arXiv subjects

Yinan Yu

Publications and source records attributed to Yinan Yu.

34 records · Page 2Linked to original sources

arXiv2024

LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks

Today's Large Language Models (LLMs) have showcased exemplary capabilities, ranging from simple text generation to advanced image processing. Such models are currently being explored for in-vehicle services such as supporting perception tasks in Advanced Driver Assistance Systems (ADAS) or Autonomous Driving (AD) systems, given the LLMs' capabilities to process multi-modal data. However, LLMs often generate nonsensical or unfaithful information, known as ``hallucinations'': a notable issue that needs to be mitigated. In this paper, we systematically explore the adoption of SelfCheckGPT to spot hallucinations by three state-of-the-art LLMs (GPT-4o, LLaVA, and Llama3) when analysing visual automotive data from two sources: Waymo Open Dataset, from the US, and PREPER CITY dataset, from Sweden. Our results show that GPT-4o is better at generating faithful image captions than LLaVA, whereas the former demonstrated leniency in mislabeling non-hallucinated content as hallucinations compared to the latter. Furthermore, the analysis of the performance metrics revealed that the dataset type (Waymo or PREPER CITY) did not significantly affect the quality of the captions or the effectiveness of hallucination detection. However, the models showed better performance rates over images captured during daytime, compared to during dawn, dusk or night. Overall, the results show that SelfCheckGPT and its adaptation can be used to filter hallucinations in generated traffic-related image captions for state-of-the-art LLMs.

cs.CV↗

arXiv2024

Domain Generalization through Meta-Learning: A Survey

Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution (OOD) data, a common scenario due to the inevitable domain shifts in real-world applications. This limitation stems from the common assumption that training and testing data share the same distribution--an assumption frequently violated in practice. Despite their effectiveness with large amounts of data and computational power, DNNs struggle with distributional shifts and limited labeled data, leading to overfitting and poor generalization across various tasks and domains. Meta-learning presents a promising approach by employing algorithms that acquire transferable knowledge across various tasks for fast adaptation, eliminating the need to learn each task from scratch. This survey paper delves into the realm of meta-learning with a focus on its contribution to domain generalization. We first clarify the concept of meta-learning for domain generalization and introduce a novel taxonomy based on the feature extraction strategy and the classifier learning methodology, offering a granular view of methodologies. Additionally, we present a decision graph to assist readers in navigating the taxonomy based on data availability and domain shifts, enabling them to select and develop a proper model tailored to their specific problem requirements. Through an exhaustive review of existing methods and underlying theories, we map out the fundamentals of the field. Our survey provides practical insights and an informed discussion on promising research directions.

cs.LG↗

arXiv2024

Tapping in a Remote Vehicle's onboard LLM to Complement the Ego Vehicle's Field-of-View

Today's advanced automotive systems are turning into intelligent Cyber-Physical Systems (CPS), bringing computational intelligence to their cyber-physical context. Such systems power advanced driver assistance systems (ADAS) that observe a vehicle's surroundings for their functionality. However, such ADAS have clear limitations in scenarios when the direct line-of-sight to surrounding objects is occluded, like in urban areas. Imagine now automated driving (AD) systems that ideally could benefit from other vehicles' field-of-view in such occluded situations to increase traffic safety if, for example, locations about pedestrians can be shared across vehicles. Current literature suggests vehicle-to-infrastructure (V2I) via roadside units (RSUs) or vehicle-to-vehicle (V2V) communication to address such issues that stream sensor or object data between vehicles. When considering the ongoing revolution in vehicle system architectures towards powerful, centralized processing units with hardware accelerators, foreseeing the onboard presence of large language models (LLMs) to improve the passengers' comfort when using voice assistants becomes a reality. We are suggesting and evaluating a concept to complement the ego vehicle's field-of-view (FOV) with another vehicle's FOV by tapping into their onboard LLM to let the machines have a dialogue about what the other vehicle ``sees''. Our results show that very recent versions of LLMs, such as GPT-4V and GPT-4o, understand a traffic situation to an impressive level of detail, and hence, they can be used even to spot traffic participants. However, better prompts are needed to improve the detection quality and future work is needed towards a standardised message interchange format between vehicles.

