A mixture of multivariate Poisson-log normal factor analyzers is introduced by imposing constraints on the covariance matrix, which resulted in flexible models for clustering purposes. In particular, a class of eight parsimonious mixture models based on the mixtures of factor analyzers model are introduced. Variational Gaussian approximation is used for parameter estimation, and information criteria are used for model selection. The proposed models are explored in the context of clustering discrete data arising from RNA sequencing studies. Using real and simulated data, the models are shown to give favourable clustering performance. The GitHub R package for this work is available at https://github.com/anjalisilva/mixMPLNFA and is released under the open-source MIT license.
Multi-modal large language models (LLM) have achieved powerful capabilities for visual semantic understanding in recent years. However, little is known about how LLMs comprehend visual information and interpret different modalities of features. In this paper, we propose a new method for identifying multi-modal neurons in transformer-based multi-modal LLMs. Through a series of experiments, We highlight three critical properties of multi-modal neurons by four well-designed quantitative evaluation metrics. Furthermore, we introduce a knowledge editing method based on the identified multi-modal neurons, for modifying a specific token to another designative token. We hope our findings can inspire further explanatory researches on understanding mechanisms of multi-modal LLMs.
Due to the frequent variability of object orientation, accurate prediction of orientation information remains a challenge in oriented object detection. To better extract orientation-related information, current methods primarily focus on the design of reasonable representations of oriented bounding box (OBB) and rotation-sensitive feature extraction. However, existing OBB representations often suffer from boundary discontinuity and representation ambiguity problems. Methods of designing continuous and unambiguous regression losses do not essentially solve such problems. Gaussian bounding box (GBB) avoids these OBB representation problems, but directly regressing GBB is susceptible to numerical instability. In this paper, we propose linear GBB (LGBB), a novel OBB representation. By linearly transforming the elements of GBB, LGBB does not have the boundary discontinuity and representation ambiguity problems, and have high numerical stability. On the other hand, current rotation-sensitive feature extraction methods based on convolutions can only extract features under a local receptive field, which is slow in aggregating rotation-sensitive features. To address this issue, we propose ring-shaped rotated convolution (RRC). By adaptively rotating feature maps to arbitrary orientations, RRC extracts rotation-sensitive features under a ring-shaped receptive field, rapidly aggregating rotation-sensitive features and contextual information. RRC can be applied to various models in a plug-and-play manner. Experimental results demonstrate that the proposed LGBB and RRC are effective and achieve state-of-the-art (SOTA) performance. By integrating LGBB and RRC into various models, the detection accuracy is effectively improved on DOTA and HRSC2016 datasets.
We study real-time tracking problem in an energy harvesting system with a Markov source under an imperfect channel. We consider both sampling and transmission costs and different from most prior studies that assume the source is fully observable, the sampling cost renders the source unobservable. The goal is to jointly optimize sampling and transmission policies for three semantic-aware metrics: i) the age of information (AoI), ii) general distortion, and iii) the age of incorrect information (AoII). To this end, we formulate and solve a stochastic control problem. Specifically, for the AoI metric, we cast a Markov decision process (MDP) problem and solve it using relative value iteration (RVI). For the distortion and AoII metrics, we utilize the partially observable MDP (POMDP) modeling and leverage the notion of belief MDP formulation of POMDP to find optimal policies. For the distortion metric and the AoII metric under the perfect channel setup, we effectively truncate the corresponding belief space and solve an MDP problem using RVI. For the general setup, a deep reinforcement learning policy is proposed. Through simulations, we demonstrate significant performance improvements achieved by the derived policies. The results reveal various switching-type structures of optimal policies and show that a distortion-optimal policy is also AoII optimal.
Anomaly detection is a crucial task across different domains and data types. However, existing anomaly detection models are often designed for specific domains and modalities. This study explores the use of GPT-4V(ision), a powerful visual-linguistic model, to address anomaly detection tasks in a generic manner. We investigate the application of GPT-4V in multi-modality, multi-domain anomaly detection tasks, including image, video, point cloud, and time series data, across multiple application areas, such as industrial, medical, logical, video, 3D anomaly detection, and localization tasks. To enhance GPT-4V's performance, we incorporate different kinds of additional cues such as class information, human expertise, and reference images as prompts.Based on our experiments, GPT-4V proves to be highly effective in detecting and explaining global and fine-grained semantic patterns in zero/one-shot anomaly detection. This enables accurate differentiation between normal and abnormal instances. Although we conducted extensive evaluations in this study, there is still room for future evaluation to further exploit GPT-4V's generic anomaly detection capacity from different aspects. These include exploring quantitative metrics, expanding evaluation benchmarks, incorporating multi-round interactions, and incorporating human feedback loops. Nevertheless, GPT-4V exhibits promising performance in generic anomaly detection and understanding, thus opening up a new avenue for anomaly detection.
