PyTorchKR Papers

“Visual Question Answering”

총 2,807편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1703.08084

Multimodal Compact Bilinear Pooling for Multimodal Neural Machine Translation

In state-of-the-art Neural Machine Translation, an attention mechanism is used during decoding to enhance the translation. At every step, the decoder uses this mechanism to focus on different parts of the source sentence to gather the most useful information before outputting its target word. Recently, the effectiveness of the attention mechanism has also been explored for multimodal tasks, where it becomes possible to focus both on sentence parts and image regions. Approaches to pool two modalities usually include element-wise product, sum or concatenation. In this paper, we evaluate the more advanced Multimodal Compact Bilinear pooling method, which takes the outer product of two vectors to combine the attention features for the two modalities. This has been previously investigated for visual question answering. We try out this approach for multimodal image caption translation and show improvements compared to basic combination methods.

arXiv:2006.07214공식 코드 · Papers with Code

Sparse and Continuous Attention Mechanisms

Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation). Distributions in each of these families have fixed support. In contrast, for finite domains, there has been recent work on sparse alternatives to softmax (e.g. sparsemax and alpha-entmax), which have varying support, being able to assign zero probability to irrelevant categories. This paper expands that work in two directions: first, we extend alpha-entmax to continuous domains, revealing a link with Tsallis statistics and deformed exponential families. Second, we introduce continuous-domain attention mechanisms, deriving efficient gradient backpropagation algorithms for alpha in {1,2}. Experiments on attention-based text classification, machine translation, and visual question answering illustrate the use of continuous attention in 1D and 2D, showing that it allows attending to time intervals and compact regions.

arXiv:2211.04861

ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation

Recent cross-lingual cross-modal works attempt to extend Vision-Language Pre-training (VLP) models to non-English inputs and achieve impressive performance. However, these models focus only on understanding tasks utilizing encoder-only architecture. In this paper, we propose ERNIE-UniX2, a unified cross-lingual cross-modal pre-training framework for both generation and understanding tasks. ERNIE-UniX2 integrates multiple pre-training paradigms (e.g., contrastive learning and language modeling) based on encoder-decoder architecture and attempts to learn a better joint representation across languages and modalities. Furthermore, ERNIE-UniX2 can be seamlessly fine-tuned for varieties of generation and understanding downstream tasks. Pre-trained on both multilingual text-only and image-text datasets, ERNIE-UniX2 achieves SOTA results on various cross-lingual cross-modal generation and understanding tasks such as multimodal machine translation and multilingual visual question answering.

arXiv:2402.00453공식 코드 · Papers with Code

Instruction Makes a Difference

We introduce Instruction Document Visual Question Answering (iDocVQA) dataset and Large Language Document (LLaDoc) model, for training Language-Vision (LV) models for document analysis and predictions on document images, respectively. Usually, deep neural networks for the DocVQA task are trained on datasets lacking instructions. We show that using instruction-following datasets improves performance. We compare performance across document-related datasets using the recent state-of-the-art (SotA) Large Language and Vision Assistant (LLaVA)1.5 as the base model. We also evaluate the performance of the derived models for object hallucination using the Polling-based Object Probing Evaluation (POPE) dataset. The results show that instruction-tuning performance ranges from 11X to 32X of zero-shot performance and from 0.1% to 4.2% over non-instruction (traditional task) finetuning. Despite the gains, these still fall short of human performance (94.36%), implying there's much room for improvement.

arXiv:2411.05755공식 코드 · Papers with Code

End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering

We present VLMnav, an embodied framework to transform a Vision-Language Model (VLM) into an end-to-end navigation policy. In contrast to prior work, we do not rely on a separation between perception, planning, and control; instead, we use a VLM to directly select actions in one step. Surprisingly, we find that a VLM can be used as an end-to-end policy zero-shot, i.e., without any fine-tuning or exposure to navigation data. This makes our approach open-ended and generalizable to any downstream navigation task. We run an extensive study to evaluate the performance of our approach in comparison to baseline prompting methods. In addition, we perform a design analysis to understand the most impactful design decisions. Visual examples and code for our project can be found at https://jirl-upenn.github.io/VLMnav/

