PyTorchKR Papers

최신 논문

총 657편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2211.11559

Visual Programming: Compositional visual reasoning without training

We present VISPROG, a neuro-symbolic approach to solving complex and compositional visual tasks given natural language instructions. VISPROG avoids the need for any task-specific training. Instead, it uses the in-context learning ability of large language models to generate python-like modular programs, which are then executed to get both the solution and a comprehensive and interpretable rationale. Each line of the generated program may invoke one of several off-the-shelf computer vision models, image processing routines, or python functions to produce intermediate outputs that may be consumed by subsequent parts of the program. We demonstrate the flexibility of VISPROG on 4 diverse tasks - compositional visual question answering, zero-shot reasoning on image pairs, factual knowledge object tagging, and language-guided image editing. We believe neuro-symbolic approaches like VISPROG are an exciting avenue to easily and effectively expand the scope of AI systems to serve the long tail of complex tasks that people may wish to perform.

arXiv:2211.01994

lilGym: Natural Language Visual Reasoning with Reinforcement Learning

We present lilGym, a new benchmark for language-conditioned reinforcement learning in visual environments. lilGym is based on 2,661 highly-compositional human-written natural language statements grounded in an interactive visual environment. We introduce a new approach for exact reward computation in every possible world state by annotating all statements with executable Python programs. Each statement is paired with multiple start states and reward functions to form thousands of distinct Markov Decision Processes of varying difficulty. We experiment with lilGym with different models and learning regimes. Our results and analysis show that while existing methods are able to achieve non-trivial performance, lilGym forms a challenging open problem. lilGym is available at https://lil.nlp.cornell.edu/lilgym/.

arXiv:2210.05335공식 코드 · Papers with Code

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model

Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our interpretation, including inter- and intra-modal uncertainty. Little effort has studied the modeling of this uncertainty, particularly in pre-training on unlabeled datasets and fine-tuning in task-specific downstream datasets. In this paper, we project the representations of all modalities as probabilistic distributions via a Probability Distribution Encoder (PDE) by utilizing sequence-level interactions. Compared to the existing deterministic methods, such uncertainty modeling can convey richer multimodal semantic information and more complex relationships. Furthermore, we integrate uncertainty modeling with popular pre-training frameworks and propose suitable pre-training tasks: Distribution-based Vision-Language Contrastive learning (D-VLC), Distribution-based Masked Language Modeling (D-MLM), and Distribution-based Image-Text Matching (D-ITM). The fine-tuned models are applied to challenging downstream tasks, including image-text retrieval, visual question answering, visual reasoning, and visual entailment, and achieve state-of-the-art results.

arXiv:2210.04183

MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning

Multimodal representation learning has shown promising improvements on various vision-language tasks. Most existing methods excel at building global-level alignment between vision and language while lacking effective fine-grained image-text interaction. In this paper, we propose a jointly masked multimodal modeling method to learn fine-grained multimodal representations. Our method performs joint masking on image-text input and integrates both implicit and explicit targets for the masked signals to recover. The implicit target provides a unified and debiased objective for vision and language, where the model predicts latent multimodal representations of the unmasked input. The explicit target further enriches the multimodal representations by recovering high-level and semantically meaningful information: momentum visual features of image patches and concepts of word tokens. Through such a masked modeling process, our model not only learns fine-grained multimodal interaction, but also avoids the semantic gap between high-level representations and low- or mid-level prediction targets (e.g. image pixels), thus producing semantically rich multimodal representations that perform well on both zero-shot and fine-tuned settings. Our pre-trained model (named MAMO) achieves state-of-the-art performance on various downstream vision-language tasks, including image-text retrieval, visual question answering, visual reasoning, and weakly-supervised visual grounding.

arXiv:2210.01936공식 코드 · Papers with Code

When and why vision-language models behave like bags-of-words, and what to do about it?

