Performance on the most commonly used Visual Question Answering dataset (VQA v2) is starting to approach human accuracy. However, in interacting with state-of-the-art VQA models, it is clear that the problem is far from being solved. In order to stress test VQA models, we benchmark them against human-adversarial examples. Human subjects interact with a state-of-the-art VQA model, and for each image in the dataset, attempt to find a question where the model's predicted answer is incorrect. We find that a wide range of state-of-the-art models perform poorly when evaluated on these examples. We conduct an extensive analysis of the collected adversarial examples and provide guidance on future research directions. We hope that this Adversarial VQA (AdVQA) benchmark can help drive progress in the field and advance the state of the art.
Medical visual question answering (VQA) bridges the gap between visual information and clinical decision-making, enabling doctors to extract understanding from clinical images and videos. In particular, surgical VQA can enhance the interpretation of surgical data, aiding in accurate diagnoses, effective education, and clinical interventions. However, the inability of VQA models to visually indicate the regions of interest corresponding to the given questions results in incomplete comprehension of the surgical scene. To tackle this, we propose the surgical visual question localized-answering (VQLA) for precise and context-aware responses to specific queries regarding surgical images. Furthermore, to address the strong demand for safety in surgical scenarios and potential corruptions in image acquisition and transmission, we propose a novel approach called Calibrated Co-Attention Gated Vision-Language (C$^2$G-ViL) embedding to integrate and align multimodal information effectively. Additionally, we leverage the adversarial sample-based contrastive learning strategy to boost our performance and robustness. We also extend our EndoVis-18-VQLA and EndoVis-17-VQLA datasets to broaden the scope and application of our data. Extensive experiments on the aforementioned datasets demonstrate the remarkable performance and robustness of our solution. Our solution can effectively combat real-world image corruption. Thus, our proposed approach can serve as an effective tool for assisting surgical education, patient care, and enhancing surgical outcomes.
Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. Current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. Inspired by the human learning mechanism, we introduce LOVA3, an innovative framework named "Learning tO Visual question Answering, Asking and Assessment," designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming at fostering the skills of asking and assessing questions in the context of images. To develop the questioning ability, we compile a comprehensive set of multimodal foundational tasks. For assessment, we introduce a new benchmark called EvalQABench, comprising 64,000 training samples (split evenly between positive and negative samples) and 5,000 validation and testing samples. We posit that enhancing MLLMs with the capabilities to answer, ask, and assess questions will enhance their multimodal comprehension, ultimately improving overall performance. To validate this hypothesis, we train MLLMs using the LOVA3 framework and evaluate them on a range of multimodal datasets and benchmarks. Our results demonstrate consistent performance gains, underscoring the critical role of these additional tasks in fostering comprehensive intelligence in MLLMs. The code is available at https://github.com/showlab/LOVA3.
Visual document understanding is a complex task that involves analyzing both the text and the visual elements in document images. Existing models often rely on manual feature engineering or domain-specific pipelines, which limit their generalization ability across different document types and languages. In this paper, we propose DUBLIN, which is pretrained on web pages using three novel objectives: Masked Document Text Generation Task, Bounding Box Task, and Rendered Question Answering Task, that leverage both the spatial and semantic information in the document images. Our model achieves competitive or state-of-the-art results on several benchmarks, such as Web-Based Structural Reading Comprehension, Document Visual Question Answering, Key Information Extraction, Diagram Understanding, and Table Question Answering. In particular, we show that DUBLIN is the first pixel-based model to achieve an EM of 77.75 and F1 of 84.25 on the WebSRC dataset. We also show that our model outperforms the current pixel-based SOTA models on DocVQA, InfographicsVQA, OCR-VQA and AI2D datasets by 4.6%, 6.5%, 2.6% and 21%, respectively. We also achieve competitive performance on RVL-CDIP document classification. Moreover, we create new baselines for text-based datasets by rendering them as document images to promote research in this direction.
