PyTorchKR Papers

최신 논문

총 2,558편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2406.07450공식 코드 · Papers with Code

Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning

We perform a comprehensive benchmarking of contrastive frameworks for learning multimodal representations in the medical domain. Through this study, we aim to answer the following research questions: (i) How transferable are general-domain representations to the medical domain? (ii) Is multimodal contrastive training sufficient, or does it benefit from unimodal training as well? (iii) What is the impact of feature granularity on the effectiveness of multimodal medical representation learning? To answer these questions, we investigate eight contrastive learning approaches under identical training setups, and train them on 2.8 million image-text pairs from four datasets, and evaluate them on 25 downstream tasks, including classification (zero-shot and linear probing), image-to-text and text-to-image retrieval, and visual question-answering. Our findings suggest a positive answer to the first question, a negative answer to the second question, and the benefit of learning fine-grained features. Finally, we make our code publicly available.

arXiv:2406.06462공식 코드 · Papers with Code

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.

arXiv:2406.05967

CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 30 countries on four continents, covering 31 languages with 13 scripts, providing a total of 10k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field.

arXiv:2406.05963

Solution for SMART-101 Challenge of CVPR Multi-modal Algorithmic Reasoning Task 2024

In this paper, the solution of HYU MLLAB KT Team to the Multimodal Algorithmic Reasoning Task: SMART-101 CVPR 2024 Challenge is presented. Beyond conventional visual question-answering problems, the SMART-101 challenge aims to achieve human-level multimodal understanding by tackling complex visio-linguistic puzzles designed for children in the 6-8 age group. To solve this problem, we suggest two main ideas. First, to utilize the reasoning ability of a large-scale language model (LLM), the given visual cues (images) are grounded in the text modality. For this purpose, we generate highly detailed text captions that describe the context of the image and use these captions as input for the LLM. Second, due to the nature of puzzle images, which often contain various geometric visual patterns, we utilize an object detection algorithm to ensure these patterns are not overlooked in the captioning process. We employed the SAM algorithm, which can detect various-size objects, to capture the visual features of these geometric patterns and used this information as input for the LLM. Under the puzzle split configuration, we achieved an option selection accuracy Oacc of 29.5 on the test set and a weighted option selection accuracy (WOSA) of 27.1 on the challenge set.

arXiv:2406.05127

Towards Semantic Equivalence of Tokenization in Multimodal LLM

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into feature representations that are most beneficial for LLMs. However, existing vision tokenizers, essential for semantic alignment between vision and language, remain problematic. Existing methods aggressively fragment visual input, corrupting the visual semantic integrity. To address this, this paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok), which groups visual features into semantic units via a dynamic clustering algorithm, flexibly determining the number of tokens based on image complexity. The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features. The proposed MLLM (Setokim) equipped with SeTok significantly demonstrates superior performance across various tasks, as evidenced by our experimental results. The project page is at https://chocowu.github.io/SeTok-web/.

arXiv:2406.04339

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation

A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face challenges in two areas: (1) insufficient reasoning ability to tackle complex tasks, and (2) high computational costs for VLA model fine-tuning and inference. The recently proposed state space model (SSM) known as Mamba demonstrates promising capabilities in non-trivial sequence modeling with linear inference complexity. Inspired by this, we introduce RoboMamba, an end-to-end robotic VLA model that leverages Mamba to deliver both robotic reasoning and action capabilities, while maintaining efficient fine-tuning and inference. Specifically, we first integrate the vision encoder with Mamba, aligning visual tokens with language embedding through co-training, empowering our model with visual common sense and robotic-related reasoning. To further equip RoboMamba with SE(3) pose prediction abilities, we explore an efficient fine-tuning strategy with a simple policy head. We find that once RoboMamba possesses sufficient reasoning capability, it can acquire manipulation skills with minimal fine-tuning parameters (0.1\% of the model) and time. In experiments, RoboMamba demonstrates outstanding reasoning capabilities on general and robotic evaluation benchmarks. Meanwhile, our model showcases impressive pose prediction results in both simulation and real-world experiments, achieving inference speeds 3 times faster than existing VLA models. Our project web page: https://sites.google.com/view/robomamba-web

arXiv:2406.04334

DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs

Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs, as it has to handle a large number of additional tokens in its input layer. This paper presents a new architecture DeepStack for LMMs. Considering $N$ layers in the language and vision transformer of LMMs, we stack the visual tokens into $N$ groups and feed each group to its aligned transformer layer \textit{from bottom to top}. Surprisingly, this simple method greatly enhances the power of LMMs to model interactions among visual tokens across layers but with minimal additional cost. We apply DeepStack to both language and vision transformer in LMMs, and validate the effectiveness of DeepStack LMMs with extensive empirical results. Using the same context length, our DeepStack 7B and 13B parameters surpass their counterparts by \textbf{2.7} and \textbf{2.9} on average across \textbf{9} benchmarks, respectively. Using only one-fifth of the context length, DeepStack rivals closely to the counterparts that use the full context length. These gains are particularly pronounced on high-resolution tasks, e.g., \textbf{4.2}, \textbf{11.0}, and \textbf{4.0} improvements on TextVQA, DocVQA, and InfoVQA compared to LLaVA-1.5-7B, respectively. We further apply DeepStack to vision transformer layers, which brings us a similar amount of improvements, \textbf{3.8} on average compared with LLaVA-1.5-7B.

