In this paper, we present OtterHD-8B, an innovative multimodal model evolved from Fuyu-8B, specifically engineered to interpret high-resolution visual inputs with granular precision. Unlike conventional models that are constrained by fixed-size vision encoders, OtterHD-8B boasts the ability to handle flexible input dimensions, ensuring its versatility across various inference requirements. Alongside this model, we introduce MagnifierBench, an evaluation framework designed to scrutinize models' ability to discern minute details and spatial relationships of small objects. Our comparative analysis reveals that while current leading models falter on this benchmark, OtterHD-8B, particularly when directly processing high-resolution inputs, outperforms its counterparts by a substantial margin. The findings illuminate the structural variances in visual information processing among different models and the influence that the vision encoders' pre-training resolution disparities have on model effectiveness within such benchmarks. Our study highlights the critical role of flexibility and high-resolution input capabilities in large multimodal models and also exemplifies the potential inherent in the Fuyu architecture's simplicity for handling complex visual data.
Large Multimodal Model (LMM) GPT-4V(ision) endows GPT-4 with visual grounding capabilities, making it possible to handle certain tasks through the Visual Question Answering (VQA) paradigm. This paper explores the potential of VQA-oriented GPT-4V in the recently popular visual Anomaly Detection (AD) and is the first to conduct qualitative and quantitative evaluations on the popular MVTec AD and VisA datasets. Considering that this task requires both image-/pixel-level evaluations, the proposed GPT-4V-AD framework contains three components: \textbf{\textit{1)}} Granular Region Division, \textbf{\textit{2)}} Prompt Designing, \textbf{\textit{3)}} Text2Segmentation for easy quantitative evaluation, and have made some different attempts for comparative analysis. The results show that GPT-4V can achieve certain results in the zero-shot AD task through a VQA paradigm, such as achieving image-level 77.1/88.0 and pixel-level 68.0/76.6 AU-ROCs on MVTec AD and VisA datasets, respectively. However, its performance still has a certain gap compared to the state-of-the-art zero-shot method, \eg, WinCLIP and CLIP-AD, and further researches are needed. This study provides a baseline reference for the research of VQA-oriented LMM in the zero-shot AD task, and we also post several possible future works. Code is available at \url{https://github.com/zhangzjn/GPT-4V-AD}.
A remarkable ability of human beings resides in compositional reasoning, i.e., the capacity to make "infinite use of finite means". However, current large vision-language foundation models (VLMs) fall short of such compositional abilities due to their "bag-of-words" behaviors and inability to construct words that correctly represent visual entities and the relations among the entities. To this end, we propose CoVLM, which can guide the LLM to explicitly compose visual entities and relationships among the text and dynamically communicate with the vision encoder and detection network to achieve vision-language communicative decoding. Specifically, we first devise a set of novel communication tokens for the LLM, for dynamic communication between the visual detection system and the language system. A communication token is generated by the LLM following a visual entity or a relation, to inform the detection network to propose regions that are relevant to the sentence generated so far. The proposed regions-of-interests (ROIs) are then fed back into the LLM for better language generation contingent on the relevant regions. The LLM is thus able to compose the visual entities and relationships through the communication tokens. The vision-to-language and language-to-vision communication are iteratively performed until the entire sentence is generated. Our framework seamlessly bridges the gap between visual perception and LLMs and outperforms previous VLMs by a large margin on compositional reasoning benchmarks (e.g., ~20% in HICO-DET mAP, ~14% in Cola top-1 accuracy, and ~3% on ARO top-1 accuracy). We also achieve state-of-the-art performances on traditional vision-language tasks such as referring expression comprehension and visual question answering.
We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular shallow alignment method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen pretrained language model and image encoder by a trainable visual expert module in the attention and FFN layers. As a result, CogVLM enables deep fusion of vision language features without sacrificing any performance on NLP tasks. CogVLM-17B achieves state-of-the-art performance on 10 classic cross-modal benchmarks, including NoCaps, Flicker30k captioning, RefCOCO, RefCOCO+, RefCOCOg, Visual7W, GQA, ScienceQA, VizWiz VQA and TDIUC, and ranks the 2nd on VQAv2, OKVQA, TextVQA, COCO captioning, etc., surpassing or matching PaLI-X 55B. Codes and checkpoints are available at https://github.com/THUDM/CogVLM.
Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization datasets for VQA exhibit a unilateral focus on textual shifts while VQA being a multi-modal task contains shifts across both visual and textual domains. We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. Experiments demonstrate VQA-GEN dataset exposes the vulnerability of existing methods to joint multi-modal distribution shifts. validating that comprehensive multi-modal shifts are critical for robust VQA generalization. Models trained on VQA-GEN exhibit improved cross-domain and in-domain performance, confirming the value of VQA-GEN. Further, we analyze the importance of each shift technique of our pipeline contributing to the generalization of the model.
The multimodal task of Visual Question Answering (VQA) encompassing elements of Computer Vision (CV) and Natural Language Processing (NLP), aims to generate answers to questions on any visual input. Over time, the scope of VQA has expanded from datasets focusing on an extensive collection of natural images to datasets featuring synthetic images, video, 3D environments, and various other visual inputs. The emergence of large pre-trained networks has shifted the early VQA approaches relying on feature extraction and fusion schemes to vision language pre-training (VLP) techniques. However, there is a lack of comprehensive surveys that encompass both traditional VQA architectures and contemporary VLP-based methods. Furthermore, the VLP challenges in the lens of VQA haven't been thoroughly explored, leaving room for potential open problems to emerge. Our work presents a survey in the domain of VQA that delves into the intricacies of VQA datasets and methods over the field's history, introduces a detailed taxonomy to categorize the facets of VQA, and highlights the recent trends, challenges, and scopes for improvement. We further generalize VQA to multimodal question answering, explore tasks related to VQA, and present a set of open problems for future investigation. The work aims to navigate both beginners and experts by shedding light on the potential avenues of research and expanding the boundaries of the field.
Although large language models (LLMs) have advanced the state-of-the-art in NLP significantly, deploying them for downstream applications is still challenging due to cost, responsiveness, control, or concerns around privacy and security. As such, trainable models are still the preferred option in some cases. However, these models still require human-labeled data for optimal performance, which is expensive and time-consuming to obtain. In order to address this issue, several techniques to reduce human effort involve labeling or generating data using LLMs. Although these methods are effective for certain applications, in practice they encounter difficulties in real-world scenarios. Labeling data requires careful data selection, while generating data necessitates task-specific prompt engineering. In this paper, we propose a unified data creation pipeline that requires only a single formatting example, and which is applicable to a broad range of tasks, including traditionally problematic ones with semantically devoid label spaces. In our experiments we demonstrate that instruction-following LLMs are highly cost-effective data creators, and that models trained with these data exhibit performance better than those trained with human-labeled data (by up to 17.5%) on out-of-distribution evaluation, while maintaining comparable performance on in-distribution tasks. These results have important implications for the robustness of NLP systems deployed in the real-world.
Visual question answering (VQA) is the task of answering questions about an image. The task assumes an understanding of both the image and the question to provide a natural language answer. VQA has gained popularity in recent years due to its potential applications in a wide range of fields, including robotics, education, and healthcare. In this paper, we focus on knowledge-augmented VQA, where answering the question requires commonsense knowledge, world knowledge, and reasoning about ideas and concepts not present in the image. We propose a multimodal framework that uses language guidance (LG) in the form of rationales, image captions, scene graphs, etc to answer questions more accurately. We benchmark our method on the multi-choice question-answering task of the A-OKVQA, Science-QA, VSR, and IconQA datasets using CLIP and BLIP models. We show that the use of language guidance is a simple but powerful and effective strategy for visual question answering. Our language guidance improves the performance of CLIP by 7.6% and BLIP-2 by 4.8% in the challenging A-OKVQA dataset. We also observe consistent improvement in performance on the Science-QA, VSR, and IconQA datasets when using the proposed language guidances. The implementation of LG-VQA is publicly available at https:// github.com/declare-lab/LG-VQA.
