Large language models have demonstrated substantial advancements in reasoning capabilities, particularly through inference-time scaling, as illustrated by models such as OpenAI's o1. However, current Vision-Language Models (VLMs) often struggle to perform systematic and structured reasoning, especially when handling complex visual question-answering tasks. In this work, we introduce LLaVA-CoT, a novel VLM designed to conduct autonomous multistage reasoning. Unlike chain-of-thought prompting, LLaVA-CoT independently engages in sequential stages of summarization, visual interpretation, logical reasoning, and conclusion generation. This structured approach enables LLaVA-CoT to achieve marked improvements in precision on reasoning-intensive tasks. To accomplish this, we compile the LLaVA-CoT-100k dataset, integrating samples from various visual question answering sources and providing structured reasoning annotations. Besides, we propose an inference-time stage-level beam search method, which enables effective inference-time scaling. Remarkably, with only 100k training samples and a simple yet effective inference time scaling method, LLaVA-CoT not only outperforms its base model by 7.4% on a wide range of multimodal reasoning benchmarks, but also surpasses the performance of larger and even closed-source models, such as Gemini-1.5-pro, GPT-4o-mini, and Llama-3.2-90B-Vision-Instruct.
Despite thousands of researchers, engineers, and artists actively working on improving text-to-image generation models, systems often fail to produce images that accurately align with the text inputs. We introduce TIFA (Text-to-Image Faithfulness evaluation with question Answering), an automatic evaluation metric that measures the faithfulness of a generated image to its text input via visual question answering (VQA). Specifically, given a text input, we automatically generate several question-answer pairs using a language model. We calculate image faithfulness by checking whether existing VQA models can answer these questions using the generated image. TIFA is a reference-free metric that allows for fine-grained and interpretable evaluations of generated images. TIFA also has better correlations with human judgments than existing metrics. Based on this approach, we introduce TIFA v1.0, a benchmark consisting of 4K diverse text inputs and 25K questions across 12 categories (object, counting, etc.). We present a comprehensive evaluation of existing text-to-image models using TIFA v1.0 and highlight the limitations and challenges of current models. For instance, we find that current text-to-image models, despite doing well on color and material, still struggle in counting, spatial relations, and composing multiple objects. We hope our benchmark will help carefully measure the research progress in text-to-image synthesis and provide valuable insights for further research.
Knowledge-based visual question answering (VQA) is a vision-language task that requires an agent to correctly answer image-related questions using knowledge that is not presented in the given image. It is not only a more challenging task than regular VQA but also a vital step towards building a general VQA system. Most existing knowledge-based VQA systems process knowledge and image information similarly and ignore the fact that the knowledge base (KB) contains complete information about a triplet, while the extracted image information might be incomplete as the relations between two objects are missing or wrongly detected. In this paper, we propose a novel model named dynamic knowledge memory enhanced multi-step graph reasoning (DMMGR), which performs explicit and implicit reasoning over a key-value knowledge memory module and a spatial-aware image graph, respectively. Specifically, the memory module learns a dynamic knowledge representation and generates a knowledge-aware question representation at each reasoning step. Then, this representation is used to guide a graph attention operator over the spatial-aware image graph. Our model achieves new state-of-the-art accuracy on the KRVQR and FVQA datasets. We also conduct ablation experiments to prove the effectiveness of each component of the proposed model.
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.
Multimodal multihop question answering (MMQA) requires reasoning over images and text from multiple sources. Despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets. Existing methods focus on single-hop, single-modality, or short texts, limiting real-world applications like interpreting educational documents with long, multimodal content. To fill this gap, we introduce FM2DS, the first framework for creating a high-quality dataset for MMQA. Our approach consists of a 5-stage pipeline that involves acquiring relevant multimodal documents from Wikipedia, synthetically generating high-level questions and answers, and validating them through rigorous criteria to ensure data quality. We evaluate our methodology by training models on our synthesized dataset and testing on two benchmarks: MultimodalQA and WebQA. Our results demonstrate that, with an equal sample size, models trained on our synthesized data outperform those trained on human-collected data by 1.9 in exact match (EM) score on average. Additionally, we introduce M2QA-Bench with 1k samples, the first benchmark for MMQA on long documents, generated using FM2DS and refined by human annotators. We believe our data synthesis method will serve as a strong foundation for training and evaluating MMQA models.
Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of Vision Large Language Models (VLLMs). However, existing visual instruction tuning datasets include the following limitations: (1) Instruction annotation quality: despite existing VLLMs exhibiting strong performance, instructions generated by those advanced VLLMs may still suffer from inaccuracies, such as hallucinations. (2) Instructions and image diversity: the limited range of instruction types and the lack of diversity in image data may impact the model's ability to generate diversified and closer to real-world scenarios outputs. To address these challenges, we construct a high-quality, diverse visual instruction tuning dataset MMInstruct, which consists of 973K instructions from 24 domains. There are four instruction types: Judgement, Multiple-Choice, Long Visual Question Answering and Short Visual Question Answering. To construct MMInstruct, we propose an instruction generation data engine that leverages GPT-4V, GPT-3.5, and manual correction. Our instruction generation engine enables semi-automatic, low-cost, and multi-domain instruction generation at 1/6 the cost of manual construction. Through extensive experiment validation and ablation experiments, we demonstrate that MMInstruct could significantly improve the performance of VLLMs, e.g., the model fine-tuning on MMInstruct achieves new state-of-the-art performance on 10 out of 12 benchmarks. The code and data shall be available at https://github.com/yuecao0119/MMInstruct.
We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g., interleaved image, text and video) through a one-model-for-all autoregressive training process. First, visual signals are encoded into embeddings, and together with text tokens form an interleaved input sequence. Emu is then end-to-end trained with a unified objective of classifying the next text token or regressing the next visual embedding in the multimodal sequence. This versatile multimodality empowers the exploration of diverse pretraining data sources at scale, such as videos with interleaved frames and text, webpages with interleaved images and text, as well as web-scale image-text pairs and video-text pairs. Emu can serve as a generalist multimodal interface for both image-to-text and text-to-image tasks, and supports in-context image and text generation. Across a broad range of zero-shot/few-shot tasks including image captioning, visual question answering, video question answering and text-to-image generation, Emu demonstrates superb performance compared to state-of-the-art large multimodal models. Extended capabilities such as multimodal assistants via instruction tuning are also demonstrated with impressive performance.
Most counting questions in visual question answering (VQA) datasets are simple and require no more than object detection. Here, we study algorithms for complex counting questions that involve relationships between objects, attribute identification, reasoning, and more. To do this, we created TallyQA, the world's largest dataset for open-ended counting. We propose a new algorithm for counting that uses relation networks with region proposals. Our method lets relation networks be efficiently used with high-resolution imagery. It yields state-of-the-art results compared to baseline and recent systems on both TallyQA and the HowMany-QA benchmark.
Existing approaches to video understanding, mainly designed for short videos from a third-person perspective, are limited in their applicability in certain fields, such as robotics. In this paper, we delve into open-ended question-answering (QA) in long, egocentric videos, which allows individuals or robots to inquire about their own past visual experiences. This task presents unique challenges, including the complexity of temporally grounding queries within extensive video content, the high resource demands for precise data annotation, and the inherent difficulty of evaluating open-ended answers due to their ambiguous nature. Our proposed approach tackles these challenges by (i) integrating query grounding and answering within a unified model to reduce error propagation; (ii) employing large language models for efficient and scalable data synthesis; and (iii) introducing a close-ended QA task for evaluation, to manage answer ambiguity. Extensive experiments demonstrate the effectiveness of our method, which also achieves state-of-the-art performance on the QaEgo4D and Ego4D-NLQ benchmarks. Code, data, and models are available at https://github.com/Becomebright/GroundVQA.
In this work, we present SciGraphQA, a synthetic multi-turn question-answer dataset related to academic graphs. SciGraphQA is 13 times larger than ChartVQA, the previously largest chart-visual question-answering dataset. It is also the largest open-sourced chart VQA dataset with non-synthetic charts. To build our dataset, we selected 290,000 Computer Science or Machine Learning ArXiv papers published between 2010 and 2020, and then used Palm-2 to generate 295K samples of open-vocabulary multi-turn question-answering dialogues about the graphs. As context, we provided the text-only Palm-2 with paper title, abstract, paragraph mentioning the graph, and rich text contextual data from the graph itself, obtaining dialogues with an average 2.23 question-answer turns for each graph. We asked GPT-4 to assess the matching quality of our question-answer turns given the paper's context, obtaining an average rating of 8.7/10 on our 3K test set. We evaluated the 0-shot capability of the most popular MLLM models such as LLaVa, mPLUGowl, BLIP-2, and openFlamingo's on our dataset, finding LLaVA-13B being the most performant with a CIDEr score of 0.08. We further enriched the question prompts for LLAVA by including the serialized data tables extracted from the graphs using the DePlot model, boosting LLaVA's 0-shot CIDEr to 0.15. To verify the validity of our dataset, we also fine-tuned LLaVa using our dataset, reaching a substantially higher CIDEr score of 0.26. We anticipate further accuracy improvement by including segmentation mask tokens and leveraging larger LLM backbones coupled with emergent prompting techniques. Our code and data are open-sourced.