arXiv:2406.04236

Understanding Information Storage and Transfer in Multi-modal Large Language Models

Understanding the mechanisms of information storage and transfer in Transformer-based models is important for driving model understanding progress. Recent work has studied these mechanisms for Large Language Models (LLMs), revealing insights on how information is stored in a model's parameters and how information flows to and from these parameters in response to specific prompts. However, these studies have not yet been extended to Multi-modal Large Language Models (MLLMs). Given their expanding capabilities and real-world use, we start by studying one aspect of these models -- how MLLMs process information in a factual visual question answering task. We use a constraint-based formulation which views a visual question as having a set of visual or textual constraints that the model's generated answer must satisfy to be correct (e.g. What movie directed by the director in this photo has won a Golden Globe?). Under this setting, we contribute i) a method that extends causal information tracing from pure language to the multi-modal setting, and ii) VQA-Constraints, a test-bed of 9.7K visual questions annotated with constraints. We use these tools to study two open-source MLLMs, LLaVa and multi-modal Phi-2. Our key findings show that these MLLMs rely on MLP and self-attention blocks in much earlier layers for information storage, compared to LLMs whose mid-layer MLPs are more important. We also show that a consistent small subset of visual tokens output by the vision encoder are responsible for transferring information from the image to these causal blocks. We validate these mechanisms by introducing MultEdit, a model-editing algorithm that can correct errors and insert new long-tailed information into MLLMs by targeting these causal blocks.

arXiv:2406.02774

Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following

Training gaze following models requires a large number of images with gaze target coordinates annotated by human annotators, which is a laborious and inherently ambiguous process. We propose the first semi-supervised method for gaze following by introducing two novel priors to the task. We obtain the first prior using a large pretrained Visual Question Answering (VQA) model, where we compute Grad-CAM heatmaps by `prompting' the VQA model with a gaze following question. These heatmaps can be noisy and not suited for use in training. The need to refine these noisy annotations leads us to incorporate a second prior. We utilize a diffusion model trained on limited human annotations and modify the reverse sampling process to refine the Grad-CAM heatmaps. By tuning the diffusion process we achieve a trade-off between the human annotation prior and the VQA heatmap prior, which retains the useful VQA prior information while exhibiting similar properties to the training data distribution. Our method outperforms simple pseudo-annotation generation baselines on the GazeFollow image dataset. More importantly, our pseudo-annotation strategy, applied to a widely used supervised gaze following model (VAT), reduces the annotation need by 50%. Our method also performs the best on the VideoAttentionTarget dataset.

arXiv:2406.03015

Balancing Performance and Efficiency in Zero-shot Robotic Navigation

We present an optimization study of the Vision-Language Frontier Maps (VLFM) applied to the Object Goal Navigation task in robotics. Our work evaluates the efficiency and performance of various vision-language models, object detectors, segmentation models, and multi-modal comprehension and Visual Question Answering modules. Using the $\textit{val-mini}$ and $\textit{val}$ splits of Habitat-Matterport 3D dataset, we conduct experiments on a desktop with limited VRAM. We propose a solution that achieves a higher success rate (+1.55%) improving over the VLFM BLIP-2 baseline without substantial success-weighted path length loss while requiring $\textbf{2.3 times}$ less video memory. Our findings provide insights into balancing model performance and computational efficiency, suggesting effective deployment strategies for resource-limited environments.

arXiv:2406.02748

Story Generation from Visual Inputs: Techniques, Related Tasks, and Challenges

Creating engaging narratives from visual data is crucial for automated digital media consumption, assistive technologies, and interactive entertainment. This survey covers methodologies used in the generation of these narratives, focusing on their principles, strengths, and limitations. The survey also covers tasks related to automatic story generation, such as image and video captioning, and visual question answering, as well as story generation without visual inputs. These tasks share common challenges with visual story generation and have served as inspiration for the techniques used in the field. We analyze the main datasets and evaluation metrics, providing a critical perspective on their limitations.