This work conducts an evaluation of GPT-4V's multimodal capability for medical image analysis, with a focus on three representative tasks of radiology report generation, medical visual question answering, and medical visual grounding. For the evaluation, a set of prompts is designed for each task to induce the corresponding capability of GPT-4V to produce sufficiently good outputs. Three evaluation ways including quantitative analysis, human evaluation, and case study are employed to achieve an in-depth and extensive evaluation. Our evaluation shows that GPT-4V excels in understanding medical images and is able to generate high-quality radiology reports and effectively answer questions about medical images. Meanwhile, it is found that its performance for medical visual grounding needs to be substantially improved. In addition, we observe the discrepancy between the evaluation outcome from quantitative analysis and that from human evaluation. This discrepancy suggests the limitations of conventional metrics in assessing the performance of large language models like GPT-4V and the necessity of developing new metrics for automatic quantitative analysis.
Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecification (the need to model the implicit meaning of instructions) 2) grounding (the need to localize where the edit has to be performed), 3) faithfulness (the need to preserve the elements of the image not affected by the edit instruction). Current approaches focusing on image editing with natural language instructions rely on automatically generated paired data, which, as shown in our investigation, is noisy and sometimes nonsensical, exacerbating the above issues. Building on recent advances in segmentation, Chain-of-Thought prompting, and visual question answering, we significantly improve the quality of the paired data. In addition, we enhance the supervision signal by highlighting parts of the image that need to be changed by the instruction. The model fine-tuned on the improved data is capable of performing fine-grained object-centric edits better than state-of-the-art baselines, mitigating the problems outlined above, as shown by automatic and human evaluations. Moreover, our model is capable of generalizing to domains unseen during training, such as visual metaphors.
In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i.e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task. Our experiments thoroughly assess GPT-4V's proficiency in answering questions paired with images using both pathology and radiology datasets from 11 modalities (e.g. Microscopy, Dermoscopy, X-ray, CT, etc.) and fifteen objects of interests (brain, liver, lung, etc.). Our datasets encompass a comprehensive range of medical inquiries, including sixteen distinct question types. Throughout our evaluations, we devised textual prompts for GPT-4V, directing it to synergize visual and textual information. The experiments with accuracy score conclude that the current version of GPT-4V is not recommended for real-world diagnostics due to its unreliable and suboptimal accuracy in responding to diagnostic medical questions. In addition, we delineate seven unique facets of GPT-4V's behavior in medical VQA, highlighting its constraints within this complex arena. The complete details of our evaluation cases are accessible at https://github.com/ZhilingYan/GPT4V-Medical-Report.
This paper explores post-disaster analytics using multimodal deep learning models trained with curriculum learning method. Studying post-disaster analytics is important as it plays a crucial role in mitigating the impact of disasters by providing timely and accurate insights into the extent of damage and the allocation of resources. We propose a curriculum learning strategy to enhance the performance of multimodal deep learning models. Curriculum learning emulates the progressive learning sequence in human education by training deep learning models on increasingly complex data. Our primary objective is to develop a curriculum-trained multimodal deep learning model, with a particular focus on visual question answering (VQA) capable of jointly processing image and text data, in conjunction with semantic segmentation for disaster analytics using the FloodNet\footnote{https://github.com/BinaLab/FloodNet-Challenge-EARTHVISION2021} dataset. To achieve this, U-Net model is used for semantic segmentation and image encoding. A custom built text classifier is used for visual question answering. Existing curriculum learning methods rely on manually defined difficulty functions. We introduce a novel curriculum learning approach termed Dynamic Task and Weight Prioritization (DATWEP), which leverages a gradient-based method to automatically decide task difficulty during curriculum learning training, thereby eliminating the need for explicit difficulty computation. The integration of DATWEP into our multimodal model shows improvement on VQA performance. Source code is available at https://github.com/fualsan/DATWEP.