Remote Sensing Visual Question Answering (RSVQA) has gained significant research interest. However, current RSVQA methods are limited by the imaging mechanisms of optical sensors, particularly under challenging conditions such as cloud-covered and low-light scenarios. Given the all-time and all-weather imaging capabilities of Synthetic Aperture Radar (SAR), it is crucial to investigate the integration of optical-SAR images to improve RSVQA performance. In this work, we propose a Text-guided Coarse-to-Fine Fusion Network (TGFNet), which leverages the semantic relationships between question text and multi-source images to guide the network toward complementary fusion at the feature level. Specifically, we develop a Text-guided Coarse-to-Fine Attention Refinement (CFAR) module to focus on key areas related to the question in complex remote sensing images. This module progressively directs attention from broad areas to finer details through key region routing, enhancing the model's ability to focus on relevant regions. Furthermore, we propose an Adaptive Multi-Expert Fusion (AMEF) module that dynamically integrates different experts, enabling the adaptive fusion of optical and SAR features. In addition, we create the first large-scale benchmark dataset for evaluating optical-SAR RSVQA methods, comprising 6,008 well-aligned optical-SAR image pairs and 1,036,694 well-labeled question-answer pairs across 16 diverse question types, including complex relational reasoning questions. Extensive experiments on the proposed dataset demonstrate that our TGFNet effectively integrates complementary information between optical and SAR images, significantly improving the model's performance in challenging scenarios. The dataset is available at: https://github.com/mmic-lcl/. Index Terms: Remote Sensing Visual Question Answering, Multi-source Data Fusion, Multimodal, Remote Sensing, OPT-SAR.
What does it take to design a machine that learns to answer natural questions about a video? A Video QA system must simultaneously understand language, represent visual content over space-time, and iteratively transform these representations in response to lingual content in the query, and finally arriving at a sensible answer. While recent advances in lingual and visual question answering have enabled sophisticated representations and neural reasoning mechanisms, major challenges in Video QA remain on dynamic grounding of concepts, relations and actions to support the reasoning process. Inspired by the dual-process account of human reasoning, we design a dual process neural architecture, which is composed of a question-guided video processing module (System 1, fast and reactive) followed by a generic reasoning module (System 2, slow and deliberative). System 1 is a hierarchical model that encodes visual patterns about objects, actions and relations in space-time given the textual cues from the question. The encoded representation is a set of high-level visual features, which are then passed to System 2. Here multi-step inference follows to iteratively chain visual elements as instructed by the textual elements. The system is evaluated on the SVQA (synthetic) and TGIF-QA datasets (real), demonstrating competitive results, with a large margin in the case of multi-step reasoning.
In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e.g., only around 800 scenes are utilized in ScanQA and SQA dataset). Current approaches resort supplement 3D reasoning with 2D information. However, these methods face challenges: either they use top-down 2D views that introduce overly complex and sometimes question-irrelevant visual clues, or they rely on globally aggregated scene/image-level representations from 2D VLMs, losing the fine-grained vision-language correlations. To overcome these limitations, our approach utilizes question-conditional 2D view selection procedure, pinpointing semantically relevant 2D inputs for crucial visual clues. We then integrate this 2D knowledge into the 3D-VQA system via a two-branch Transformer structure. This structure, featuring a Twin-Transformer design, compactly combines 2D and 3D modalities and captures fine-grained correlations between modalities, allowing them mutually augmenting each other. Integrating proposed mechanisms above, we present BridgeQA, that offers a fresh perspective on multi-modal transformer-based architectures for 3D-VQA. Experiments validate that BridgeQA achieves state-of-the-art on 3D-VQA datasets and significantly outperforms existing solutions. Code is available at $\href{https://github.com/matthewdm0816/BridgeQA}{\text{this URL}}$.
With the growing number and size of Linked Data datasets, it is crucial to make the data accessible and useful for users without knowledge of formal query languages. Two approaches towards this goal are knowledge graph visualization and natural language interfaces. Here, we investigate specifically question answering (QA) over Linked Data by comparing a diagrammatic visual approach with existing natural language-based systems. Given a QA benchmark (QALD7), we evaluate a visual method which is based on iteratively creating diagrams until the answer is found, against four QA systems that have natural language queries as input. Besides other benefits, the visual approach provides higher performance, but also requires more manual input. The results indicate that the methods can be used complementary, and that such a combination has a large positive impact on QA performance, and also facilitates additional features such as data exploration.