arXiv:2406.03496

Wings: Learning Multimodal LLMs without Text-only Forgetting

Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophically forgets the text-only instructions, which do not include images and can be addressed within the initial LLM. In this paper, we present Wings, a novel MLLM that excels in both text-only dialogues and multimodal comprehension. Analyzing MLLM attention in multimodal instructions reveals that text-only forgetting is related to the attention shifts from pre-image to post-image text. From that, we construct extra modules that act as the boosted learner to compensate for the attention shift. The complementary visual and textual learners, like "wings" on either side, are connected in parallel within each layer's attention block. Initially, image and text inputs are aligned with visual learners operating alongside the main attention, balancing focus on visual elements. Textual learners are later collaboratively integrated with attention-based routing to blend the outputs of the visual and textual learners. We design the Low-Rank Residual Attention (LoRRA) to guarantee high efficiency for learners. Our experimental results demonstrate that Wings outperforms equally-scaled MLLMs in both text-only and visual question-answering tasks. On a newly constructed Interleaved Image-Text (IIT) benchmark, Wings exhibits superior performance from text-only-rich to multimodal-rich question-answering tasks.

arXiv:2406.01495공식 코드 · Papers with Code

Re-ReST: Reflection-Reinforced Self-Training for Language Agents

Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impractical. In this paper, we investigate the use of self-training in language agents, which can generate supervision from the agent itself, offering a promising alternative without relying on human or stronger model demonstrations. Self-training, however, requires high-quality model-generated samples, which are hard to obtain for challenging language agent tasks. To address this, we present Reflection-Reinforced Self-Training (Re-ReST), which uses a \textit{reflector} to refine low-quality generated samples during self-training. The reflector takes the agent's output and feedback from an external environment (e.g., unit test results in code generation) to produce improved samples. This technique enhances the quality of inferior samples and efficiently enriches the self-training dataset with higher-quality samples. We conduct extensive experiments on open-source language agents across tasks, including multi-hop question answering, sequential decision-making, code generation, visual question answering, and text-to-image generation. The results demonstrate the effectiveness of self-training and Re-ReST in language agent tasks, with self-training improving baselines by 7.6\% on HotpotQA and 28.4\% on AlfWorld, and Re-ReST further boosting performance by 2.0\% and 14.1\%, respectively. Our studies also confirm the efficiency of using a reflector to generate high-quality samples for self-training. Moreover, we demonstrate a method to employ reflection during inference without ground-truth feedback, addressing the limitation of previous reflection work. Our code is released at https://github.com/PlusLabNLP/Re-ReST.

arXiv:2406.02331

Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering

Building a reliable visual question answering~(VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts.

arXiv:2406.00980

Selectively Answering Visual Questions

Recently, large multi-modal models (LMMs) have emerged with the capacity to perform vision tasks such as captioning and visual question answering (VQA) with unprecedented accuracy. Applications such as helping the blind or visually impaired have a critical need for precise answers. It is specially important for models to be well calibrated and be able to quantify their uncertainty in order to selectively decide when to answer and when to abstain or ask for clarifications. We perform the first in-depth analysis of calibration methods and metrics for VQA with in-context learning LMMs. Studying VQA on two answerability benchmarks, we show that the likelihood score of visually grounded models is better calibrated than in their text-only counterparts for in-context learning, where sampling based methods are generally superior, but no clear winner arises. We propose Avg BLEU, a calibration score combining the benefits of both sampling and likelihood methods across modalities.

arXiv:2406.00977공식 코드 · Papers with Code

Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models

Recent advances in vision-language models (VLMs) have demonstrated the advantages of processing images at higher resolutions and utilizing multi-crop features to preserve native resolution details. However, despite these improvements, existing vision transformers (ViTs) still struggle to capture fine-grained details from less prominent objects, charts, and embedded text, limiting their effectiveness in certain tasks. In this paper, we extend recent high-resolution and multi-crop techniques by not only preserving the native resolution, but zooming in beyond it and extracting features from a large number of image sub-crops. This enhancement allows our model to better capture fine-grained details, overcoming the limitations of current ViTs. To manage the increased token count and computational complexity, we demonstrate that a simple mean-pooling aggregation over tokens is effective. Our model, Dragonfly, achieves competitive performance on general-domain tasks such as ScienceQA and AI2D, and excels in tasks requiring fine-grained image understanding, including TextVQA and ChartQA. Among models in the 7-8B parameter range, Dragonfly consistently ranks at the top across ten general-domain benchmarks, achieving the highest or second-highest scores in most cases, outperforming models that are significantly larger or trained on larger datasets. Our biomedical model, Dragonfly-Med, sets new benchmarks on several medical tasks, achieving 91.6% accuracy on SLAKE (compared to 84.8% for Med-Gemini), a 67.1% token F1 score on Path-VQA (compared to 62.7% for Med-PaLM M), and state-of-the-art results across the majority of image captioning tasks. Overall, our work highlights the persistent challenge of engineering visual representations with fixed-resolution ViTs, and proposes a simple yet effective solution to address this issue and boost performance in both general and specialized domains.

