precisely describing the compositional aspects of the referred regions. However, compositionality - the ability to understand and generate novel combinations of known visual and textual components - is critical for facilitating coherent reasoning and understanding across modalities by VLMs. To address this issue, we propose FINECAPTION, a novel VLM that can recognize arbitrary masks as referential inputs and process high-resolution images for compositional image captioning at different granularity levels. To support this endeavor, we introduce COMPOSITIONCAP, a new dataset for multi-grained region compositional image captioning, which introduces the task of compositional attribute-aware regional image captioning. Empirical results demonstrate the effectiveness of our proposed model compared to other state-of-the-art VLMs. Additionally, we analyze the capabilities of current VLMs in recognizing various visual prompts for compositional region image captioning, highlighting areas for improvement in VLM design and training.
Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become increasingly widespread, their potential safety and robustness issues raise concerns that adversaries may evade the system and cause these models to generate toxic content through malicious attacks. Therefore, evaluating the robustness of open-source VLMs against adversarial attacks has garnered growing attention, with transfer-based attacks as a representative black-box attacking strategy. However, most existing transfer-based attacks neglect the importance of the semantic correlations between vision and text modalities, leading to sub-optimal adversarial example generation and attack performance. To address this issue, we present Chain of Attack (CoA), which iteratively enhances the generation of adversarial examples based on the multi-modal semantic update using a series of intermediate attacking steps, achieving superior adversarial transferability and efficiency. A unified attack success rate computing method is further proposed for automatic evasion evaluation. Extensive experiments conducted under the most realistic and high-stakes scenario, demonstrate that our attacking strategy can effectively mislead models to generate targeted responses using only black-box attacks without any knowledge of the victim models. The comprehensive robustness evaluation in our paper provides insight into the vulnerabilities of VLMs and offers a reference for the safety considerations of future model developments.
Developing an interpretable system for generating reports in chest X-ray (CXR) analysis is becoming increasingly crucial in Computer-aided Diagnosis (CAD) systems, enabling radiologists to comprehend the decisions made by these systems. Despite the growth of diverse datasets and methods focusing on report generation, there remains a notable gap in how closely these models' generated reports align with the interpretations of real radiologists. In this study, we tackle this challenge by initially introducing Fine-Grained CXR (FG-CXR) dataset, which provides fine-grained paired information between the captions generated by radiologists and the corresponding gaze attention heatmaps for each anatomy. Unlike existing datasets that include a raw sequence of gaze alongside a report, with significant misalignment between gaze location and report content, our FG-CXR dataset offers a more grained alignment between gaze attention and diagnosis transcript. Furthermore, our analysis reveals that simply applying black-box image captioning methods to generate reports cannot adequately explain which information in CXR is utilized and how long needs to attend to accurately generate reports. Consequently, we propose a novel explainable radiologist's attention generator network (Gen-XAI) that mimics the diagnosis process of radiologists, explicitly constraining its output to closely align with both radiologist's gaze attention and transcript. Finally, we perform extensive experiments to illustrate the effectiveness of our method. Our datasets and checkpoint is available at https://github.com/UARK-AICV/FG-CXR.
Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative Adversarial Networks (GANs) to mitigate biases. We introduce DiffuBias, a novel pipeline for text-to-image generation that enhances classifier robustness by generating bias-conflict samples, without requiring training during the generation phase. Utilizing pretrained diffusion and image captioning models, DiffuBias generates images that challenge the biases of classifiers, using the top-$K$ losses from a biased classifier ($f_B$) to create more representative data samples. This method not only debiases effectively but also boosts classifier generalization capabilities. To the best of our knowledge, DiffuBias is the first approach leveraging a stable diffusion model to generate bias-conflict samples in debiasing tasks. Our comprehensive experimental evaluations demonstrate that DiffuBias achieves state-of-the-art performance on benchmark datasets. We also conduct a comparative analysis of various generative models in terms of carbon emissions and energy consumption to highlight the significance of computational efficiency.
Medical imaging has significantly revolutionized medical diagnostics and treatment planning, progressing from early X-ray usage to sophisticated methods like MRIs, CT scans, and ultrasounds. This paper investigates the use of deep learning for medical image captioning, with a particular focus on uterine ultrasound images. These images are vital in obstetrics and gynecology for diagnosing and monitoring various conditions across different age groups. However, their interpretation is often challenging due to their complexity and variability. To address this, a deep learning-based medical image captioning system was developed, integrating Convolutional Neural Networks with a Bidirectional Gated Recurrent Unit network. This hybrid model processes both image and text features to generate descriptive captions for uterine ultrasound images. Our experimental results demonstrate the effectiveness of this approach over baseline methods, with the proposed model achieving superior performance in generating accurate and informative captions, as indicated by higher BLEU and ROUGE scores. By enhancing the interpretation of uterine ultrasound images, our research aims to assist medical professionals in making timely and accurate diagnoses, ultimately contributing to improved patient care.