arXiv:2503.10042공식 코드 · Papers with Code

How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game

The rapid advancing of Multimodal Large Language Models (MLLMs) has spurred interest in complex multimodal reasoning tasks in the real-world and virtual environment, which require coordinating multiple abilities, including visual perception, visual reasoning, spatial awareness, and target deduction. However, existing evaluations primarily assess the final task completion, often degrading assessments to isolated abilities such as visual grounding and visual question answering. Less attention is given to comprehensively and quantitatively analyzing reasoning process in multimodal environments, which is crucial for understanding model behaviors and underlying reasoning mechanisms beyond merely task success. To address this, we introduce MM-Escape, an extensible benchmark for investigating multimodal reasoning, inspired by real-world escape games. MM-Escape emphasizes intermediate model behaviors alongside final task completion. To achieve this, we develop EscapeCraft, a customizable and open environment that enables models to engage in free-form exploration for assessing multimodal reasoning. Extensive experiments show that MLLMs, regardless of scale, can successfully complete the simplest room escape tasks, with some exhibiting human-like exploration strategies. Yet, performance dramatically drops as task difficulty increases. Moreover, we observe that performance bottlenecks vary across models, revealing distinct failure modes and limitations in their multimodal reasoning abilities, such as repetitive trajectories without adaptive exploration, getting stuck in corners due to poor visual spatial awareness, and ineffective use of acquired props, such as the key. We hope our work sheds light on new challenges in multimodal reasoning, and uncovers potential improvements in MLLMs capabilities.

arXiv:2610.37341v1cs.CV

CodeCap-Bench: Can Code Serve as a Good Video Caption?

Video captioning aims to preserve visual information through compact descriptions, predominantly using natural language. However, precisely expressing fine-grained spatial structures and temporal dynamics in natural language often leads to lengthy and potentially ambiguous descriptions. In this work, we explore Code as Video Caption, a paradigm where executable programs serve as a complementary representation of visual content through graphical primitives, layout rules, and functions of time. To examine whether code captions effectively preserve video information, we compare them with natural language captions on downstream question answering and video reconstruction tasks. Our results show that code captions achieve superior reasoning accuracy and reconstruction fidelity. Despite these advantages, realizing the potential of code captioning depends on whether current multimodal large language models (MLLMs) can generate faithful code captions. To systematically assess this capability, we introduce CodeCap-Bench, which comprises 323 videos spanning five categories of structured 2D content, along with fine-grained annotations and a multi-level evaluation framework. Extensive experiments reveal that while leading proprietary MLLMs demonstrate promising code captioning capabilities, they still struggle to faithfully capture complex temporal dynamics, with open-source models lagging substantially behind.

arXiv:2412.10302공식 코드 · Papers with Code

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL, through two key major upgrades. For the vision component, we incorporate a dynamic tiling vision encoding strategy designed for processing high-resolution images with different aspect ratios. For the language component, we leverage DeepSeekMoE models with the Multi-head Latent Attention mechanism, which compresses Key-Value cache into latent vectors, to enable efficient inference and high throughput. Trained on an improved vision-language dataset, DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is composed of three variants: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively. DeepSeek-VL2 achieves competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing open-source dense and MoE-based models. Codes and pre-trained models are publicly accessible at https://github.com/deepseek-ai/DeepSeek-VL2.

arXiv:2503.12545

PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models

In recent years, Multimodal Large Language Models (MLLMs) have demonstrated remarkable advancements in tasks such as visual question answering, visual understanding, and reasoning. However, this impressive progress relies on vast amounts of data collected from the internet, raising significant concerns about privacy and security. To address these issues, machine unlearning (MU) has emerged as a promising solution, enabling the removal of specific knowledge from an already trained model without requiring retraining from scratch. Although MU for MLLMs has gained attention, current evaluations of its efficacy remain incomplete, and the underlying problem is often poorly defined, which hinders the development of strategies for creating more secure and trustworthy systems. To bridge this gap, we introduce a benchmark, named PEBench, which includes a dataset of personal entities and corresponding general event scenes, designed to comprehensively assess the performance of MU for MLLMs. Through PEBench, we aim to provide a standardized and robust framework to advance research in secure and privacy-preserving multimodal models. We benchmarked 6 MU methods, revealing their strengths and limitations, and shedding light on key challenges and opportunities for MU in MLLMs.