cs.CV↗

arXiv2024

Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks

Today's advanced driver assistance systems (ADAS), like adaptive cruise control or rear collision warning, are finding broader adoption across vehicle classes. Integrating such advanced, multimodal Large Language Models (LLMs) on board a vehicle, which are capable of processing text, images, audio, and other data types, may have the potential to greatly enhance passenger comfort. Yet, an LLM's hallucinations are still a major challenge to be addressed. In this paper, we systematically assessed potential hallucination detection strategies for such LLMs in the context of object detection in vision-based data on the example of pedestrian detection and localization. We evaluate three hallucination detection strategies applied to two state-of-the-art LLMs, the proprietary GPT-4V and the open LLaVA, on two datasets (Waymo/US and PREPER CITY/Sweden). Our results show that these LLMs can describe a traffic situation to an impressive level of detail but are still challenged for further analysis activities such as object localization. We evaluate and extend hallucination detection approaches when applying these LLMs to video sequences in the example of pedestrian detection. Our experiments show that, at the moment, the state-of-the-art proprietary LLM performs much better than the open LLM. Furthermore, consistency enhancement techniques based on voting, such as the Best-of-Three (BO3) method, do not effectively reduce hallucinations in LLMs that tend to exhibit high false negatives in detecting pedestrians. However, extending the hallucination detection by including information from the past helps to improve results.

cs.CV↗

arXiv2024

Semantic-Aware Representation of Multi-Modal Data for Data Ingress: A Literature Review

Machine Learning (ML) is continuously permeating a growing amount of application domains. Generative AI such as Large Language Models (LLMs) also sees broad adoption to process multi-modal data such as text, images, audio, and video. While the trend is to use ever-larger datasets for training, managing this data efficiently has become a significant practical challenge in the industry-double as much data is certainly not double as good. Rather the opposite is important since getting an understanding of the inherent quality and diversity of the underlying data lakes is a growing challenge for application-specific ML as well as for fine-tuning foundation models. Furthermore, information retrieval (IR) from expanding data lakes is complicated by the temporal dimension inherent in time-series data which must be considered to determine its semantic value. This study focuses on the different semantic-aware techniques to extract embeddings from mono-modal, multi-modal, and cross-modal data to enhance IR capabilities in a growing data lake. Articles were collected to summarize information about the state-of-the-art techniques focusing on applications of embedding for three different categories of data modalities.

cs.LG↗

arXiv2024

AirDnD -- Asynchronous In-Range Dynamic and Distributed Network Orchestration Framework

The increasing usage of IoT devices has generated an extensive volume of data which resulted in the establishment of data centers with well-structured computing infrastructure. Reducing underutilized resources of such data centers can be achieved by monitoring the tasks and offloading them across various compute units. This approach can also be used in mini mobile data ponds generated by edge devices and smart vehicles. This research aims to improve and utilize the usage of computing resources in distributed edge devices by forming a dynamic mesh network. The nodes in the mesh network shall share their computing tasks with another node that possesses unused computing resources. This proposed method ensures the minimization of data transfer between entities. The proposed AirDnD vision will be applied to a practical scenario relevant to an autonomous vehicle that approaches an intersection commonly known as ``looking around the corner'' in related literature, collecting essential computational results from nearby vehicles to enhance its perception. The proposed solution consists of three models that transform growing amounts of geographically distributed edge devices into a living organism.

cs.SE↗

arXiv2024

Review Helpfulness Scores vs. Review Unhelpfulness Scores: Two Sides of the Same Coin or Different Coins?

Evaluating the helpfulness of online reviews supports consumers who must sift through large volumes of online reviews. Online review platforms have increasingly adopted review evaluating systems, which let users evaluate whether reviews are helpful or not; in turn, these evaluations assist review readers and encourage review contributors. Although review helpfulness scores have been studied extensively in the literature, our knowledge regarding their counterpart, review unhelpfulness scores, is lacking. Addressing this gap in the literature is important because researchers and practitioners have assumed that unhelpfulness scores are driven by intrinsic review characteristics and that such scores are associated with low-quality reviews. This study validates this conventional wisdom by examining factors that influence unhelpfulness scores. We find that, unlike review helpfulness scores, unhelpfulness scores are generally not driven by intrinsic review characteristics, as almost none of them are statistically significant predictors of an unhelpfulness score. We also find that users who receive review unhelpfulness votes are more likely to cast unhelpfulness votes for other reviews. Finally, unhelpfulness voters engage much less with the platform than helpfulness voters do. In summary, our findings suggest that review unhelpfulness scores are not driven by intrinsic review characteristics. Therefore, helpfulness and unhelpfulness scores should not be considered as two sides of the same coin.