Despite the success of large vision and language models (VLMs) in many downstream applications, it is unclear how well they encode compositional information. Here, we create the Attribution, Relation, and Order (ARO) benchmark to systematically evaluate the ability of VLMs to understand different types of relationships, attributes, and order. ARO consists of Visual Genome Attribution, to test the understanding of objects' properties; Visual Genome Relation, to test for relational understanding; and COCO & Flickr30k-Order, to test for order sensitivity. ARO is orders of magnitude larger than previous benchmarks of compositionality, with more than 50,000 test cases. We show where state-of-the-art VLMs have poor relational understanding, can blunder when linking objects to their attributes, and demonstrate a severe lack of order sensitivity. VLMs are predominantly trained and evaluated on large datasets with rich compositional structure in the images and captions. Yet, training on these datasets has not been enough to address the lack of compositional understanding, and evaluating on these datasets has failed to surface this deficiency. To understand why these limitations emerge and are not represented in the standard tests, we zoom into the evaluation and training procedures. We demonstrate that it is possible to perform well on retrieval over existing datasets without using the composition and order information. Given that contrastive pretraining optimizes for retrieval on datasets with similar shortcuts, we hypothesize that this can explain why the models do not need to learn to represent compositional information. This finding suggests a natural solution: composition-aware hard negative mining. We show that a simple-to-implement modification of contrastive learning significantly improves the performance on tasks requiring understanding of order and compositionality.

arXiv:2210.01338공식 코드 · Papers with Code

Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning

Humans tend to decompose a sentence into different parts like \textsc{sth do sth at someplace} and then fill each part with certain content. Inspired by this, we follow the \textit{principle of modular design} to propose a novel image captioner: learning to Collocate Visual-Linguistic Neural Modules (CVLNM). Unlike the \re{widely used} neural module networks in VQA, where the language (\ie, question) is fully observable, \re{the task of collocating visual-linguistic modules is more challenging.} This is because the language is only partially observable, for which we need to dynamically collocate the modules during the process of image captioning. To sum up, we make the following technical contributions to design and train our CVLNM: 1) \textit{distinguishable module design} -- \re{four modules in the encoder} including one linguistic module for function words and three visual modules for different content words (\ie, noun, adjective, and verb) and another linguistic one in the decoder for commonsense reasoning, 2) a self-attention based \textit{module controller} for robustifying the visual reasoning, 3) a part-of-speech based \textit{syntax loss} imposed on the module controller for further regularizing the training of our CVLNM. Extensive experiments on the MS-COCO dataset show that our CVLNM is more effective, \eg, achieving a new state-of-the-art 129.5 CIDEr-D, and more robust, \eg, being less likely to overfit to dataset bias and suffering less when fewer training samples are available. Codes are available at \url{https://github.com/GCYZSL/CVLMN}

arXiv:2210.00220공식 코드 · Papers with Code

A Dual-Attention Learning Network with Word and Sentence Embedding for Medical Visual Question Answering

Research in medical visual question answering (MVQA) can contribute to the development of computeraided diagnosis. MVQA is a task that aims to predict accurate and convincing answers based on given medical images and associated natural language questions. This task requires extracting medical knowledge-rich feature content and making fine-grained understandings of them. Therefore, constructing an effective feature extraction and understanding scheme are keys to modeling. Existing MVQA question extraction schemes mainly focus on word information, ignoring medical information in the text. Meanwhile, some visual and textual feature understanding schemes cannot effectively capture the correlation between regions and keywords for reasonable visual reasoning. In this study, a dual-attention learning network with word and sentence embedding (WSDAN) is proposed. We design a module, transformer with sentence embedding (TSE), to extract a double embedding representation of questions containing keywords and medical information. A dualattention learning (DAL) module consisting of self-attention and guided attention is proposed to model intensive intramodal and intermodal interactions. With multiple DAL modules (DALs), learning visual and textual co-attention can increase the granularity of understanding and improve visual reasoning. Experimental results on the ImageCLEF 2019 VQA-MED (VQA-MED 2019) and VQA-RAD datasets demonstrate that our proposed method outperforms previous state-of-the-art methods. According to the ablation studies and Grad-CAM maps, WSDAN can extract rich textual information and has strong visual reasoning ability.