In recent years, Visual Question Answering (VQA) has gained significant attention for its diverse applications, including intelligent car assistance, aiding visually impaired individuals, and document image information retrieval using natural language queries. VQA requires effective integration of information from questions and images to generate accurate answers. Neural models for VQA have made remarkable progress on large-scale datasets, with a primary focus on resource-rich languages like English. To address this, we introduce the ViCLEVR dataset, a pioneering collection for evaluating various visual reasoning capabilities in Vietnamese while mitigating biases. The dataset comprises over 26,000 images and 30,000 question-answer pairs (QAs), each question annotated to specify the type of reasoning involved. Leveraging this dataset, we conduct a comprehensive analysis of contemporary visual reasoning systems, offering valuable insights into their strengths and limitations. Furthermore, we present PhoVIT, a comprehensive multimodal fusion that identifies objects in images based on questions. The architecture effectively employs transformers to enable simultaneous reasoning over textual and visual data, merging both modalities at an early model stage. The experimental findings demonstrate that our proposed model achieves state-of-the-art performance across four evaluation metrics. The accompanying code and dataset have been made publicly accessible at \url{https://github.com/kvt0012/ViCLEVR}. This provision seeks to stimulate advancements within the research community, fostering the development of more multimodal fusion algorithms, specifically tailored to address the nuances of low-resource languages, exemplified by Vietnamese.
Evaluating text-to-image models is notoriously difficult. A strong recent approach for assessing text-image faithfulness is based on QG/A (question generation and answering), which uses pre-trained foundational models to automatically generate a set of questions and answers from the prompt, and output images are scored based on whether these answers extracted with a visual question answering model are consistent with the prompt-based answers. This kind of evaluation is naturally dependent on the quality of the underlying QG and VQA models. We identify and address several reliability challenges in existing QG/A work: (a) QG questions should respect the prompt (avoiding hallucinations, duplications, and omissions) and (b) VQA answers should be consistent (not asserting that there is no motorcycle in an image while also claiming the motorcycle is blue). We address these issues with Davidsonian Scene Graph (DSG), an empirically grounded evaluation framework inspired by formal semantics, which is adaptable to any QG/A frameworks. DSG produces atomic and unique questions organized in dependency graphs, which (i) ensure appropriate semantic coverage and (ii) sidestep inconsistent answers. With extensive experimentation and human evaluation on a range of model configurations (LLM, VQA, and T2I), we empirically demonstrate that DSG addresses the challenges noted above. Finally, we present DSG-1k, an open-sourced evaluation benchmark that includes 1,060 prompts, covering a wide range of fine-grained semantic categories with a balanced distribution. We release the DSG-1k prompts and the corresponding DSG questions.
Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake images, where the existing methods typically learn classifiers in the image domain or various feature domains. However, the generalizability of deepfake detection against emerging and more advanced generative models remains challenging. In this paper, being inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel approach called AntifakePrompt, using VLMs (e.g., InstructBLIP) and prompt tuning techniques to improve the deepfake detection accuracy over unseen data. We formulate deepfake detection as a visual question answering problem, and tune soft prompts for InstructBLIP to answer the real/fake information of a query image. We conduct full-spectrum experiments on datasets from a diversity of 3 held-in and 20 held-out generative models, covering modern text-to-image generation, image editing and adversarial image attacks. These testing datasets provide useful benchmarks in the realm of deepfake detection for further research. Moreover, results demonstrate that (1) the deepfake detection accuracy can be significantly and consistently improved (from 71.06% to 92.11%, in average accuracy over unseen domains) using pretrained vision-language models with prompt tuning; (2) our superior performance is at less cost of training data and trainable parameters, resulting in an effective and efficient solution for deepfake detection. Code and models can be found at https://github.com/nctu-eva-lab/AntifakePrompt.
Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering strategies. We explore a question decomposition strategy for VQA to overcome this limitation. We probe the ability of recently developed large vision-language models to use human-written decompositions and produce their own decompositions of visual questions, finding they are capable of learning both tasks from demonstrations alone. However, we show that naive application of model-written decompositions can hurt performance. We introduce a model-driven selective decomposition approach for second-guessing predictions and correcting errors, and validate its effectiveness on eight VQA tasks across three domains, showing consistent improvements in accuracy, including improvements of >20% on medical VQA datasets and boosting the zero-shot performance of BLIP-2 above chance on a VQA reformulation of the challenging Winoground task. Project Site: https://zaidkhan.me/decomposition-0shot-vqa/
This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual information when text inputs are complete. Instead, we attribute this phenomenon to insufficient cross-modal interaction, rather than image information redundancy. A novel approach is proposed to generate parallel Visual Question-Answering (VQA) style pairs from the source text, fostering more robust cross-modal interaction. Using Large Language Models (LLMs), we explicitly model the probing signal in MMT to convert it into VQA-style data to create the Multi30K-VQA dataset. An MMT-VQA multitask learning framework is introduced to incorporate explicit probing signals from the dataset into the MMT training process. Experimental results on two widely-used benchmarks demonstrate the effectiveness of this novel approach. Our code and data would be available at: \url{https://github.com/libeineu/MMT-VQA}.
This paper introduces a deep learning model tailored for document information analysis, emphasizing document classification, entity relation extraction, and document visual question answering. The proposed model leverages transformer-based models to encode all the information present in a document image, including textual, visual, and layout information. The model is pre-trained and subsequently fine-tuned for various document image analysis tasks. The proposed model incorporates three additional tasks during the pre-training phase, including reading order identification of different layout segments in a document image, layout segments categorization as per PubLayNet, and generation of the text sequence within a given layout segment (text block). The model also incorporates a collective pre-training scheme where losses of all the tasks under consideration, including pre-training and fine-tuning tasks with all datasets, are considered. Additional encoder and decoder blocks are added to the RoBERTa network to generate results for all tasks. The proposed model achieved impressive results across all tasks, with an accuracy of 95.87% on the RVL-CDIP dataset for document classification, F1 scores of 0.9306, 0.9804, 0.9794, and 0.8742 on the FUNSD, CORD, SROIE, and Kleister-NDA datasets respectively for entity relation extraction, and an ANLS score of 0.8468 on the DocVQA dataset for visual question answering. The results highlight the effectiveness of the proposed model in understanding and interpreting complex document layouts and content, making it a promising tool for document analysis tasks.
In the context of Audio Visual Question Answering (AVQA) tasks, the audio visual modalities could be learnt on three levels: 1) Spatial, 2) Temporal, and 3) Semantic. Existing AVQA methods suffer from two major shortcomings; the audio-visual (AV) information passing through the network isn't aligned on Spatial and Temporal levels; and, inter-modal (audio and visual) Semantic information is often not balanced within a context; this results in poor performance. In this paper, we propose a novel end-to-end Contextual Multi-modal Alignment (CAD) network that addresses the challenges in AVQA methods by i) introducing a parameter-free stochastic Contextual block that ensures robust audio and visual alignment on the Spatial level; ii) proposing a pre-training technique for dynamic audio and visual alignment on Temporal level in a self-supervised setting, and iii) introducing a cross-attention mechanism to balance audio and visual information on Semantic level. The proposed novel CAD network improves the overall performance over the state-of-the-art methods on average by 9.4% on the MUSIC-AVQA dataset. We also demonstrate that our proposed contributions to AVQA can be added to the existing methods to improve their performance without additional complexity requirements.
Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream applications and domains. Given the great potential for the broad use of these models, it is important to investigate their limitations in dealing with different image and question properties. In this work, we investigate whether MLLMs can perceive small details as well as large details in images. In particular, we show that their zero-shot accuracy in answering visual questions is very sensitive to the size of the visual subject of the question, declining up to 46% with size. Furthermore, we show that this effect is causal by observing that human visual cropping can significantly mitigate their sensitivity to size. Inspired by the usefulness of human cropping, we then propose five automatic visual cropping methods -- leveraging either external localization models or the decision process of the given MLLM itself -- as inference time mechanisms to improve the zero-shot performance of MLLMs. We study their effectiveness on four popular VQA datasets, and a subset of the VQAv2 dataset tailored towards fine visual details. Our findings suggest that MLLMs should be used with caution in detail-sensitive VQA applications, and that visual cropping is a promising direction to improve their zero-shot performance. To facilitate further investigation of MLLMs' behaviors, our code and data are publicly released.