cs.CY↗

arXiv2024

Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data

Computer vision models trained on Google Street View images can create material cadastres. However, current approaches need manually annotated datasets that are difficult to obtain and often have class imbalance. To address these challenges, this paper fine-tuned a Swin Transformer model on a synthetic dataset generated with DALL-E and compared the performance to a similar manually annotated dataset. Although manual annotation remains the gold standard, the synthetic dataset performance demonstrates a reasonable alternative. The findings will ease annotation needed to develop material cadastres, offering architects insights into opportunities for material reuse, thus contributing to the reduction of demolition waste.

cs.CV↗

arXiv2022

A Pre-study on Data Processing Pipelines for Roadside Object Detection Systems Towards Safer Road Infrastructure

Single-vehicle accidents are the most common type of fatal accidents in Sweden, where a car drives off the road and runs into hazardous roadside objects. Proper installation and maintenance of protective objects, such as crash cushions and guard rails, may reduce the chance and severity of such accidents. Moreover, efficient detection and management of hazardous roadside objects also plays an important role in improving road safety. To better understand the state-of-the-art and system requirements, in this pre-study, we investigate the feasibility, implementation, limitations and scaling up of data processing pipelines for roadside object detection. In particular, we divide our investigation into three parts: the target of interest, the sensors of choice and the algorithm design. The data sources we consider in this study cover two common setups: 1) road surveying fleet - annual scans conducted by Trafikverket, the Swedish Transport Administration, and 2) consumer vehicle - data collected using a research vehicle from the laboratory of Resource for vehicle research at Chalmers (REVERE). The goal of this report is to investigate how to implement a scalable roadside object detection system towards safe road infrastructure and Sweden's Vision Zero.

cs.CV↗

arXiv2022

Building Efficient CNNs Using Depthwise Convolutional Eigen-Filters (DeCEF)

Deep Convolutional Neural Networks (CNNs) have been widely used in various domains due to their impressive capabilities. These models are typically composed of a large number of 2D convolutional (Conv2D) layers with numerous trainable parameters. To reduce the complexity of a network, compression techniques can be applied. These methods typically rely on the analysis of trained deep learning models. However, in some applications, due to reasons such as particular data or system specifications and licensing restrictions, a pre-trained network may not be available. This would require the user to train a CNN from scratch. In this paper, we aim to find an alternative parameterization to Conv2D filters without relying on a pre-trained convolutional network. During the analysis, we observe that the effective rank of the vectorized Conv2D filters decreases with respect to the increasing depth in the network, which then leads to the implementation of the Depthwise Convolutional Eigen-Filter (DeCEF) layer. Essentially, a DeCEF layer is a low rank version of the Conv2D layer with significantly fewer trainable parameters and floating point operations (FLOPs). The way we define the effective rank is different from the previous work and it is easy to implement in any deep learning frameworks. To evaluate the effectiveness of DeCEF, experiments are conducted on the benchmark datasets CIFAR-10 and ImageNet using various network architectures. The results have shown a similar or higher accuracy and robustness using about 2/3 of the original parameters and reducing the number of FLOPs to 2/3 of the base network, which is then compared to the state-of-the-art techniques.

cs.LG↗

arXiv2019

Learning Hierarchical Feature Space Using CLAss-specific Subspace Multiple Kernel -- Metric Learning for Classification

Metric learning for classification has been intensively studied over the last decade. The idea is to learn a metric space induced from a normed vector space on which data from different classes are well separated. Different measures of the separation thus lead to various designs of the objective function in the metric learning model. One classical metric is the Mahalanobis distance, where a linear transformation matrix is designed and applied on the original dataset to obtain a new subspace equipped with the Euclidean norm. The kernelized version has also been developed, followed by Multiple-Kernel learning models. In this paper, we consider metric learning to be the identification of the best kernel function with respect to a high class separability in the corresponding metric space. The contribution is twofold: 1) No pairwise computations are required as in most metric learning techniques; 2) Better flexibility and lower computational complexity is achieved using the CLAss-Specific (Multiple) Kernel - Metric Learning (CLAS(M)K-ML). The proposed techniques can be considered as a preprocessing step to any kernel method or kernel approximation technique. An extension to a hierarchical learning structure is also proposed to further improve the classification performance, where on each layer, the CLASMK is computed based on a selected "marginal" subset and feature vectors are constructed by concatenating the features from all previous layers.

