PyTorchKR Papers

최신 논문

총 2,558편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2403.12026

FlexCap: Describe Anything in Images in Controllable Detail

We introduce FlexCap, a vision-language model that generates region-specific descriptions of varying lengths. FlexCap is trained to produce length-conditioned captions for input boxes, enabling control over information density, with descriptions ranging from concise object labels to detailed captions. To achieve this, we create large-scale training datasets of image region descriptions with varying lengths from captioned web images. We demonstrate FlexCap's effectiveness in several applications: first, it achieves strong performance in dense captioning tasks on the Visual Genome dataset. Second, we show how FlexCap's localized descriptions can serve as input to a large language model to create a visual question answering (VQA) system, achieving state-of-the-art zero-shot performance on multiple VQA benchmarks. Our experiments illustrate FlexCap's utility for tasks including image labeling, object attribute recognition, and visual dialog. Project webpage: https://flex-cap.github.io .

arXiv:2403.10534

VISREAS: Complex Visual Reasoning with Unanswerable Questions

Verifying a question's validity before answering is crucial in real-world applications, where users may provide imperfect instructions. In this scenario, an ideal model should address the discrepancies in the query and convey them to the users rather than generating the best possible answer. Addressing this requirement, we introduce a new compositional visual question-answering dataset, VISREAS, that consists of answerable and unanswerable visual queries formulated by traversing and perturbing commonalities and differences among objects, attributes, and relations. VISREAS contains 2.07M semantically diverse queries generated automatically using Visual Genome scene graphs. The unique feature of this task, validating question answerability with respect to an image before answering, and the poor performance of state-of-the-art models inspired the design of a new modular baseline, LOGIC2VISION that reasons by producing and executing pseudocode without any external modules to generate the answer. LOGIC2VISION outperforms generative models in VISREAS (+4.82% over LLaVA-1.5; +12.23% over InstructBLIP) and achieves a significant gain in performance against the classification models.

arXiv:2403.11317

Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches

Two approaches have emerged to input images into large language models (LLMs). The first is to caption images into natural language. The second is to map image feature embeddings into the domain of the LLM and pass the mapped embeddings directly to the LLM. The majority of recent few-shot multimodal work reports performance using architectures that employ variations of one of these two approaches. But they overlook an important comparison between them. We design a controlled and focused experiment to compare these two approaches to few-shot visual question answering (VQA) with LLMs. Our findings indicate that for Flan-T5 XL, a 3B parameter LLM, connecting visual embeddings directly to the LLM embedding space does not guarantee improved performance over using image captions. In the zero-shot regime, we find using textual image captions is better. In the few-shot regimes, how the in-context examples are selected determines which is better.

arXiv:2403.10704

Parameter Efficient Reinforcement Learning from Human Feedback

While Reinforcement Learning from Human Feedback (RLHF) effectively aligns pretrained Large Language and Vision-Language Models (LLMs, and VLMs) with human preferences, its computational cost and complexity hamper its wider adoption. To alleviate some of the computational burden of fine-tuning, parameter efficient methods, like LoRA were introduced. In this work, we empirically evaluate the setup of Parameter Efficient Reinforcement Learning from Human Feedback (PE-RLHF) that leverages LoRA fine-tuning for Reward Modeling, and Reinforcement Learning. We benchmark the PE-RLHF setup on six diverse datasets spanning summarization, harmless/helpful response generation, UI automation, and visual question answering in terms of effectiveness of the trained models, and the training resources required. Our findings show, for the first time, that PE-RLHF achieves comparable performance to RLHF, while significantly reducing training time (up to 90% faster for reward models, and 30% faster for RL), and memory footprint (up to 50% reduction for reward models, and 27% for RL). We provide comprehensive ablations across LoRA ranks, and model sizes for both reward modeling and reinforcement learning. By mitigating the computational burden associated with RLHF, we push for a broader adoption of PE-RLHF as an alignment technique for LLMs and VLMs.