Continual Learning in Visual Question Answering (VQACL) requires models to learn new visual-linguistic tasks (plasticity) while retaining knowledge from previous tasks (stability). The multimodal nature of VQACL presents unique challenges, requiring models to balance stability across visual and textual domains while maintaining plasticity to adapt to novel objects and reasoning tasks. Existing methods, predominantly designed for unimodal tasks, often struggle to balance these demands effectively. In this work, we introduce QUestion-only replay with Attention Distillation (QUAD), a novel approach for VQACL that leverages only past task questions for regularisation, eliminating the need to store visual data and addressing both memory and privacy concerns. QUAD achieves stability by introducing a question-only replay mechanism that selectively uses questions from previous tasks to prevent overfitting to the current task's answer space, thereby mitigating the out-of-answer-set problem. Complementing this, we propose attention consistency distillation, which uniquely enforces both intra-modal and inter-modal attention consistency across tasks, preserving essential visual-linguistic associations. Extensive experiments on VQAv2 and NExT-QA demonstrate that QUAD significantly outperforms state-of-the-art methods, achieving robust performance in continual VQA.
Visual Question Answering (VQA) research seeks to create AI systems to answer natural language questions in images, yet VQA methods often yield overly simplistic and short answers. This paper aims to advance the field by introducing Visual Question Explanation (VQE), which enhances the ability of VQA to provide detailed explanations rather than brief responses and address the need for more complex interaction with visual content. We first created an MLVQE dataset from a 14-week streamed video machine learning course, including 885 slide images, 110,407 words of transcripts, and 9,416 designed question-answer (QA) pairs. Next, we proposed a novel SparrowVQE, a small 3 billion parameters multimodal model. We trained our model with a three-stage training mechanism consisting of multimodal pre-training (slide images and transcripts feature alignment), instruction tuning (tuning the pre-trained model with transcripts and QA pairs), and domain fine-tuning (fine-tuning slide image and QA pairs). Eventually, our SparrowVQE can understand and connect visual information using the SigLIP model with transcripts using the Phi-2 language model with an MLP adapter. Experimental results demonstrate that our SparrowVQE achieves better performance in our developed MLVQE dataset and outperforms state-of-the-art methods in the other five benchmark VQA datasets. The source code is available at \url{https://github.com/YoushanZhang/SparrowVQE}.
Currently nearing human-level performance, Visual Question Answering (VQA) is an emerging area in artificial intelligence. Established as a multi-disciplinary field in machine learning, both computer vision and natural language processing communities are working together to achieve state-of-the-art (SOTA) performance. However, there is a gap between the SOTA results and real world applications. This is due to the lack of model generalisation. The RAMEN model \cite{Shrestha2019} aimed to achieve domain generalization by obtaining the highest score across two main types of VQA datasets. This study provides two major improvements to the early/late fusion module and aggregation module of the RAMEN architecture, with the objective of further strengthening domain generalization. Vector operations based fusion strategies are introduced for the fusion module and the transformer architecture is introduced for the aggregation module. Improvements of up to five VQA datasets from the experiments conducted are evident. Following the results, this study analyses the effects of both the improvements on the domain generalization problem. The code is available on GitHub though the following link \url{https://github.com/bhanukaManesha/ramen}.
To address computational and memory limitations of Large Multimodal Models in the Video Question-Answering task, several recent methods extract textual representations per frame (e.g., by captioning) and feed them to a Large Language Model (LLM) that processes them to produce the final response. However, in this way, the LLM does not have access to visual information and often has to process repetitive textual descriptions of nearby frames. To address those shortcomings, in this paper, we introduce VidCtx, a novel training-free VideoQA framework which integrates both modalities, i.e. both visual information from input frames and textual descriptions of others frames that give the appropriate context. More specifically, in the proposed framework a pre-trained Large Multimodal Model (LMM) is prompted to extract at regular intervals, question-aware textual descriptions (captions) of video frames. Those will be used as context when the same LMM will be prompted to answer the question at hand given as input a) a certain frame, b) the question and c) the context/caption of an appropriate frame. To avoid redundant information, we chose as context the descriptions of distant frames. Finally, a simple yet effective max pooling mechanism is used to aggregate the frame-level decisions. This methodology enables the model to focus on the relevant segments of the video and scale to a high number of frames. Experiments show that VidCtx achieves competitive performance among approaches that rely on open models on three public Video QA benchmarks, NExT-QA, IntentQA and STAR. Our code is available at https://github.com/IDT-ITI/VidCtx.
The MEDIQA-M3G 2024 challenge necessitates novel solutions for Multilingual & Multimodal Medical Answer Generation in dermatology (wai Yim et al., 2024a). This paper addresses the limitations of traditional methods by proposing a weakly supervised learning approach for open-ended medical question-answering (QA). Our system leverages readily available MEDIQA-M3G images via a VGG16-CNN-SVM model, enabling multilingual (English, Chinese, Spanish) learning of informative skin condition representations. Using pre-trained QA models, we further bridge the gap between visual and textual information through multimodal fusion. This approach tackles complex, open-ended questions even without predefined answer choices. We empower the generation of comprehensive answers by feeding the ViT-CLIP model with multiple responses alongside images. This work advances medical QA research, paving the way for clinical decision support systems and ultimately improving healthcare delivery.
