Related papers: A Hybrid Co-Finetuning Approach for Visual Bug Det…

Federated multi-view clustering offers the potential to develop a global clustering model using data distributed across multiple devices. However, current methods face challenges due to the absence of label information and the paramount…

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle…

It is a long-term goal to transfer biological processing principles as well as the power of human recognition into machine vision and engineering systems. One of such principles is visual attention, a smart human concept which focuses…

Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages…

Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional…

Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…

We address the problem of multi-modal object tracking in video and explore various options of fusing the complementary information conveyed by the visible (RGB) and thermal infrared (TIR) modalities including pixel-level, feature-level and…

Three key challenges hinder the development of current deepfake video detection: (1) Temporal features can be complex and diverse: how can we identify general temporal artifacts to enhance model generalization? (2) Spatiotemporal models…

Cross-modality fusing complementary information of multispectral remote sensing image pairs can improve the perception ability of detection algorithms, making them more robust and reliable for a wider range of applications, such as…

Automated visual inspection in the semiconductor industry aims to detect and classify manufacturing defects utilizing modern image processing techniques. While an earliest possible detection of defect patterns allows quality control and…

Generalist robot policies trained on large-scale, visually homogeneous datasets can be susceptible to shortcut learning, which impairs their out-of-distribution (OOD) generalization. While generative data augmentation is a common approach…

Deep neural networks have demonstrated remarkable performance in various vision tasks, but their success heavily depends on the quality of the training data. Noisy labels are a critical issue in medical datasets and can significantly…

Adapting pre-trained models to unseen feature modalities has become increasingly important due to the growing need for cross-disciplinary knowledge integration. A key challenge here is how to align the representation of new modalities with…

We present a deep learning system for testing graphics units by detecting novel visual corruptions in videos. Unlike previous work in which manual tagging was required to collect labeled training data, our weak supervision method is fully…

This paper addresses the critical challenge of unlearning in Vertical Federated Learning (VFL), a setting that has received far less attention than its horizontal counterpart. Specifically, we propose the first method tailored to…

Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of pre-trained vision-language models (e.g., CLIP). However, we find that both…

Concurrency bugs, caused by improper synchronization of shared resources in multi-threaded or distributed systems, are notoriously hard to detect and thus compromise software reliability and security. The existing deep learning methods face…

Edge detection remains a fundamental yet challenging task in computer vision, especially under varying illumination, noise, and complex scene conditions. This paper introduces a Hybrid Multi-Stage Learning Framework that integrates…

Videos are inherently multimodal. This paper studies the problem of how to fully exploit the abundant multimodal clues for improved video categorization. We introduce a hybrid deep learning framework that integrates useful clues from…

One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types. This work considers the unknown fault detection capabilities of deep neural network-based…