arXiv:2403.11487

Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis

We present a novel approach to automatically synthesize "wayfinding instructions" for an embodied robot agent. In contrast to prior approaches that are heavily reliant on human-annotated datasets designed exclusively for specific simulation platforms, our algorithm uses in-context learning to condition an LLM to generate instructions using just a few references. Using an LLM-based Visual Question Answering strategy, we gather detailed information about the environment which is used by the LLM for instruction synthesis. We implement our approach on multiple simulation platforms including Matterport3D, AI Habitat and ThreeDWorld, thereby demonstrating its platform-agnostic nature. We subjectively evaluate our approach via a user study and observe that 83.3% of users find the synthesized instructions accurately capture the details of the environment and show characteristics similar to those of human-generated instructions. Further, we conduct zero-shot navigation with multiple approaches on the REVERIE dataset using the generated instructions, and observe very close correlation with the baseline on standard success metrics (< 1% change in SR), quantifying the viability of generated instructions in replacing human-annotated data. We finally discuss the applicability of our approach in enabling a generalizable evaluation of embodied navigation policies. To the best of our knowledge, ours is the first LLM-driven approach capable of generating "human-like" instructions in a platform-agnostic manner, without training.

arXiv:2403.11299공식 코드 · Papers with Code

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant

Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the whole network's bottleneck. To improve cross-modality alignment, existing works usually consider more visual instruction data covering a broader range of vision tasks to fine-tune the model for question-answering, which, however, is costly to obtain and has not thoroughly explored the rich contextual information contained in images. This paper first attempts to harness the overlooked context within visual instruction data, training the model to self-supervised "learning" how to ask high-quality questions. In this way, we introduce a novel framework named SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant. SQ-LLaVA exhibits proficiency in generating flexible and meaningful image-related questions while analyzing the visual clue and prior language knowledge, signifying an advanced level of generalized visual understanding. Moreover, fine-tuning SQ-LLaVA on higher-quality instruction data shows a performance improvement compared with traditional visual-instruction tuning methods. This improvement highlights the efficacy of self-questioning techniques in achieving a deeper and more nuanced comprehension of visual content across various contexts.

arXiv:2403.10037

Knowledge Condensation and Reasoning for Knowledge-based VQA

Knowledge-based visual question answering (KB-VQA) is a challenging task, which requires the model to leverage external knowledge for comprehending and answering questions grounded in visual content. Recent studies retrieve the knowledge passages from external knowledge bases and then use them to answer questions. However, these retrieved knowledge passages often contain irrelevant or noisy information, which limits the performance of the model. To address the challenge, we propose two synergistic models: Knowledge Condensation model and Knowledge Reasoning model. We condense the retrieved knowledge passages from two perspectives. First, we leverage the multimodal perception and reasoning ability of the visual-language models to distill concise knowledge concepts from retrieved lengthy passages, ensuring relevance to both the visual content and the question. Second, we leverage the text comprehension ability of the large language models to summarize and condense the passages into the knowledge essence which helps answer the question. These two types of condensed knowledge are then seamlessly integrated into our Knowledge Reasoning model, which judiciously navigates through the amalgamated information to arrive at the conclusive answer. Extensive experiments validate the superiority of the proposed method. Compared to previous methods, our method achieves state-of-the-art performance on knowledge-based VQA datasets (65.1% on OK-VQA and 60.1% on A-OKVQA) without resorting to the knowledge produced by GPT-3 (175B).

arXiv:2403.10287

Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models

The task of few-shot image classification and segmentation (FS-CS) involves classifying and segmenting target objects in a query image, given only a few examples of the target classes. We introduce the Vision-Instructed Segmentation and Evaluation (VISE) method that transforms the FS-CS problem into the Visual Question Answering (VQA) problem, utilising Vision-Language Models (VLMs), and addresses it in a training-free manner. By enabling a VLM to interact with off-the-shelf vision models as tools, the proposed method is capable of classifying and segmenting target objects using only image-level labels. Specifically, chain-of-thought prompting and in-context learning guide the VLM to answer multiple-choice questions like a human; vision models such as YOLO and Segment Anything Model (SAM) assist the VLM in completing the task. The modular framework of the proposed method makes it easily extendable. Our approach achieves state-of-the-art performance on the Pascal-5i and COCO-20i datasets.