arXiv:2104.02096

Compressing Visual-linguistic Model via Knowledge Distillation

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a small VL model. The major challenge arises from the inconsistent regional visual tokens extracted from different detectors of Teacher and Student, resulting in the misalignment of hidden representations and attention distributions. To address the problem, we retrain and adapt the Teacher by using the same region proposals from Student's detector while the features are from Teacher's own object detector. With aligned network inputs, the adapted Teacher is capable of transferring the knowledge through the intermediate representations. Specifically, we use the mean square error loss to mimic the attention distribution inside the transformer block and present a token-wise noise contrastive loss to align the hidden state by contrasting with negative representations stored in a sample queue. To this end, we show that our proposed distillation significantly improves the performance of small VL models on image captioning and visual question answering tasks. It reaches 120.8 in CIDEr score on COCO captioning, an improvement of 5.1 over its non-distilled counterpart; and an accuracy of 69.8 on VQA 2.0, a 0.8 gain from the baseline. Our extensive experiments and ablations confirm the effectiveness of VL distillation in both pre-training and fine-tuning stages.

arXiv:2409.01560

Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models

Categorization, a core cognitive ability in humans that organizes objects based on common features, is essential to cognitive science as well as computer vision. To evaluate the categorization ability of visual AI models, various proxy tasks on recognition from datasets to open world scenarios have been proposed. Recent development of Large Multimodal Models (LMMs) has demonstrated impressive results in high-level visual tasks, such as visual question answering, video temporal reasoning, etc., utilizing the advanced architectures and large-scale multimodal instruction tuning. Previous researchers have developed holistic benchmarks to measure the high-level visual capability of LMMs, but there is still a lack of pure and in-depth quantitative evaluation of the most fundamental categorization ability. According to the research on human cognitive process, categorization can be seen as including two parts: category learning and category use. Inspired by this, we propose a novel, challenging, and efficient benchmark based on composite blocks, called ComBo, which provides a disentangled evaluation framework and covers the entire categorization process from learning to use. By analyzing the results of multiple evaluation tasks, we find that although LMMs exhibit acceptable generalization ability in learning new categories, there are still gaps compared to humans in many ways, such as fine-grained perception of spatial relationship and abstract category understanding. Through the study of categorization, we can provide inspiration for the further development of LMMs in terms of interpretability and generalization.

arXiv:2610.38389v1cs.CV

의료 비전-언어 모델의 시각적 무관 환각

Visually Irrelevant Hallucinations in Medical Vision-Language Models

의료 비전-언어 모델(VLM)은 의료 영상으로부터 자유 형식의 임상 서술과 답변을 생성하는 영상의학 보고서 생성(RRG)과 의료 시각 질의응답(Med-VQA)에서 강한 성능을 보인다. 그러나 이러한 모델은 시각적 근거가 없거나 영상 내용과 모순되는, 임상적으로 의미 있는 진술을 생성할 수 있다. 우리는 이러한 오류를 시각적 무관 환각이라 부르고 구절 수준에서 이를 조사한다. 우리는 구절 수준 환각 위험 추정을 위한 모델 비의존적 사후 프레임워크인 CLEAR(Counterfactual Localized Evaluation of Alignment and Response)를 제안한다. CLEAR는 생성된 응답을 시각적으로 평가 가능한 임상 구절로 분해한다. 각 구절에 대해 구절 조건부 그라운딩이 후보 시각 영역을 식별하고, 이 영역은 국소적 반사실 개입으로 선택적으로 교란된다. CLEAR는 상호 보완적인 두 가지 감사 단서, 즉 생성 응답에서의 의미적·임상적으로 유의미한 변화를 포착하는 응답 단서와 영상-구절 적합성의 변화를 측정하는 정렬 단서로 개입을 특성화한다. 이러한 단서는 정규화되어 함께 모델링되며 구절 수준 환각 위험을 추정한다. RRG와 Med-VQA에 걸친 네 개 데이터셋에서 CLEAR는 여러 의료 및 범용 VLM에 대해 최신 환각 탐지 기준선을 능가한다. MIMIC-CXR에서 CLEAR는 AUPRC를 85.10%에서 90.23%로 향상시킨다. 그 효과는 GT에서 도출한 통제된 VIH 벤치마크에서도 추가로 검증된다. 이러한 결과는 시각적 무관 환각이 의료 VLM의 중요한 세밀한 신뢰성 실패 양상임을 보여 주며, 더 신뢰할 수 있는 멀티모달 임상 생성을 위한 모델 비의존적 시각 근거 감사의 가치를 입증한다.