arXiv:2210.00858공식 코드 · Papers with Code

Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach

In this paper we present a neurosymbolic architecture for coupling language-guided visual reasoning with robot manipulation. A non-expert human user can prompt the robot using unconstrained natural language, providing a referring expression (REF), a question (VQA), or a grasp action instruction. The system tackles all cases in a task-agnostic fashion through the utilization of a shared library of primitive skills. Each primitive handles an independent sub-task, such as reasoning about visual attributes, spatial relation comprehension, logic and enumeration, as well as arm control. A language parser maps the input query to an executable program composed of such primitives, depending on the context. While some primitives are purely symbolic operations (e.g. counting), others are trainable neural functions (e.g. visual grounding), therefore marrying the interpretability and systematic generalization benefits of discrete symbolic approaches with the scalability and representational power of deep networks. We generate a 3D vision-and-language synthetic dataset of tabletop scenes in a simulation environment to train our approach and perform extensive evaluations in both synthetic and real-world scenes. Results showcase the benefits of our approach in terms of accuracy, sample-efficiency, and robustness to the user's vocabulary, while being transferable to real-world scenes with few-shot visual fine-tuning. Finally, we integrate our method with a robot framework and demonstrate how it can serve as an interpretable solution for an interactive object-picking task, both in simulation and with a real robot. We make our datasets available in https://gtziafas.github.io/neurosymbolic-manipulation.

arXiv:2209.15087

Zero-shot visual reasoning through probabilistic analogical mapping

Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require extensive direct training on visual reasoning tasks, and yield limited generalization to problems with novel content. In contrast, a long tradition of research in cognitive science has focused on elucidating the computational principles underlying human analogical reasoning; however, this work has generally relied on manually constructed representations. Here we present visiPAM (visual Probabilistic Analogical Mapping), a model of visual reasoning that synthesizes these two approaches. VisiPAM employs learned representations derived directly from naturalistic visual inputs, coupled with a similarity-based mapping operation derived from cognitive theories of human reasoning. We show that without any direct training, visiPAM outperforms a state-of-the-art deep learning model on an analogical mapping task. In addition, visiPAM closely matches the pattern of human performance on a novel task involving mapping of 3D objects across disparate categories.

arXiv:2209.11990

Deep Neural Networks for Visual Reasoning

Visual perception and language understanding are - fundamental components of human intelligence, enabling them to understand and reason about objects and their interactions. It is crucial for machines to have this capacity to reason using these two modalities to invent new robot-human collaborative systems. Recent advances in deep learning have built separate sophisticated representations of both visual scenes and languages. However, understanding the associations between the two modalities in a shared context for multimodal reasoning remains a challenge. Focusing on language and vision modalities, this thesis advances the understanding of how to exploit and use pivotal aspects of vision-and-language tasks with neural networks to support reasoning. We derive these understandings from a series of works, making a two-fold contribution: (i) effective mechanisms for content selection and construction of temporal relations from dynamic visual scenes in response to a linguistic query and preparing adequate knowledge for the reasoning process (ii) new frameworks to perform reasoning with neural networks by exploiting visual-linguistic associations, deduced either directly from data or guided by external priors.

arXiv:2209.08163공식 코드 · Papers with Code

Belief Revision based Caption Re-ranker with Visual Semantic Information

In this work, we focus on improving the captions generated by image-caption generation systems. We propose a novel re-ranking approach that leverages visual-semantic measures to identify the ideal caption that maximally captures the visual information in the image. Our re-ranker utilizes the Belief Revision framework (Blok et al., 2003) to calibrate the original likelihood of the top-n captions by explicitly exploiting the semantic relatedness between the depicted caption and the visual context. Our experiments demonstrate the utility of our approach, where we observe that our re-ranker can enhance the performance of a typical image-captioning system without the necessity of any additional training or fine-tuning.