스트리밍 비디오 이해는 지속적으로 늘어나는 시각 스트림 위에서 임의의 시점에 질문에 답해야 한다. 핵심 과제는 장기 이력을 압축적으로 기억하면서 질문과 관련된 근거를 효과적으로 검색하는 것이다. 우리는 Dynamic Hub-and-Spoke Memory(D-HSM)를 제안한다. 이는 먼 과거 이력을 구조화된 텍스트 메모리로 표현하고, 세밀한 지각을 위해 최근 프레임은 visual token으로 유지하는 추가 학습 없는 프레임워크이다. 구체적으로 D-HSM은 선택된 과거 비디오 청크를 유형이 부여된 텍스트 관측으로 바꾸어 엔터티를 허브(hub)로, 관련 근거를 스poke(spoke)로 두는 엔터티 중심 허브-앤-스poke 메모리에 저장한다. 질문에 답할 때 D-HSM은 질문에 맞춘(question-aware) 압축 메모리 부분집합을 동적으로 검색하고, 허브-앤-스poke 연결을 통해 확장한 뒤 최근 visual window와 결합하여 frozen-VLM으로 답을 예측한다. 스트리밍 및 장시간 비디오 벤치마크에 대한 광범위한 실험에서 D-HSM은 VLM 백본을 일관되고 크게 개선하며, 다른 최신(state-of-the-art) 온라인·오프라인 비디오 이해 베이스라인을 능가함을 보인다.
Visual Question Answering (VQA) is the task of taking as input an image and a free-form natural language question about the image, and producing an accurate answer. In this work we view VQA as a "feature extraction" module to extract image and caption representations. We employ these representations for the task of image-caption ranking. Each feature dimension captures (imagines) whether a fact (question-answer pair) could plausibly be true for the image and caption. This allows the model to interpret images and captions from a wide variety of perspectives. We propose score-level and representation-level fusion models to incorporate VQA knowledge in an existing state-of-the-art VQA-agnostic image-caption ranking model. We find that incorporating and reasoning about consistency between images and captions significantly improves performance. Concretely, our model improves state-of-the-art on caption retrieval by 7.1% and on image retrieval by 4.4% on the MSCOCO dataset.
Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations. Previous approaches extensively employ entity-level alignments, such as the correlations between the visual regions and their semantic labels, or the interactions across question words and object features. These attempts aim to improve the cross-modality representations, while ignoring their internal relations. Instead, we propose to apply structured alignments, which work with graph representation of visual and textual content, aiming to capture the deep connections between the visual and textual modalities. Nevertheless, it is nontrivial to represent and integrate graphs for structured alignments. In this work, we attempt to solve this issue by first converting different modality entities into sequential nodes and the adjacency graph, then incorporating them for structured alignments. As demonstrated in our experimental results, such a structured alignment improves reasoning performance. In addition, our model also exhibits better interpretability for each generated answer. The proposed model, without any pretraining, outperforms the state-of-the-art methods on GQA dataset, and beats the non-pretrained state-of-the-art methods on VQA-v2 dataset.
Visual Question Answering (VQA) models aim to answer natural language questions about given images. Due to its ability to ask questions that differ from those used when training the model, medical VQA has received substantial attention in recent years. However, existing medical VQA models typically focus on answering questions that refer to an entire image rather than where the relevant content may be located in the image. Consequently, VQA models are limited in their interpretability power and the possibility to probe the model about specific image regions. This paper proposes a novel approach for medical VQA that addresses this limitation by developing a model that can answer questions about image regions while considering the context necessary to answer the questions. Our experimental results demonstrate the effectiveness of our proposed model, outperforming existing methods on three datasets. Our code and data are available at https://github.com/sergiotasconmorales/locvqa.
The complex compositional structure of language makes problems at the intersection of vision and language challenging. But language also provides a strong prior that can result in good superficial performance, without the underlying models truly understanding the visual content. This can hinder progress in pushing state of art in the computer vision aspects of multi-modal AI. In this paper, we address binary Visual Question Answering (VQA) on abstract scenes. We formulate this problem as visual verification of concepts inquired in the questions. Specifically, we convert the question to a tuple that concisely summarizes the visual concept to be detected in the image. If the concept can be found in the image, the answer to the question is "yes", and otherwise "no". Abstract scenes play two roles (1) They allow us to focus on the high-level semantics of the VQA task as opposed to the low-level recognition problems, and perhaps more importantly, (2) They provide us the modality to balance the dataset such that language priors are controlled, and the role of vision is essential. In particular, we collect fine-grained pairs of scenes for every question, such that the answer to the question is "yes" for one scene, and "no" for the other for the exact same question. Indeed, language priors alone do not perform better than chance on our balanced dataset. Moreover, our proposed approach matches the performance of a state-of-the-art VQA approach on the unbalanced dataset, and outperforms it on the balanced dataset.