arXiv:2304.01611

Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder

Medical Visual Question Answering (VQA) systems play a supporting role to understand clinic-relevant information carried by medical images. The questions to a medical image include two categories: close-end (such as Yes/No question) and open-end. To obtain answers, the majority of the existing medical VQA methods relies on classification approaches, while a few works attempt to use generation approaches or a mixture of the two. The classification approaches are relatively simple but perform poorly on long open-end questions. To bridge this gap, in this paper, we propose a new Transformer based framework for medical VQA (named as Q2ATransformer), which integrates the advantages of both the classification and the generation approaches and provides a unified treatment for the close-end and open-end questions. Specifically, we introduce an additional Transformer decoder with a set of learnable candidate answer embeddings to query the existence of each answer class to a given image-question pair. Through the Transformer attention, the candidate answer embeddings interact with the fused features of the image-question pair to make the decision. In this way, despite being a classification-based approach, our method provides a mechanism to interact with the answer information for prediction like the generation-based approaches. On the other hand, by classification, we mitigate the task difficulty by reducing the search space of answers. Our method achieves new state-of-the-art performance on two medical VQA benchmarks. Especially, for the open-end questions, we achieve 79.19% on VQA-RAD and 54.85% on PathVQA, with 16.09% and 41.45% absolute improvements, respectively.

arXiv:1908.00061

An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation

Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set impairs generalization in certain tasks. Recently, alternative methods for normalizing feature activations in neural networks have been proposed. Among them, group normalization has been shown to yield similar, in some domains even superior performance to batch normalization. All these methods utilize a learned affine transformation after the normalization operation to increase representational power. Methods used in conditional computation define the parameters of these transformations as learnable functions of conditioning information. In this work, we study whether and where the conditional formulation of group normalization can improve generalization compared to conditional batch normalization. We evaluate performances on the tasks of visual question answering, few-shot learning, and conditional image generation.

arXiv:2312.10300공식 코드 · Papers with Code

Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark Shot2Story20K with detailed shot-level captions and comprehensive video summaries. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video and narration captioning, multi-shot video summarization, and video retrieval with shot descriptions. Preliminary experiments show some challenges to generate a long and comprehensive video summary. Nevertheless, the generated imperfect summaries can already significantly boost the performance of existing video understanding tasks such as video question-answering, promoting an under-explored setting of video understanding with detailed summaries.

arXiv:2404.14567

WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models

This paper outlines our submission to the MEDIQA2024 Multilingual and Multimodal Medical Answer Generation (M3G) shared task. We report results for two standalone solutions under the English category of the task, the first involving two consecutive API calls to the Claude 3 Opus API and the second involving training an image-disease label joint embedding in the style of CLIP for image classification. These two solutions scored 1st and 2nd place respectively on the competition leaderboard, substantially outperforming the next best solution. Additionally, we discuss insights gained from post-competition experiments. While the performance of these two solutions have significant room for improvement due to the difficulty of the shared task and the challenging nature of medical visual question answering in general, we identify the multi-stage LLM approach and the CLIP image classification approach as promising avenues for further investigation.