arXiv:2406.01402

Mixture of Rationale: Multi-Modal Reasoning Mixture for Visual Question Answering

Zero-shot visual question answering (VQA) is a challenging task that requires reasoning across modalities. While some existing methods rely on a single rationale within the Chain of Thoughts (CoT) framework, they may fall short of capturing the complexity of the VQA problem. On the other hand, some other methods that use multiple rationales may still suffer from low diversity, poor modality alignment, and inefficient retrieval and fusion. In response to these challenges, we propose \emph{Mixture of Rationales (MoR)}, a novel multi-modal reasoning method that mixes multiple rationales for VQA. MoR uses a single frozen Vision-and-Language Pre-trained Models (VLPM) model to {dynamically generate, retrieve and fuse multi-modal thoughts}. We evaluate MoR on two challenging VQA datasets, i.e. NLVR2 and OKVQA, with two representative backbones OFA and VL-T5. MoR achieves a 12.43\% accuracy improvement on NLVR2, and a 2.45\% accuracy improvement on OKVQA-S( the science and technology category of OKVQA).

arXiv:2405.20421공식 코드 · Papers with Code

Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA

Large Multimodal Models (LMMs) have shown remarkable progress in medical Visual Question Answering (Med-VQA), achieving high accuracy on existing benchmarks. However, their reliability under robust evaluation is questionable. This study reveals that when subjected to simple probing evaluation, state-of-the-art models perform worse than random guessing on medical diagnosis questions. To address this critical evaluation problem, we introduce the Probing Evaluation for Medical Diagnosis (ProbMed) dataset to rigorously assess LMM performance in medical imaging through probing evaluation and procedural diagnosis. Particularly, probing evaluation features pairing original questions with negation questions with hallucinated attributes, while procedural diagnosis requires reasoning across various diagnostic dimensions for each image, including modality recognition, organ identification, clinical findings, abnormalities, and positional grounding. Our evaluation reveals that top-performing models like GPT-4o, GPT-4V, and Gemini Pro perform worse than random guessing on specialized diagnostic questions, indicating significant limitations in handling fine-grained medical inquiries. Besides, models like LLaVA-Med struggle even with more general questions, and results from CheXagent demonstrate the transferability of expertise across different modalities of the same organ, showing that specialized domain knowledge is still crucial for improving performance. This study underscores the urgent need for more robust evaluation to ensure the reliability of LMMs in critical fields like medical diagnosis, and current LMMs are still far from applicable to those fields.

arXiv:2405.19794

Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera

This paper addresses the daily challenges encountered by visually impaired individuals, such as limited access to information, navigation difficulties, and barriers to social interaction. To alleviate these challenges, we introduce a novel visual question answering dataset. Our dataset offers two significant advancements over previous datasets: Firstly, it features videos captured using a 360-degree egocentric wearable camera, enabling observation of the entire surroundings, departing from the static image-centric nature of prior datasets. Secondly, unlike datasets centered on singular challenges, ours addresses multiple real-life obstacles simultaneously through an innovative visual-question answering framework. We validate our dataset using various state-of-the-art VideoQA methods and diverse metrics. Results indicate that while progress has been made, satisfactory performance levels for AI-powered assistive services remain elusive for visually impaired individuals. Additionally, our evaluation highlights the distinctive features of the proposed dataset, featuring ego-motion in videos captured via 360-degree cameras across varied scenarios.

arXiv:2405.19773

VQA Training Sets are Self-play Environments for Generating Few-shot Pools

Large-language models and large-vision models are increasingly capable of solving compositional reasoning tasks, as measured by breakthroughs in visual-question answering benchmarks. However, state-of-the-art solutions often involve careful construction of large pre-training and fine-tuning datasets, which can be expensive. The use of external tools, whether other ML models, search engines, or APIs, can significantly improve performance by breaking down high-level reasoning questions into sub-questions that are answerable by individual tools, but this approach has similar dataset construction costs to teach fine-tuned models how to use the available tools. We propose a technique in which existing training sets can be directly used for constructing computational environments with task metrics as rewards. This enables a model to autonomously teach itself to use itself or another model as a tool. By doing so, we augment training sets by integrating external signals. The proposed method starts with zero-shot prompts and iteratively refines them by selecting few-shot examples that maximize the task metric on the training set. Our experiments showcase how Gemini learns how to use itself, or another smaller and specialized model such as ScreenAI, to iteratively improve performance on training sets. Our approach successfully generalizes and improves upon zeroshot performance on charts, infographics, and document visual question-answering datasets