Visual Question Answering (VQA) is the task of answering a question about an image and requires processing multimodal input and reasoning to obtain the answer. Modular solutions that use declarative representations within the reasoning component have a clear advantage over end-to-end trained systems regarding interpretability. The downside is that crafting the rules for such a component can be an additional burden on the developer. We address this challenge by presenting an approach for declarative knowledge distillation from Large Language Models (LLMs). Our method is to prompt an LLM to extend an initial theory on VQA reasoning, given as an answer-set program, to meet the requirements of the VQA task. Examples from the VQA dataset are used to guide the LLM, validate the results, and mend rules if they are not correct by using feedback from the ASP solver. We demonstrate that our approach works on the prominent CLEVR and GQA datasets. Our results confirm that distilling knowledge from LLMs is in fact a promising direction besides data-driven rule learning approaches.
Performing high level cognitive tasks requires the integration of feature maps with drastically different structure. In Visual Question Answering (VQA) image descriptors have spatial structures, while lexical inputs inherently follow a temporal sequence. The recently proposed Multimodal Compact Bilinear pooling (MCB) forms the outer products, via count-sketch approximation, of the visual and textual representation at each spatial location. While this procedure preserves spatial information locally, outer-products are taken independently for each fiber of the activation tensor, and therefore do not include spatial context. In this work, we introduce multi-dimensional sketch ({MD-sketch}), a novel extension of count-sketch to tensors. Using this new formulation, we propose Multimodal Compact Tensor Pooling (MCT) to fully exploit the global spatial context during bilinear pooling operations. Contrarily to MCB, our approach preserves spatial context by directly convolving the MD-sketch from the visual tensor features with the text vector feature using higher order FFT. Furthermore we apply MCT incrementally at each step of the question embedding and accumulate the multi-modal vectors with a second LSTM layer before the final answer is chosen.
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.
Visual question answering (VQA) systems are emerging from a desire to empower users to ask any natural language question about visual content and receive a valid answer in response. However, close examination of the VQA problem reveals an unavoidable, entangled problem that multiple humans may or may not always agree on a single answer to a visual question. We train a model to automatically predict from a visual question whether a crowd would agree on a single answer. We then propose how to exploit this system in a novel application to efficiently allocate human effort to collect answers to visual questions. Specifically, we propose a crowdsourcing system that automatically solicits fewer human responses when answer agreement is expected and more human responses when answer disagreement is expected. Our system improves upon existing crowdsourcing systems, typically eliminating at least 20% of human effort with no loss to the information collected from the crowd.
We present Q-ViD, a simple approach for video question answering (video QA), that unlike prior methods, which are based on complex architectures, computationally expensive pipelines or use closed models like GPTs, Q-ViD relies on a single instruction-aware open vision-language model (InstructBLIP) to tackle videoQA using frame descriptions. Specifically, we create captioning instruction prompts that rely on the target questions about the videos and leverage InstructBLIP to obtain video frame captions that are useful to the task at hand. Subsequently, we form descriptions of the whole video using the question-dependent frame captions, and feed that information, along with a question-answering prompt, to a large language model (LLM). The LLM is our reasoning module, and performs the final step of multiple-choice QA. Our simple Q-ViD framework achieves competitive or even higher performances than current state of the art models on a diverse range of videoQA benchmarks, including NExT-QA, STAR, How2QA, TVQA and IntentQA.
We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design challenging questions, yet we experimentally show that humans struggle to predict which questions are difficult for machine learning models. Our automatic approach leverages recent advances in code generation for visual question answering, using the complexity of generated code as a proxy for question difficulty. We demonstrate that this measure correlates significantly better with model performance than human estimates. To operationalize this insight, we propose an algorithm for estimating question complexity from code. It identifies fine-grained primitives that correlate with the hardest questions for any given set of models, making it easy to scale to new approaches in the future. Finally, to further illustrate the utility of our method, we extend it to automatically generate complex questions, constructing a new benchmark that is 1.9 times harder than the popular NExT-QA.
We present a novel prompt-based personalized federated learning (pFL) method to address data heterogeneity and privacy concerns in traditional medical visual question answering (VQA) methods. Specifically, we regard medical datasets from different organs as clients and use pFL to train personalized transformer-based VQA models for each client. To address the high computational complexity of client-to-client communication in previous pFL methods, we propose a succinct information sharing system by introducing prompts that are small learnable parameters. In addition, the proposed method introduces a reliability parameter to prevent the negative effects of low performance and irrelevant clients. Finally, extensive evaluations on various heterogeneous medical datasets attest to the effectiveness of our proposed method.