arXiv:2411.05961

Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models

Vision Language Models (VLMs) are central to Visual Question Answering (VQA) systems and are typically deployed in the cloud due to their high computational demands. However, this cloud-only approach underutilizes edge computational resources and requires significant bandwidth for transmitting raw images. In this paper, we introduce an edge-cloud collaborative VQA system, called LLaVA-AlignedVQ, which features a novel Aligned Vector Quantization algorithm (AlignedVQ) that efficiently compress intermediate features without compromising accuracy to support partitioned execution. Our experiments demonstrate that LLaVA-AlignedVQ achieves approximately 1365x compression rate of intermediate features, reducing data transmission overhead by 96.8% compared to transmitting JPEG90-compressed images to the cloud. LLaVA-AlignedVQ achieves an inference speedup of 2-15x while maintaining high accuracy, remaining within -2.23% to +1.6% of the original model's accuracy performance across eight VQA datasets, compared to the cloud-only solution.

arXiv:2505.13973

Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models

Recently, reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs), particularly following the introduction of Group Relative Policy Optimization (GRPO). However, directly applying it to medical tasks remains challenging for achieving clinically grounded model behavior. Motivated by the need to align model response with clinical expectations, we investigate four critical dimensions that affect the effectiveness of RL-based tuning in medical visual question answering (VQA): base model initialization strategy, the role of medical semantic alignment, the impact of length-based rewards on long-chain reasoning, and the influence of bias. We conduct extensive experiments to analyze these factors for medical MLLMs, providing new insights into how models are domain-specifically fine-tuned. Additionally, our results also demonstrate that GRPO-based RL tuning consistently outperforms standard supervised fine-tuning (SFT) in both accuracy and reasoning quality.

arXiv:2608.30475v1cs.CL

ImageEval 2026: 문화적으로 그라운딩된 아랍어 멀티모달 평가

ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation

문화적으로 그라운딩된 아랍어 멀티모달 평가를 다루는 ImageEval 2026 공유 과제(shared task)의 개요를 소개한다. 이 과제는 두 가지 태스크로 구성된다. (i) AynVQA는 영어와 현대 표준 아랍어(MSA)를 대상으로 음성 시각 질의응답(spoken visual question answering)과 이미지 그라운딩 환각 탐지(image-grounded hallucination detection)를 다루며, (ii) CRAI-Bench는 텍스트-이미지 생성(text-to-image generation)의 문화적 정확성을 평가한다. 테스트 단계에는 총 14개 팀이 참가했으며, 이 중 12개 팀이 시스템 설명 논문을 제출했다. 참가 시스템은 제로샷 프롬프팅, 비전-언어 모델의 미세조정, 음성 인식 파이프라인, 앙상블, 점수 보정(score calibration) 등 다양한 접근법을 사용했다. 본 논문에서는 과제 설정, 데이터셋, 평가 절차, 참가 시스템을 설명하고 각 트랙별 주요 결과를 요약한다. 공유 과제의 모든 데이터셋과 평가 스크립트는 연구 커뮤니티에 공개된다. 이 공유 과제는 특히 아랍어 음성과 이미지-텍스트 추론에서 문화적으로 그라운딩된 멀티모달 평가가 지닌 어려움을 부각한다.

arXiv:2209.15162공식 코드 · Papers with Code

Linearly Mapping from Image to Text Space

The extent to which text-only language models (LMs) learn to represent features of the non-linguistic world is an open question. Prior work has shown that pretrained LMs can be taught to caption images when a vision model's parameters are optimized to encode images in the language space. We test a stronger hypothesis: that the conceptual representations learned by frozen text-only models and vision-only models are similar enough that this can be achieved with a linear map. We show that the image representations from vision models can be transferred as continuous prompts to frozen LMs by training only a single linear projection. Using these to prompt the LM achieves competitive performance on captioning and visual question answering tasks compared to models that tune both the image encoder and text decoder (such as the MAGMA model). We compare three image encoders with increasing amounts of linguistic supervision seen during pretraining: BEIT (no linguistic information), NF-ResNET (lexical category information), and CLIP (full natural language descriptions). We find that all three encoders perform equally well at transferring visual property information to the language model (e.g., whether an animal is large or small), but that image encoders pretrained with linguistic supervision more saliently encode category information (e.g., distinguishing hippo vs. elephant) and thus perform significantly better on benchmark language-and-vision tasks. Our results indicate that LMs encode conceptual information structurally similarly to vision-based models, even those that are solely trained on images. Code is available here: https://github.com/jmerullo/limber