cs.LG↗

arXiv2019

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. We argue that treating these two sub-tasks separately is suboptimal. In fact, employing multiple separate modules significantly reduces the potential for application. The mutual benefits between the two complementary sub-tasks are also unexplored. To this end, this work proposes a single-shot proposal-free instance segmentation method that requires only one single pass for prediction. Our method is based on a pixel-pair affinity pyramid, which computes the probability that two pixels belong to the same instance in a hierarchical manner. The affinity pyramid can also be jointly learned with the semantic class labeling and achieve mutual benefits. Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine. Unlike previous time-consuming graph partition methods, this module achieves $5\times$ speedup and 9% relative improvement on Average-Precision (AP). Our approach achieves state-of-the-art results on the challenging Cityscapes dataset.

cs.CV↗

arXiv2018

Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making

Tactical driving decision making is crucial for autonomous driving systems and has attracted considerable interest in recent years. In this paper, we propose several practical components that can speed up deep reinforcement learning algorithms towards tactical decision making tasks: 1) non-uniform action skipping as a more stable alternative to action-repetition frame skipping, 2) a counter-based penalty for lanes on which ego vehicle has less right-of-road, and 3) heuristic inference-time action masking for apparently undesirable actions. We evaluate the proposed components in a realistic driving simulator and compare them with several baselines. Results show that the proposed scheme provides superior performance in terms of safety, efficiency, and comfort.

cs.AI↗

arXiv2016

Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation

Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera. Although those platforms do not have sensors for 3D depth sensing capability, knowledge of depth is an essential part in many robotics activities. Therefore, recently, there is an increasing interest in depth estimation using monocular images. As this task is inherently ambiguous, the data-driven estimated depth might be unreliable in robotics applications. In this paper, we have attempted to improve the precision of monocular depth estimation by introducing 2D planar observation from the remaining laser range finder without extra cost. Specifically, we construct a dense reference map from the sparse laser range data, redefining the depth estimation task as estimating the distance between the real and the reference depth. To solve the problem, we construct a novel residual of residual neural network, and tightly combine the classification and regression losses for continuous depth estimation. Experimental results suggest that our method achieves considerable promotion compared to the state-of-the-art methods on both NYUD2 and KITTI, validating the effectiveness of our method on leveraging the additional sensory information. We further demonstrate the potential usage of our method in obstacle avoidance where our methodology provides comprehensive depth information compared to the solution using monocular camera or 2D laser range finder alone.

cs.CV↗

arXiv2015

DenseBox: Unifying Landmark Localization with End to End Object Detection

How can a single fully convolutional neural network (FCN) perform on object detection? We introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding boxes and object class confidences through all locations and scales of an image. Our contribution is two-fold. First, we show that a single FCN, if designed and optimized carefully, can detect multiple different objects extremely accurately and efficiently. Second, we show that when incorporating with landmark localization during multi-task learning, DenseBox further improves object detection accuray. We present experimental results on public benchmark datasets including MALF face detection and KITTI car detection, that indicate our DenseBox is the state-of-the-art system for detecting challenging objects such as faces and cars.

cs.CV↗

arXiv2014

Arm locking for space-based laser interferometry gravitational wave observatories

Laser frequency stabilization is a critical part of the interferometry measurement system of space-based gravitational wave observatories such as the Laser Interferometer Space Antenna (LISA). Arm locking as a proposed frequency stabilization technique, transfers the stability of the long arm lengths to the laser frequency. The arm locking sensor synthesizes an adequately filtered linear combination of the inter-spacecraft phase measurements to estimate the laser frequency noise, which can be used to control the laser frequency. At the University of Florida we developed the hardware-based University of Florida LISA Interferometer Simulator (UFLIS) to study and verify laser frequency noise reduction and suppression techniques under realistic LISA-like conditions. These conditions include the variable Doppler shifts between the spacecraft, LISA-like signal travel times, optical transponders, realistic laser frequency and timing noise. We review the different types of arm locking sensors and discuss their expected performance in LISA. The presented results are supported by results obtained during experimental studies of arm locking under relevant LISA-like conditions. We measured the noise suppression as well as initial transients and frequency pulling in the presence of Doppler frequency errors. This work has demonstrated the validity and \ feasibility of arm locking in LISA.

gr-qc↗