Related papers: Approximate Domain Unlearning for Vision-Language …

Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the…

Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting…

Despite significant progress in safety alignment, large language models (LLMs) remain susceptible to jailbreak attacks. Existing defense mechanisms have not fully deleted harmful knowledge in LLMs, which allows such attacks to bypass…

Deep neural networks (DNNs) remain challenged by distribution shifts in complex open-world domains like automated driving (AD): Robustness against yet unknown novel objects (semantic shift) or styles like lighting conditions (covariate…

The need to selectively and efficiently erase learned information from deep neural networks is becoming increasingly important for privacy, regulatory compliance, and adaptive system design. We introduce Graph-Propagated Projection…

In the domain of anomaly detection, methods often excel in either high-level semantic or low-level industrial benchmarks, rarely achieving cross-domain proficiency. Semantic anomalies are novelties that differ in meaning from the training…

In recent years, we have witnessed significant progress in emerging deep learning models, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs). These models have demonstrated promising results, indicating a new era of…

Previous works on vehicle Re-ID mainly focus on extracting global features and learning distance metrics. Because some vehicles commonly share same model and maker, it is hard to distinguish them based on their global appearances. Compared…

Domain generalization (DG) remains a significant challenge for perception based on deep neural networks (DNNs), where domain shifts occur due to synthetic data, lighting, weather, or location changes. Vision-language models (VLMs) marked a…

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to image-level anomaly detection and textual reasoning, while…

Image degradation is a prevalent issue in various real-world applications, affecting visual quality and downstream processing tasks. In this study, we propose a novel framework that employs a Vision-Language Model (VLM) to automatically…

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of…

Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual information received in real-time. Prior works have…

The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their generalization problem, where their performance drastically decreases when evaluated on examples that differ from the training dataset, known…

Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. However, current approaches are inherently limited to a…

With the increase in the learning capability of deep convolution-based architectures, various applications of such models have been proposed over time. In the field of anomaly detection, improvements in deep learning opened new prospects of…

The widespread popularization of vehicles has facilitated all people's life during the last decades. However, the emergence of a large number of vehicles poses the critical but challenging problem of vehicle re-identification (reID). Till…

In this paper, we address the problem of class-generalizable anomaly detection, where the objective is to develop a unified model by focusing our learning on the available normal data and a small amount of anomaly data in order to detect…

Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task and they are usually trained on a closed set of object classes appearing in a closed operational…

Despite the significant advancements represented by Vision-Language Models (VLMs), current architectures often exhibit limitations in retaining fine-grained visual information, leading to coarse-grained multimodal comprehension. We…