arXiv:2403.08773공식 코드 · Papers with Code

Veagle: Advancements in Multimodal Representation Learning

Lately, researchers in artificial intelligence have been really interested in how language and vision come together, giving rise to the development of multimodal models that aim to seamlessly integrate textual and visual information. Multimodal models, an extension of Large Language Models (LLMs), have exhibited remarkable capabilities in addressing a diverse array of tasks, ranging from image captioning and visual question answering (VQA) to visual grounding. While these models have showcased significant advancements, challenges persist in accurately interpreting images and answering the question, a common occurrence in real-world scenarios. This paper introduces a novel approach to enhance the multimodal capabilities of existing models. In response to the limitations observed in current Vision Language Models (VLMs) and Multimodal Large Language Models (MLLMs), our proposed model Veagle, incorporates a unique mechanism inspired by the successes and insights of previous works. Veagle leverages a dynamic mechanism to project encoded visual information directly into the language model. This dynamic approach allows for a more nuanced understanding of intricate details present in visual contexts. To validate the effectiveness of Veagle, we conduct comprehensive experiments on benchmark datasets, emphasizing tasks such as visual question answering and image understanding. Our results indicate a improvement of 5-6 \% in performance, with Veagle outperforming existing models by a notable margin. The outcomes underscore the model's versatility and applicability beyond traditional benchmarks.

arXiv:2403.09027

VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework

With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In this paper, we introduce VisionGPT to consolidate and automate the integration of state-of-the-art foundation models, thereby facilitating vision-language understanding and the development of vision-oriented AI. VisionGPT builds upon a generalized multimodal framework that distinguishes itself through three key features: (1) utilizing LLMs (e.g., LLaMA-2) as the pivot to break down users' requests into detailed action proposals to call suitable foundation models; (2) integrating multi-source outputs from foundation models automatically and generating comprehensive responses for users; (3) adaptable to a wide range of applications such as text-conditioned image understanding/generation/editing and visual question answering. This paper outlines the architecture and capabilities of VisionGPT, demonstrating its potential to revolutionize the field of computer vision through enhanced efficiency, versatility, and generalization, and performance. Our code and models will be made publicly available. Keywords: VisionGPT, Open-world visual perception, Vision-language understanding, Large language model, and Foundation model

arXiv:2403.09611

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

In this work, we discuss building performant Multimodal Large Language Models (MLLMs). In particular, we study the importance of various architecture components and data choices. Through careful and comprehensive ablations of the image encoder, the vision language connector, and various pre-training data choices, we identified several crucial design lessons. For example, we demonstrate that for large-scale multimodal pre-training using a careful mix of image-caption, interleaved image-text, and text-only data is crucial for achieving state-of-the-art (SOTA) few-shot results across multiple benchmarks, compared to other published pre-training results. Further, we show that the image encoder together with image resolution and the image token count has substantial impact, while the vision-language connector design is of comparatively negligible importance. By scaling up the presented recipe, we build MM1, a family of multimodal models up to 30B parameters, including both dense models and mixture-of-experts (MoE) variants, that are SOTA in pre-training metrics and achieve competitive performance after supervised fine-tuning on a range of established multimodal benchmarks. Thanks to large-scale pre-training, MM1 enjoys appealing properties such as enhanced in-context learning, and multi-image reasoning, enabling few-shot chain-of-thought prompting.

arXiv:2403.09288공식 코드 · Papers with Code

Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering

Scene-Text Visual Question Answering (ST-VQA) aims to understand scene text in images and answer questions related to the text content. Most existing methods heavily rely on the accuracy of Optical Character Recognition (OCR) systems, and aggressive fine-tuning based on limited spatial location information and erroneous OCR text information often leads to inevitable overfitting. In this paper, we propose a multimodal adversarial training architecture with spatial awareness capabilities. Specifically, we introduce an Adversarial OCR Enhancement (AOE) module, which leverages adversarial training in the embedding space of OCR modality to enhance fault-tolerant representation of OCR texts, thereby reducing noise caused by OCR errors. Simultaneously, We add a Spatial-Aware Self-Attention (SASA) mechanism to help the model better capture the spatial relationships among OCR tokens. Various experiments demonstrate that our method achieves significant performance improvements on both the ST-VQA and TextVQA datasets and provides a novel paradigm for multimodal adversarial training.

arXiv:2403.09193공식 코드 · Papers with Code

Can We Talk Models Into Seeing the World Differently?

Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model (LLM) with a vision encoder. However, both the LLM and the vision encoder come with their own set of biases, cue preferences, and shortcuts, which have been rigorously studied in uni-modal models. A timely question is how such (potentially misaligned) biases and cue preferences behave under multi-modal fusion in VLMs. As a first step towards a better understanding, we investigate a particularly well-studied vision-only bias - the texture vs. shape bias and the dominance of local over global information. As expected, we find that VLMs inherit this bias to some extent from their vision encoders. Surprisingly, the multi-modality alone proves to have important effects on the model behavior, i.e., the joint training and the language querying change the way visual cues are processed. While this direct impact of language-informed training on a model's visual perception is intriguing, it raises further questions on our ability to actively steer a model's output so that its prediction is based on particular visual cues of the user's choice. Interestingly, VLMs have an inherent tendency to recognize objects based on shape information, which is different from what a plain vision encoder would do. Further active steering towards shape-based classifications through language prompts is however limited. In contrast, active VLM steering towards texture-based decisions through simple natural language prompts is often more successful. URL: https://github.com/paulgavrikov/vlm_shapebias

arXiv:2403.08730

Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization

Multimodal Large Language Models (MLLMs) excel in generating responses based on visual inputs. However, they often suffer from a bias towards generating responses similar to their pretraining corpus, overshadowing the importance of visual information. We treat this bias as a "preference" for pretraining statistics, which hinders the model's grounding in visual input. To mitigate this issue, we propose Bootstrapped Preference Optimization (BPO), which conducts preference learning with datasets containing negative responses bootstrapped from the model itself. Specifically, we propose the following two strategies: 1) using distorted image inputs to the MLLM for eliciting responses that contain signified pretraining bias; 2) leveraging text-based LLM to explicitly inject erroneous but common elements into the original response. Those undesirable responses are paired with original annotated responses from the datasets to construct the preference dataset, which is subsequently utilized to perform preference learning. Our approach effectively suppresses pretrained LLM bias, enabling enhanced grounding in visual inputs. Extensive experimentation demonstrates significant performance improvements across multiple benchmarks, advancing the state-of-the-art in multimodal conversational systems.

arXiv:2403.08092

Mitigating the Impact of Attribute Editing on Face Recognition

Through a large-scale study over diverse face images, we show that facial attribute editing using modern generative AI models can severely degrade automated face recognition systems. This degradation persists even with identity-preserving generative models. To mitigate this issue, we propose two novel techniques for local and global attribute editing. We empirically ablate twenty-six facial semantic, demographic and expression-based attributes that have been edited using state-of-the-art generative models, and evaluate them using ArcFace and AdaFace matchers on CelebA, CelebAMaskHQ and LFW datasets. Finally, we use LLaVA, an emerging visual question-answering framework for attribute prediction to validate our editing techniques. Our methods outperform the current state-of-the-art at facial editing (BLIP, InstantID) while improving identity retention by a significant extent.

arXiv:2403.07794

Fine-tuning Large Language Models with Sequential Instructions

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple intermediate tasks. Thus, we contend that part of the fine-tuning data mixture should be sequential--containing a chain of interrelated tasks. We first approach sequential instruction tuning from a task-driven perspective, manually creating interpretable intermediate tasks for multilingual and visual question answering: namely "translate then predict" and "caption then answer". Next, we automate this process by turning instructions in existing datasets (e.g., Alpaca and FlanCoT) into diverse and complex sequential instructions, making our method general-purpose. Models that underwent our sequential instruction tuning show improved results in coding, maths, and open-ended generation. Moreover, we put forward a new benchmark named SeqEval to evaluate a model's ability to follow all the instructions in a sequence, which further corroborates the benefits of our fine-tuning method. We hope that our endeavours will open new research avenues on instruction tuning for complex tasks.

arXiv:2403.07874공식 코드 · Papers with Code

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

In this work, we investigate the potential of a large language model (LLM) to directly comprehend visual signals without the necessity of fine-tuning on multi-modal datasets. The foundational concept of our method views an image as a linguistic entity, and translates it to a set of discrete words derived from the LLM's vocabulary. To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model. With this innovative image encoding, the LLM gains the ability not only for visual comprehension but also for image denoising and restoration in an auto-regressive fashion-crucially, without any fine-tuning. We undertake rigorous experiments to validate our method, encompassing understanding tasks like image recognition, image captioning, and visual question answering, as well as image denoising tasks like inpainting, outpainting, deblurring, and shift restoration. Code and models are available at https://github.com/zh460045050/V2L-Tokenizer.