Supported by powerful generative models, low-bitrate learned image compression (LIC) models utilizing perceptual metrics have become feasible. Some of the most advanced models achieve high compression rates and superior perceptual quality by using image captions as sub-information. This paper demonstrates that using a large multi-modal model (LMM), it is possible to generate captions and compress them within a single model. We also propose a novel semantic-perceptual-oriented fine-tuning method applicable to any LIC network, resulting in a 41.58\% improvement in LPIPS BD-rate compared to existing methods. Our implementation and pre-trained weights are available at https://github.com/tokkiwa/ImageTextCoding.
Despite the impressive performance of large multimodal models (LMMs) in high-level visual tasks, their capacity for image quality assessment (IQA) remains limited. One main reason is that LMMs are primarily trained for high-level tasks (e.g., image captioning), emphasizing unified image semantics extraction under varied quality. Such semantic-aware yet quality-insensitive perception bias inevitably leads to a heavy reliance on image semantics when those LMMs are forced for quality rating. In this paper, instead of retraining or tuning an LMM costly, we propose a training-free debiasing framework, in which the image quality prediction is rectified by mitigating the bias caused by image semantics. Specifically, we first explore several semantic-preserving distortions that can significantly degrade image quality while maintaining identifiable semantics. By applying these specific distortions to the query or test images, we ensure that the degraded images are recognized as poor quality while their semantics remain. During quality inference, both a query image and its corresponding degraded version are fed to the LMM along with a prompt indicating that the query image quality should be inferred under the condition that the degraded one is deemed poor quality.This prior condition effectively aligns the LMM's quality perception, as all degraded images are consistently rated as poor quality, regardless of their semantic difference.Finally, the quality scores of the query image inferred under different prior conditions (degraded versions) are aggregated using a conditional probability model. Extensive experiments on various IQA datasets show that our debiasing framework could consistently enhance the LMM performance and the code will be publicly available.
Recent advancements in large language models (LLMs) and their multimodal variants have led to remarkable progress across various domains, demonstrating impressive capabilities and unprecedented potential. In the era of ubiquitous connectivity, leveraging communication networks to distribute intelligence is a transformative concept, envisioning AI-powered services accessible at the network edge. However, pushing large models from the cloud to resource-constrained environments faces critical challenges. Model inference on low-end devices leads to excessive latency and performance bottlenecks, while raw data transmission over limited bandwidth networks causes high communication overhead. This article presents AI Flow, a framework that streamlines the inference process by jointly leveraging the heterogeneous resources available across devices, edge nodes, and cloud servers, making intelligence flow across networks. To facilitate cooperation among multiple computational nodes, the proposed framework explores a paradigm shift in the design of communication network systems from transmitting information flow to intelligence flow, where the goal of communications is task-oriented and folded into the inference process. Experimental results demonstrate the effectiveness of the proposed framework through an image captioning use case, showcasing the ability to reduce response latency while maintaining high-quality captions. This article serves as a position paper for identifying the motivation, challenges, and principles of AI Flow.
In recent decades, chemistry publications and patents have increased rapidly. A significant portion of key information is embedded in molecular structure figures, complicating large-scale literature searches and limiting the application of large language models in fields such as biology, chemistry, and pharmaceuticals. The automatic extraction of precise chemical structures is of critical importance. However, the presence of numerous Markush structures in real-world documents, along with variations in molecular image quality, drawing styles, and noise, significantly limits the performance of existing optical chemical structure recognition (OCSR) methods. We present MolParser, a novel end-to-end OCSR method that efficiently and accurately recognizes chemical structures from real-world documents, including difficult Markush structure. We use a extended SMILES encoding rule to annotate our training dataset. Under this rule, we build MolParser-7M, the largest annotated molecular image dataset to our knowledge. While utilizing a large amount of synthetic data, we employed active learning methods to incorporate substantial in-the-wild data, specifically samples cropped from real patents and scientific literature, into the training process. We trained an end-to-end molecular image captioning model, MolParser, using a curriculum learning approach. MolParser significantly outperforms classical and learning-based methods across most scenarios, with potential for broader downstream applications. The dataset is publicly available.
Multimodal Large Language Model (MLLM) have demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. However, during fine-tuning, MLLM often faces the risk of forgetting knowledge acquired during pre-training, which can result in a decline in generalization abilities. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions, based on frozen pre-trained weight magnitude and accumulated fine-tuning gradient values. We further apply an importance-aware weight allocation strategy, selectively updating relatively important parameters for downstream tasks. We conduct empirical evaluations on both image captioning and visual question-answering tasks using various MLLM architectures. The comprehensive experimental analysis demonstrates the effectiveness of the proposed solution, highlighting the efficiency of the crucial modules in enhancing downstream specialization performance while mitigating generalization degradation in MLLM Fine-Tuning.
