Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in obvious cases, especially due to the modality bias learned from statistically biased datasets. From these problems, we anticipate that maybe understanding the complementary information itself is difficult to achieve from vision-only models. Accordingly, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework, which incorporates Large Language Models (LLMs) to understand the complementary information at the semantic level and further enhance the fusion process. Specifically, we generate text descriptions of the pedestrian in each RGB and thermal modality and design a Multispectral Chain-of-Thought (MSCoT) prompting, which models a step-by-step process to facilitate cross-modal reasoning at the semantic level and perform accurate detection. Moreover, we design a Language-driven Multi-modal Fusion (LMF) strategy that enables fusing vision-driven and language-driven detections. Extensive experiments validate that MSCoTDet improves multispectral pedestrian detection.
相關內容
Distributed approaches have many computational benefits, but they are vulnerable to attacks from a subset of devices transmitting incorrect information. This paper investigates Byzantine-resilient algorithms in a decentralized setting, where devices communicate directly with one another. We leverage the so-called dual approach to design a general robust decentralized optimization method. We provide both global and local clipping rules in the special case of average consensus, with tight convergence guarantees. These clipping rules are practical, and yield results that finely characterize the impact of Byzantine nodes, highlighting for instance a qualitative difference in convergence between global and local clipping thresholds. Lastly, we demonstrate that they can serve as a basis for designing efficient attacks.
Writing declarative models has numerous benefits, ranging from automated reasoning and correction of design-level properties before systems are built to automated testing and debugging of their implementations after they are built. Unfortunately, the model itself needs to be correct to gain these benefits. Alloy is a commonly used modeling language that has several existing efforts to repair faulty models automatically. Currently, these efforts are search-based methods that use an Abstract Syntax Tree (AST) representation of the model and do not scale. One issue is that ASTs themselves suffer from exponential growth in their data size due to the limitation that ASTs will often have identical nodes separately listed in the tree. To address this issue, we introduce a novel code representation schema, Complex Structurally Balanced Abstract Semantic Graph (CSBASG), which represents code as a complex-weighted directed graph that lists a semantic element as a node in the graph and ensures its structural balance for almost finitely enumerable code segments. We evaluate the efficiency of our CSBASG representation for Alloy models in terms of it's compactness compared to ASTs, and we explore if a CSBASG can ease the process of comparing two Alloy predicates. Moreover, with this representation in place, we identify several future applications of CSBASG, including Alloy code generation and automated repair.
The cold-start problem is a long-standing challenge in recommender systems due to the lack of user-item interactions, which significantly hurts the recommendation effect over new users and items. Recently, meta-learning based methods attempt to learn globally shared prior knowledge across all users, which can be rapidly adapted to new users and items with very few interactions. Though with significant performance improvement, the globally shared parameter may lead to local optimum. Besides, they are oblivious to the inherent information and feature interactions existing in the new users and items, which are critical in cold-start scenarios. In this paper, we propose a Task aligned Meta-learning based Augmented Graph (TMAG) to address cold-start recommendation. Specifically, a fine-grained task aligned constructor is proposed to cluster similar users and divide tasks for meta-learning, enabling consistent optimization direction. Besides, an augmented graph neural network with two graph enhanced approaches is designed to alleviate data sparsity and capture the high-order user-item interactions. We validate our approach on three real-world datasets in various cold-start scenarios, showing the superiority of TMAG over state-of-the-art methods for cold-start recommendation.
Autonomous robots for gathering information on objects of interest has numerous real-world applications because of they improve efficiency, performance and safety. Realizing autonomy demands online planning algorithms to solve sequential decision making problems under uncertainty; because, objects of interest are often dynamic, object state, such as location is not directly observable and are obtained from noisy measurements. Such planning problems are notoriously difficult due to the combinatorial nature of predicting the future to make optimal decisions. For information theoretic planning algorithms, we develop a computationally efficient and effective approximation for the difficult problem of predicting the likely sensor measurements from uncertain belief states}. The approach more accurately predicts information gain from information gathering actions. Our theoretical analysis proves the proposed formulation achieves a lower prediction error than the current efficient-method. We demonstrate improved performance gains in radio-source tracking and localization problems using extensive simulated and field experiments with a multirotor aerial robot.
Deterministic and nondeterministic finite automata (DFAs and NFAs) are abstract models of computation commonly taught in introductory computing theory courses. These models have important applications (such as fast regular expression matching), and are used to introduce formal language theory. Undergraduate students often struggle with understanding these models at first, due to the level of abstraction. As a result, various pedagogical tools have been developed to allow students to practice with these models. We introduce the FSM Builder, a new pedagogical tool enabling students to practice constructing DFAs and NFAs with a graphical editor, giving personalized feedback and partial credit. The algorithms used for generating these are heavily inspired by previous works. The key advantages to its competitors are greater flexibility and scalability. This is because the FSM Builder is implemented using efficient algorithms from an open source package, allowing for easy extension and question creation. We discuss the implementation of the tool, how it stands out from previous tools, and takeaways from experiences of using the tool in multiple large courses. Survey results indicate the interface and feedback provided by the tool were useful to students.