arXiv:2209.09115공식 코드 · Papers with Code

Compositional Law Parsing with Latent Random Functions

Human cognition has compositionality. We understand a scene by decomposing the scene into different concepts (e.g., shape and position of an object) and learning the respective laws of these concepts, which may be either natural (e.g., laws of motion) or man-made (e.g., laws of a game). The automatic parsing of these laws indicates the model's ability to understand the scene, which makes law parsing play a central role in many visual tasks. This paper proposes a deep latent variable model for Compositional LAw Parsing (CLAP), which achieves the human-like compositionality ability through an encoding-decoding architecture to represent concepts in the scene as latent variables. CLAP employs concept-specific latent random functions instantiated with Neural Processes to capture the law of concepts. Our experimental results demonstrate that CLAP outperforms the baseline methods in multiple visual tasks such as intuitive physics, abstract visual reasoning, and scene representation. The law manipulation experiments illustrate CLAP's interpretability by modifying specific latent random functions on samples. For example, CLAP learns the laws of position-changing and appearance constancy from the moving balls in a scene, making it possible to exchange laws between samples or compose existing laws into novel laws.

arXiv:2209.07000공식 코드 · Papers with Code

VIPHY: Probing "Visible" Physical Commonsense Knowledge

In recent years, vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks (e.g. attributes, location). While such tasks measure the requisite knowledge to ground and reason over a given visual instance, they do not, however, measure the ability of VLMs to retain and generalize such knowledge. In this work, we evaluate their ability to acquire "visible" physical knowledge -- the information that is easily accessible from images of static scenes, particularly across the dimensions of object color, size and space. We build an automatic pipeline to derive a comprehensive knowledge resource for calibrating and probing these models. Our results indicate a severe gap between model and human performance across all three tasks. Furthermore, our caption pretrained baseline (CapBERT) significantly outperforms VLMs on both size and spatial tasks -- highlighting that despite sufficient access to ground language with visual modality, they struggle to retain such knowledge. The dataset and code are available at https://github.com/Axe--/ViPhy .

arXiv:2209.06794공식 코드 · Papers with Code

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Effective scaling and a flexible task interface enable large language models to excel at many tasks. We present PaLI (Pathways Language and Image model), a model that extends this approach to the joint modeling of language and vision. PaLI generates text based on visual and textual inputs, and with this interface performs many vision, language, and multimodal tasks, in many languages. To train PaLI, we make use of large pre-trained encoder-decoder language models and Vision Transformers (ViTs). This allows us to capitalize on their existing capabilities and leverage the substantial cost of training them. We find that joint scaling of the vision and language components is important. Since existing Transformers for language are much larger than their vision counterparts, we train a large, 4-billion parameter ViT (ViT-e) to quantify the benefits from even larger-capacity vision models. To train PaLI, we create a large multilingual mix of pretraining tasks, based on a new image-text training set containing 10B images and texts in over 100 languages. PaLI achieves state-of-the-art in multiple vision and language tasks (such as captioning, visual question-answering, scene-text understanding), while retaining a simple, modular, and scalable design.

arXiv:2208.13628공식 코드 · Papers with Code

Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment

Vision and Language Pretraining has become the prevalent approach for tackling multimodal downstream tasks. The current trend is to move towards ever larger models and pretraining datasets. This computational headlong rush does not seem reasonable in the long term to move toward sustainable solutions, and de facto excludes academic laboratories with limited resources. In this work, we propose a new framework, dubbed ViCHA, that efficiently exploits the input data to boost the learning by: (a) a new hierarchical cross-modal alignment loss, (b) new self-supervised scheme based on masked image modeling, (c) leveraging image-level annotations, called Visual Concepts, obtained with existing foundation models such as CLIP to boost the performance of the image encoder. Although pretrained on four times less data, our ViCHA strategy outperforms other approaches on several downstream tasks such as Image-Text Retrieval, VQA, Visual Reasoning, Visual Entailment and Visual Grounding. The code will be made publicly available here: https://github.com/mshukor/ViCHA

arXiv:2208.10442공식 코드 · Papers with Code

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).

