Related papers: CrackCLF: Automatic Pavement Crack Detection based…
The software inevitably encounters the crash, which will take developers a large amount of effort to find the fault causing the crash (short for crashing fault). Developing automatic methods to identify the residence of the crashing fault…
Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues -- their performance significantly deteriorates on clean…
Deep convolutional neural networks (CNN) have recently been shown in many computer vision and pattern recog- nition applications to outperform by a significant margin state- of-the-art solutions that use traditional hand-crafted features.…
Loop closure detection (LCD) is the key module in appearance based simultaneously localization and mapping (SLAM). However, in the real life, the appearance of visual inputs are usually affected by the illumination changes and texture…
Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…
Lane detection, the process of identifying lane markings as approximated curves, is widely used for lane departure warning and adaptive cruise control in autonomous vehicles. The popular pipeline that solves it in two steps -- feature…
The elaborate pavement performance prediction is an important premise of implementing preventive maintenance. Our survey reveals that in practice, the pavement performance is usually measured at segment-level, where an unique performance…
Conventional deep networks rely on one-way backpropagation that overlooks reconciling high-level predictions with lower-level representations. We propose \emph{Contextual Feedback Loops} (CFLs), a lightweight mechanism that re-injects…
Recent works on deep conditional random fields (CRF) have set new records on many vision tasks involving structured predictions. Here we propose a fully-connected deep continuous CRF model for both discrete and continuous labelling…
Lane detection is critical for autonomous driving and ad-vanced driver assistance systems (ADAS). While recent methods like CLRNet achieve strong performance, they struggle under adverse con-ditions such as extreme weather, illumination…
Deep learning has enabled significant advances in feedback-based channel coding, yet existing learned schemes remain fundamentally limited: they employ fixed block lengths, suffer degraded performance at high rates, and cannot fully exploit…
While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior for model safety analysis. For example, steering-based jailbreak attacks exploit this by…
Safety-critical corner cases, difficult to collect in the real world, are crucial for evaluating end-to-end autonomous driving. Adversarial interaction is an effective method to generate such safety-critical corner cases. While existing…
In the realm of practical fine-grained visual classification applications rooted in deep learning, a common scenario involves training a model using a pre-existing dataset. Subsequently, a new dataset becomes available, prompting the desire…
Traffic flow forecasting aims to predict future traffic flows based on the historical traffic conditions and the road network. It is an important problem in intelligent transportation systems, with a plethora of methods been proposed.…
The core component of most modern trackers is a discriminative classifier, tasked with distinguishing between the target and the surrounding environment. To cope with natural image changes, this classifier is typically trained with…
Geometric Representation Learning (GRL) aims to approximate the non-Euclidean topology of high-dimensional data through discrete graph structures, grounded in the manifold hypothesis. However, traditional static graph construction methods…
Human ability to recognize complex visual patterns arises through transformations performed by successive areas in the ventral visual cortex. Deep neural networks trained end-to-end for object recognition approach human capabilities, and…
The lane detection is a key problem to solve the division of derivable areas in unmanned driving, and the detection accuracy of lane lines plays an important role in the decision-making of vehicle driving. Scenes faced by vehicles in daily…
Loop closing is a crucial component in SLAM that helps eliminate accumulated errors through two main steps: loop detection and loop pose correction. The first step determines whether loop closing should be performed, while the second…