Large Multimodal Models (LMMs) exhibit impressive performance across various multimodal tasks. However, their effectiveness in cross-cultural contexts remains limited due to the predominantly Western-centric nature of most data and models. Conversely, multi-agent models have shown significant capability in solving complex tasks. Our study evaluates the collective performance of LMMs in a multi-agent interaction setting for the novel task of cultural image captioning. Our contributions are as follows: (1) We introduce MosAIC, a Multi-Agent framework to enhance cross-cultural Image Captioning using LMMs with distinct cultural personas; (2) We provide a dataset of culturally enriched image captions in English for images from China, India, and Romania across three datasets: GeoDE, GD-VCR, CVQA; (3) We propose a culture-adaptable metric for evaluating cultural information within image captions; and (4) We show that the multi-agent interaction outperforms single-agent models across different metrics, and offer valuable insights for future research. Our dataset and models can be accessed at https://github.com/MichiganNLP/MosAIC.
Recent research increasingly focuses on training vision-language models (VLMs) with long, detailed image captions. However, small-scale VLMs often struggle to balance the richness of these captions with the risk of hallucinating content during fine-tuning. In this paper, we explore how well VLMs adapt to such captions. To quantify caption quality, we propose Decomposed NLI (DNLI), an evaluation framework that breaks down generated captions into individual propositions, assessing each in isolation. This fine-grained analysis reveals a critical balance between capturing descriptive details and preventing hallucinations. Our findings show that simply reducing caption complexity or employing standard data curation techniques does not effectively resolve this issue. To tackle this challenge, we introduce Knowledge Adapted (KnowAda) fine-tuning, a data-centric approach that automatically adapts training data with the model's existing knowledge and visual understanding. KnowAda minimizes hallucinations while preserving high descriptiveness. We validate this approach across several small-scale VLMs (up to 7B parameters) and dense caption datasets, demonstrating that KnowAda effectively balances hallucination reduction and descriptiveness. Our results show that KnowAda outperforms various baselines in both automatic metrics and human evaluations. We will release our code and models.
Recent developments in multimodal methodologies have marked the beginning of an exciting era for models adept at processing diverse data types, encompassing text, audio, and visual content. Models like GPT-4V, which merge computer vision with advanced language processing, exhibit extraordinary proficiency in handling intricate tasks that require a simultaneous understanding of both textual and visual information. Prior research efforts have meticulously evaluated the efficacy of these Vision Large Language Models (VLLMs) in various domains, including object detection, image captioning, and other related fields. However, existing analyses have often suffered from limitations, primarily centering on the isolated evaluation of each modality's performance while neglecting to explore their intricate cross-modal interactions. Specifically, the question of whether these models achieve the same level of accuracy when confronted with identical task instances across different modalities remains unanswered. In this study, we take the initiative to delve into the interaction and comparison among these modalities of interest by introducing a novel concept termed cross-modal consistency. Furthermore, we propose a quantitative evaluation framework founded on this concept. Our experimental findings, drawn from a curated collection of parallel vision-language datasets developed by us, unveil a pronounced inconsistency between the vision and language modalities within GPT-4V, despite its portrayal as a unified multimodal model. Our research yields insights into the appropriate utilization of such models and hints at potential avenues for enhancing their design.
We propose a new task, dataset and model for grounded video caption generation. This task unifies captioning and object grounding in video, where the objects in the caption are grounded in the video via temporally consistent bounding boxes. We introduce the following contributions. First, we present a task definition and a manually annotated test dataset for this task, referred to as GROunded Video Caption Generation (GROC). Second, we introduce a large-scale automatic annotation method leveraging an existing model for grounded still image captioning together with an LLM for summarising frame-level captions into temporally consistent captions in video. Furthermore, we prompt the LLM to track by language -- classifying noun phrases from the frame-level captions into noun phrases of the video-level generated caption. We apply this approach to videos from the HowTo100M dataset, which results in a new large-scale training dataset, called HowToGround, with automatically annotated captions and spatio-temporally consistent bounding boxes with coherent natural language labels. Third, we introduce a new grounded video caption generation model, called VideoGround, and train the model on the new automatically annotated HowToGround dataset. Finally, results of our VideoGround model set the state of the art for the new task of grounded video caption generation. We perform extensive ablations and demonstrate the importance of key technical contributions of our model.
This paper presents ViTOC (Vision Transformer and Object-aware Captioner), a novel vision-language model for image captioning that addresses the challenges of accuracy and diversity in generated descriptions. Unlike conventional approaches, ViTOC employs a dual-path architecture based on Vision Transformer and object detector, effectively fusing global visual features and local object information through learnable vectors. The model introduces an innovative object-aware prompting strategy that significantly enhances its capability in handling long-tail data. Experiments on the standard COCO dataset demonstrate that ViTOC outperforms baseline models across all evaluation metrics. Additionally, we propose a reference-free evaluation method based on CLIP to further validate the model's effectiveness. By utilizing pretrained visual model parameters, ViTOC achieves efficient end-to-end training.