Convolutional Neural Networks (CNNs) have become the state of the art method for image classification in the last ten years. Despite the fact that they achieve superhuman classification accuracy on many popular datasets, they often perform much worse on more abstract image classification tasks. We will show that these difficult tasks are linked to relational concepts from cognitive psychology and that despite progress over the last few years, such relational reasoning tasks still remain difficult for current neural network architectures.
We will review deep learning research that is linked to relational concept learning, even if it was not originally presented from this angle. Reviewing the current literature, we will argue that some form of attention will be an important component of future systems to solve relational tasks.
In addition, we will point out the shortcomings of currently used datasets, and we will recommend steps to make future datasets more relevant for testing systems on relational reasoning.
In the past ten years, with the help of deep learning, especially the rapid development of deep neural networks, medical image analysis has made remarkable progress. However, how to effectively use the relational information between various tissues or organs in medical images is still a very challenging problem, and it has not been fully studied. In this thesis, we propose two novel solutions to this problem based on deep relational learning. First, we propose a context-aware fully convolutional network that effectively models implicit relation information between features to perform medical i…
MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models
Multimodal Art Projection Research Community（多模态艺术投影研究社区）；University of Manchester（曼彻斯特大学）；National University of Singapore（新加坡国立大学）；Dartmouth College（达特茅斯学院）；Peking University（北京大学）；University of Waterloo（滑铁卢大学）
Beijing Institute of Technology（北京理工大学）；University of Rochester（罗切斯特大学）
Exploiting relationships among objects has achieved remarkable progress in interpreting images or videos by natural language. Most existing methods resort to first detecting objects and their relationships, and then generating textual descriptions, which heavily depends on pre-trained detectors and leads to performance drop when facing problems of heavy occlusion, tiny-size objects and long-tail in object detection. In addition, the separate procedure of detecting and captioning results in semantic inconsistency between the pre-defined object/relation categories and the target lexical words. W…
Bournemouth University（伯恩茅斯大学）；Xiamen University（厦门大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Tsinghua University（清华大学）
Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a single RGB image, our method simultaneously recovers semantic contents, 3D geometry and object relationship by reasoning indoor environment context. Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling. It involves multi-level convolutional networks to parse indoor semantics/g…
Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different subcategories still remains a challenge. In this paper, we propose to solve this issue in one unified framework from two aspects, i.e., constructing feature-level interrelationships, and capturing part-level discriminative features. This framework, namely PArt-guided Relational Transformers (PART), is proposed to learn the discriminative part features with an automatic…
UCLA Center for Vision, Cognition, Learning and Autonomy（加州大学洛杉矶分校视觉、认知、学习与自主性中心）；International Center for AI and Robot Autonomy (CARA)（人工智能与机器人自主性国际中心（CARA））
Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and human intelligence in terms of higher-level vision problems, especially ones involving reasoning. Earlier attempts in equipping machines with high-level reasoning have hovered around Visual Question Answering (VQA), one typical task associating vision and language understanding. In this work, we propose a new dataset, built in the context of Raven's Progress…
Unraveling the geometry of visual relational reasoning
Program in Neuroscience, Harvard Medical School（神经科学项目，哈佛医学院）；Boston Children’s Hospital, Harvard Medical School（波士顿儿童医院，哈佛医学院）；Center for Brains, Minds, and Machines（大脑、心智与机器中心）；Edmond and Lily Safra Center for Brain Sciences, Hebrew University（埃德蒙与莉莉·萨弗脑科学中心，希伯来大学）
Applied Artificial Intelligence Institute, Deakin University（迪肯大学应用人工智能学院）
We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains with applications in visual question answering. Relaxing the common assumption made by current models that the object predicates pre-exist and stay static, passive to the reasoning process, we propose that these dynamic predicates expand across the domain borders to include pair-wise visual-linguistic object binding. In our method, these contextualized object links are actively found within each recurrent reasoning step without relying on…
Despite the impressive progress achieved in robotic grasping, robots are not skilled in sophisticated tasks (e.g. search and grasp a specified target in clutter). Such tasks involve not only grasping but the comprehensive perception of the world (e.g. the object relationships). Recently, encouraging results demonstrate that it is possible to understand high-level concepts by learning. However, such algorithms are usually data-intensive, and the lack of data severely limits their performance. In this paper, we present a new dataset named REGRAD for the learning of relationships among objects an…
Generalization of CNNs on Relational Reasoning with Bar Charts
School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）；State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）；School of Information, Renmin University of China（中国人民大学信息学院）；College of Science and Mathematics, University of Massachusetts Boston（马萨诸塞大学波士顿分校科学与数学学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Heuritech（赫瑞泰克公司）；Conservatoire National des Arts et Métiers（法国国立工艺学院）
Multimodal attentional networks are currently state-of-the-art models for Visual Question Answering (VQA) tasks involving real images. Although attention allows to focus on the visual content relevant to the question, this simple mechanism is arguably insufficient to model complex reasoning features required for VQA or other high-level tasks. In this paper, we propose MuRel, a multimodal relational network which is learned end-to-end to reason over real images. Our first contribution is the introduction of the MuRel cell, an atomic reasoning primitive representing interactions between question…
ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；School of Engineering, Westlake University（西湖大学工程学院）；University of Minnesota – Twin Cities（明尼苏达大学双城分校）；University of Toronto（多伦多大学）
Singulos Research Inc.（Singulos研究公司）；University of British Columbia（不列颠哥伦比亚大学）
Augmented and Mixed Reality are emerging as likely successors to the mobile internet. However, many technical challenges remain. One of the key requirements of these systems is the ability to create a continuity between physical and virtual worlds, with the user's visual perception as the primary interface medium. Building this continuity requires the system to develop a visual understanding of the physical world. While there has been significant recent progress in computer vision and AI techniques such as image classification and object detection, success in these areas has not yet led to the…