Software vulnerability detection is generally supported by automated static analysis tools, which have recently been reinforced by deep learning (DL) models. However, despite the superior performance of DL-based approaches over rule-based ones in research, applying DL approaches to software vulnerability detection in practice remains a challenge due to the complex structure of source code, the black-box nature of DL, and the domain knowledge required to understand and validate the black-box results for addressing tasks after detection. Conventional DL models are trained by specific projects and, hence, excel in identifying vulnerabilities in these projects but not in others. These models with poor performance in vulnerability detection would impact the downstream tasks such as location and repair. More importantly, these models do not provide explanations for developers to comprehend detection results. In contrast, Large Language Models (LLMs) have made lots of progress in addressing these issues by leveraging prompting techniques. Unfortunately, their performance in identifying vulnerabilities is unsatisfactory. This paper contributes \textbf{\DLAP}, a \underline{\textbf{D}}eep \underline{\textbf{L}}earning \underline{\textbf{A}}ugmented LLMs \underline{\textbf{P}}rompting framework that combines the best of both DL models and LLMs to achieve exceptional vulnerability detection performance. Experimental evaluation results confirm that \DLAP outperforms state-of-the-art prompting frameworks, including role-based prompts, auxiliary information prompts, chain-of-thought prompts, and in-context learning prompts, as well as fine-turning on multiple metrics.
Multi-modal 3D scene understanding has gained considerable attention due to its wide applications in many areas, such as autonomous driving and human-computer interaction. Compared to conventional single-modal 3D understanding, introducing an additional modality not only elevates the richness and precision of scene interpretation but also ensures a more robust and resilient understanding. This becomes especially crucial in varied and challenging environments where solely relying on 3D data might be inadequate. While there has been a surge in the development of multi-modal 3D methods over past three years, especially those integrating multi-camera images (3D+2D) and textual descriptions (3D+language), a comprehensive and in-depth review is notably absent. In this article, we present a systematic survey of recent progress to bridge this gap. We begin by briefly introducing a background that formally defines various 3D multi-modal tasks and summarizes their inherent challenges. After that, we present a novel taxonomy that delivers a thorough categorization of existing methods according to modalities and tasks, exploring their respective strengths and limitations. Furthermore, comparative results of recent approaches on several benchmark datasets, together with insightful analysis, are offered. Finally, we discuss the unresolved issues and provide several potential avenues for future research.
Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers. However, achieving a rather good performance is not an easy task due to the noisy raw data, underutilized information, and the misalignment of multi-modal sensors. In this paper, we provide a literature review of the existing multi-modal-based methods for perception tasks in autonomous driving. Generally, we make a detailed analysis including over 50 papers leveraging perception sensors including LiDAR and camera trying to solve object detection and semantic segmentation tasks. Different from traditional fusion methodology for categorizing fusion models, we propose an innovative way that divides them into two major classes, four minor classes by a more reasonable taxonomy in the view of the fusion stage. Moreover, we dive deep into the current fusion methods, focusing on the remaining problems and open-up discussions on the potential research opportunities. In conclusion, what we expect to do in this paper is to present a new taxonomy of multi-modal fusion methods for the autonomous driving perception tasks and provoke thoughts of the fusion-based techniques in the future.
Visual information extraction (VIE) has attracted considerable attention recently owing to its various advanced applications such as document understanding, automatic marking and intelligent education. Most existing works decoupled this problem into several independent sub-tasks of text spotting (text detection and recognition) and information extraction, which completely ignored the high correlation among them during optimization. In this paper, we propose a robust visual information extraction system (VIES) towards real-world scenarios, which is a unified end-to-end trainable framework for simultaneous text detection, recognition and information extraction by taking a single document image as input and outputting the structured information. Specifically, the information extraction branch collects abundant visual and semantic representations from text spotting for multimodal feature fusion and conversely, provides higher-level semantic clues to contribute to the optimization of text spotting. Moreover, regarding the shortage of public benchmarks, we construct a fully-annotated dataset called EPHOIE (//github.com/HCIILAB/EPHOIE), which is the first Chinese benchmark for both text spotting and visual information extraction. EPHOIE consists of 1,494 images of examination paper head with complex layouts and background, including a total of 15,771 Chinese handwritten or printed text instances. Compared with the state-of-the-art methods, our VIES shows significant superior performance on the EPHOIE dataset and achieves a 9.01% F-score gain on the widely used SROIE dataset under the end-to-end scenario.
Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: //github.com/JDAI-CV/LIO.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191