arXiv:2403.07508공식 코드 · Papers with Code

MoAI: Mixture of All Intelligence for Large Language and Vision Models

The rise of large language models (LLMs) and instruction tuning has led to the current trend of instruction-tuned large language and vision models (LLVMs). This trend involves either meticulously curating numerous instruction tuning datasets tailored to specific objectives or enlarging LLVMs to manage vast amounts of vision language (VL) data. However, current LLVMs have disregarded the detailed and comprehensive real-world scene understanding available from specialized computer vision (CV) models in visual perception tasks such as segmentation, detection, scene graph generation (SGG), and optical character recognition (OCR). Instead, the existing LLVMs rely mainly on the large capacity and emergent capabilities of their LLM backbones. Therefore, we present a new LLVM, Mixture of All Intelligence (MoAI), which leverages auxiliary visual information obtained from the outputs of external segmentation, detection, SGG, and OCR models. MoAI operates through two newly introduced modules: MoAI-Compressor and MoAI-Mixer. After verbalizing the outputs of the external CV models, the MoAI-Compressor aligns and condenses them to efficiently use relevant auxiliary visual information for VL tasks. MoAI-Mixer then blends three types of intelligence (1) visual features, (2) auxiliary features from the external CV models, and (3) language features by utilizing the concept of Mixture of Experts. Through this integration, MoAI significantly outperforms both open-source and closed-source LLVMs in numerous zero-shot VL tasks, particularly those related to real-world scene understanding such as object existence, positions, relations, and OCR without enlarging the model size or curating extra visual instruction tuning datasets.

arXiv:2403.07720공식 코드 · Papers with Code

Multi-modal Auto-regressive Modeling via Visual Words

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive modelling to multi-modal scenarios to build Large Multi-modal Models (LMMs), there lies a great difficulty that the image information is processed in the LMM as continuous visual embeddings, which cannot obtain discrete supervised labels for classification.In this paper, we successfully perform multi-modal auto-regressive modeling with a unified objective for the first time.Specifically, we propose the concept of visual tokens, which maps the visual features to probability distributions over LLM's vocabulary, providing supervision information for visual modelling.We further explore the distribution of visual features in the semantic space within LMM and the possibility of using text embeddings to represent visual information.Experimental results and ablation studies on 5 VQA tasks and 4 benchmark toolkits validate the powerful performance of our proposed approach.

arXiv:2403.06679공식 코드 · Papers with Code

Answering Diverse Questions via Text Attached with Key Audio-Visual Clues

Audio-visual question answering (AVQA) requires reference to video content and auditory information, followed by correlating the question to predict the most precise answer. Although mining deeper layers of audio-visual information to interact with questions facilitates the multimodal fusion process, the redundancy of audio-visual parameters tends to reduce the generalization of the inference engine to multiple question-answer pairs in a single video. Indeed, the natural heterogeneous relationship between audiovisuals and text makes the perfect fusion challenging, to prevent high-level audio-visual semantics from weakening the network's adaptability to diverse question types, we propose a framework for performing mutual correlation distillation (MCD) to aid question inference. MCD is divided into three main steps: 1) firstly, the residual structure is utilized to enhance the audio-visual soft associations based on self-attention, then key local audio-visual features relevant to the question context are captured hierarchically by shared aggregators and coupled in the form of clues with specific question vectors. 2) Secondly, knowledge distillation is enforced to align audio-visual-text pairs in a shared latent space to narrow the cross-modal semantic gap. 3) And finally, the audio-visual dependencies are decoupled by discarding the decision-level integrations. We evaluate the proposed method on two publicly available datasets containing multiple question-and-answer pairs, i.e., Music-AVQA and AVQA. Experiments show that our method outperforms other state-of-the-art methods, and one interesting finding behind is that removing deep audio-visual features during inference can effectively mitigate overfitting. The source code is released at http://github.com/rikeilong/MCD-forAVQA.