Autonomous vehicle refers to a vehicle capable of perceiving its surrounding environment and driving with little or no human driver input. The perception system is a fundamental component which enables the autonomous vehicle to collect data and extract relevant information from the environment to drive safely. Benefit from the recent advances in computer vision, the perception task can be achieved by using sensors, such as camera, LiDAR, radar, and ultrasonic sensor. This paper reviews publications on computer vision and autonomous driving that are published during the last ten years. In particular, we first investigate the development of autonomous driving systems and summarize these systems that are developed by the major automotive manufacturers from different countries. Second, we investigate the sensors and benchmark data sets that are commonly utilized for autonomous driving. Then, a comprehensive overview of computer vision applications for autonomous driving such as depth estimation, object detection, lane detection, and traffic sign recognition are discussed. Additionally, we review public opinions and concerns on autonomous vehicles. Based on the discussion, we analyze the current technological challenges that autonomous vehicles meet with. Finally, we present our insights and point out some promising directions for future research. This paper will help the reader to understand autonomous vehicles from the perspectives of academia and industry.
Vertebral detection and segmentation are critical steps for treatment planning in spine surgery and radiation therapy. Accurate identification and segmentation are complicated in imaging that does not include the full spine, in cases with variations in anatomy (T13 and/or L6 vertebrae), and in the presence of fracture or hardware. This paper proposes VertDetect, a fully automated end-to-end 3D vertebral instance segmentation Convolutional Neural Network (CNN) model to predict vertebral level labels and segmentations for all vertebrae present in a CT scan. The utilization of a shared CNN backbone provides the detection and segmentation branches of the network with feature maps containing both spinal and vertebral level information. A Graph Convolutional Network (GCN) layer is used to improve vertebral labelling by using the known structure of the spine. This model achieved a Dice Similarity Coefficient (DSC) of 0.883 (95% CI, 0.843-0.906) and 0.882 (95% CI, 0.835-0.909) in the VerSe 2019 and 0.868 (95\% CI, 0.834-0.890) and 0.869 (95\% CI, 0.832-0.891) in the VerSe 2020 public and hidden test sets, respectively. This model achieved state-of-the-art performance for an end-to-end architecture, whose design facilitates the extraction of features that can be subsequently used for downstream tasks.
Large Language Models (LLMs) often struggle when faced with situations where they lack the prerequisite knowledge to generate a sensical response. In these cases, models tend to fabricate and hallucinate, rather than appropriately signaling uncertainty as humans would. This behavior misaligns with human conversational norms and presents challenges surrounding responsible and ethical AI development. This work aims to systematically investigate LLMs' behaviors in such situations. We curate an adversarial question-answering benchmark containing unanswerable questions targeting information absent from the LLM's training data. Concretely, these unanswerable questions contain non-existent concepts or false premises. When presented with such unanswerable questions, an LLM should appropriately convey uncertainty, and be able to challenge the premise and refuse to generate a response. While facing answerable valid questions, a model should demonstrate a positive correlation between accuracy and confidence. Using a model-agnostic unified confidence elicitation approach, we observe that LLMs that have gone through instruction finetuning and reinforcement learning from human feedback (RLHF) perform significantly better than their counterparts that do not. Moreover, uncertainty expression 1 through our elicitation method does not always stay consistent with the perceived confidence of the direct response of an LLM. Our findings call for further research into teaching LLMs to proactively and reliably express uncertainty.
This paper presents a promising design concept for reconfigurable intelligent surfaces (RISs), named plug-in RIS, wherein the RIS is plugged into an appropriate position in the environment, adjusted once according to the location of both base station and blocked region, and operates with fixed beams to enhance the system performance. The plug-in RIS is a novel system design, streamlining RIS-assisted millimeter-wave (mmWave) communication without requiring decoupling two parts of the end-to-end channel, traditional control signal transmission, and online RIS configuration. In plug-in RIS-aided transmission, the transmitter efficiently activates specific regions of the divided large RIS by employing hybrid beamforming techniques, each with predetermined phase adjustments tailored to reflect signals to desired user locations. This user-centric approach enhances connectivity and overall user experience by dynamically illuminating the targeted user based on location. By introducing plug-in RIS's theoretical framework, design principles, and performance evaluation, we demonstrate its potential to revolutionize mmWave communications in limited channel state information (CSI) scenarios. Simulation results illustrate that plug-in RIS provides power/cost-efficient solutions to overcome blockage in the mmWave communication system and a striking convergence in average bit error rate and achievable rate performance with traditional full CSI-enabled RIS solutions.
Large language models (LLMs) have demonstrated impressive reasoning ability in various language-based tasks. Despite many proposed reasoning methods aimed at enhancing performance in downstream tasks, two fundamental questions persist: Does reasoning genuinely support predictions, and how reliable is the quality of reasoning? In this paper, we propose a framework \textsc{SCORE} to analyze how well LLMs can reason. Specifically, we focus on self-contradictory reasoning, where reasoning does not support the prediction. We find that LLMs often contradict themselves when performing reasoning tasks that involve contextual information and commonsense. The model may miss evidence or use shortcuts, thereby exhibiting self-contradictory behaviors. We also employ the Point-of-View (POV) method, which probes models to generate reasoning from multiple perspectives, as a diagnostic tool for further analysis. We find that though LLMs may appear to perform well in one-perspective settings, they fail to stabilize such behavior in multi-perspectives settings. Even for correct predictions, the reasoning may be messy and incomplete, and LLMs can easily be led astray from good reasoning. \textsc{SCORE}'s results underscore the lack of robustness required for trustworthy reasoning and the urgency for further research to establish best practices for a comprehensive evaluation of reasoning beyond accuracy-based metrics.