Charts are very popular for analyzing data. When exploring charts, people often ask a variety of complex reasoning questions that involve several logical and arithmetic operations. They also commonly refer to visual features of a chart in their questions. However, most existing datasets do not focus on such complex reasoning questions as their questions are template-based and answers come from a fixed-vocabulary. In this work, we present a large-scale benchmark covering 9.6K human-written questions as well as 23.1K questions generated from human-written chart summaries. To address the unique challenges in our benchmark involving visual and logical reasoning over charts, we present two transformer-based models that combine visual features and the data table of the chart in a unified way to answer questions. While our models achieve the state-of-the-art results on the previous datasets as well as on our benchmark, the evaluation also reveals several challenges in answering complex reasoning questions.
Visual question answering (VQA) is a task where an image is given, and a series of questions are asked about the image. To build an efficient VQA algorithm, a large amount of QA data is required which is very expensive. Generating synthetic QA pairs based on templates is a practical way to obtain data. However, VQA models trained on those data do not perform well on complex, human-written questions. To address this issue, we propose a new method called {\it chain of QA for human-written questions} (CoQAH). CoQAH utilizes a sequence of QA interactions between a large language model and a VQA model trained on synthetic data to reason and derive logical answers for human-written questions. We tested the effectiveness of CoQAH on two types of human-written VQA datasets for 3D-rendered and chest X-ray images and found that it achieved state-of-the-art accuracy in both types of data. Notably, CoQAH outperformed general vision-language models, VQA models, and medical foundation models with no finetuning.
What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to revisit text-based representations, such as general-purpose video captions, which are interpretable and can be directly consumed by large language models (LLMs). Intuitively, different video understanding tasks may require representations that are complementary and at different granularity. To this end, we propose versatile action models (Vamos), a learning framework powered by a large language model as the ``reasoner'', and can flexibly leverage visual embedding and free-form text descriptions as its input. To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the free-form text as inputs to the LLM reasoner. We evaluate Vamos on five complementary benchmarks, Ego4D, NeXT-QA, IntentQA, Spacewalk-18, and EgoSchema, on its capability to model temporal dynamics, encode visual history, and perform reasoning. Surprisingly, we observe that text-based representations consistently achieve competitive performance on all benchmarks, and that visual embeddings provide marginal or no performance improvement, demonstrating the effectiveness of text-based video representation in the LLM era. We also demonstrate that our token bottleneck model is able to select relevant evidence from free-form text, support test-time intervention, and achieves nearly 5 times inference speedup while keeping a competitive question answering performance. Code and models are publicly released at https://brown-palm.github.io/Vamos/
Medical Visual Question Answering (Med-VQA) represents a critical and challenging subtask within the general VQA domain. Despite significant advancements in general Visual Question Answering (VQA), multimodal large language models (MLLMs) still exhibit substantial limitations when handling multi-task VQA scenarios. These limitations manifest through erroneous spatial localization and misinterpretation of medical images, which primarily arise from two fundamental issues: inadequate image-text alignment and insufficient medical knowledge in general-purpose MLLMs for specialized medical applications. To address these issues, we introduce the Cross-Modal Clinical Knowledge Distiller (ClinKD), an innovative framework designed to enhance image-text alignment and establish more effective medical knowledge adaptation mechanisms, which enables MLLMs to adapt to medical knowledge. Our extensive experimental evaluations demonstrate that the ClinKD achieves state-of-the-art performance on the Med-GRIT-270k dataset, a challenging medical benchmark containing fine-grained multi-task QA pairs. The results indicate that our approach not only significantly improves image-text alignment but also effectively enables MLLMs to adapt to the medical knowledge. The source code for ClinKD is available at: https://github.com/overloadedHenry/ClinKD.
In recent years, synthetic visual instructions by generative language model have demonstrated plausible text generation performance on the visual question-answering tasks. However, challenges persist in the hallucination of generative language models, i.e., the generated image-text data contains unintended contents. This paper presents a novel and scalable method for generating visually dehallucinative instructions, dubbed CAP2QA, that constrains the scope to only image contents. Our key contributions lie in introducing image-aligned instructive QA dataset CAP2QA-COCO and its scalable recipe. In our experiments, we compare synthetic visual instruction datasets that share the same source data by visual instruction tuning and conduct general visual recognition tasks. It shows that our proposed method significantly reduces visual hallucination while consistently improving visual recognition ability and expressiveness.