arXiv:2208.00361

One for All: One-stage Referring Expression Comprehension with Dynamic Reasoning

Referring Expression Comprehension (REC) is one of the most important tasks in visual reasoning that requires a model to detect the target object referred by a natural language expression. Among the proposed pipelines, the one-stage Referring Expression Comprehension (OSREC) has become the dominant trend since it merges the region proposal and selection stages. Many state-of-the-art OSREC models adopt a multi-hop reasoning strategy because a sequence of objects is frequently mentioned in a single expression which needs multi-hop reasoning to analyze the semantic relation. However, one unsolved issue of these models is that the number of reasoning steps needs to be pre-defined and fixed before inference, ignoring the varying complexity of expressions. In this paper, we propose a Dynamic Multi-step Reasoning Network, which allows the reasoning steps to be dynamically adjusted based on the reasoning state and expression complexity. Specifically, we adopt a Transformer module to memorize & process the reasoning state and a Reinforcement Learning strategy to dynamically infer the reasoning steps. The work achieves the state-of-the-art performance or significant improvements on several REC datasets, ranging from RefCOCO (+, g) with short expressions, to Ref-Reasoning, a dataset with long and complex compositional expressions.

arXiv:2207.12576공식 코드 · Papers with Code

WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models

While vision-and-language models perform well on tasks such as visual question answering, they struggle when it comes to basic human commonsense reasoning skills. In this work, we introduce WinoGAViL: an online game of vision-and-language associations (e.g., between werewolves and a full moon), used as a dynamic evaluation benchmark. Inspired by the popular card game Codenames, a spymaster gives a textual cue related to several visual candidates, and another player tries to identify them. Human players are rewarded for creating associations that are challenging for a rival AI model but still solvable by other human players. We use the game to collect 3.5K instances, finding that they are intuitive for humans (>90% Jaccard index) but challenging for state-of-the-art AI models, where the best model (ViLT) achieves a score of 52%, succeeding mostly where the cue is visually salient. Our analysis as well as the feedback we collect from players indicate that the collected associations require diverse reasoning skills, including general knowledge, common sense, abstraction, and more. We release the dataset, the code and the interactive game, allowing future data collection that can be used to develop models with better association abilities.

arXiv:2207.06403

3D Concept Grounding on Neural Fields

In this paper, we address the challenging problem of 3D concept grounding (i.e. segmenting and learning visual concepts) by looking at RGBD images and reasoning about paired questions and answers. Existing visual reasoning approaches typically utilize supervised methods to extract 2D segmentation masks on which concepts are grounded. In contrast, humans are capable of grounding concepts on the underlying 3D representation of images. However, traditionally inferred 3D representations (e.g., point clouds, voxelgrids, and meshes) cannot capture continuous 3D features flexibly, thus making it challenging to ground concepts to 3D regions based on the language description of the object being referred to. To address both issues, we propose to leverage the continuous, differentiable nature of neural fields to segment and learn concepts. Specifically, each 3D coordinate in a scene is represented as a high-dimensional descriptor. Concept grounding can then be performed by computing the similarity between the descriptor vector of a 3D coordinate and the vector embedding of a language concept, which enables segmentations and concept learning to be jointly learned on neural fields in a differentiable fashion. As a result, both 3D semantic and instance segmentations can emerge directly from question answering supervision using a set of defined neural operators on top of neural fields (e.g., filtering and counting). Experimental results show that our proposed framework outperforms unsupervised/language-mediated segmentation models on semantic and instance segmentation tasks, as well as outperforms existing models on the challenging 3D aware visual reasoning tasks. Furthermore, our framework can generalize well to unseen shape categories and real scans.

arXiv:2206.12533

From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering

In order to achieve a general visual question answering (VQA) system, it is essential to learn to answer deeper questions that require compositional reasoning on the image and external knowledge. Meanwhile, the reasoning process should be explicit and explainable to understand the working mechanism of the model. It is effortless for human but challenging for machines. In this paper, we propose a Hierarchical Graph Neural Module Network (HGNMN) that reasons over multi-layer graphs with neural modules to address the above issues. Specifically, we first encode the image by multi-layer graphs from the visual, semantic and commonsense views since the clues that support the answer may exist in different modalities. Our model consists of several well-designed neural modules that perform specific functions over graphs, which can be used to conduct multi-step reasoning within and between different graphs. Compared to existing modular networks, we extend visual reasoning from one graph to more graphs. We can explicitly trace the reasoning process according to module weights and graph attentions. Experiments show that our model not only achieves state-of-the-art performance on the CRIC dataset but also obtains explicit and explainable reasoning procedures.