相关论文: Access Control of Semantic Segmentation Models Usi…

Despite significant advancements in computer vision, semantic segmentation models may be susceptible to backdoor attacks. These attacks, involving hidden triggers, aim to cause the models to misclassify instances of the victim class as the…

Most machine vision tasks (e.g., semantic segmentation) are based on images encoded and decoded by image compression algorithms (e.g., JPEG). However, these decoded images in the pixel domain introduce distortion, and they are optimized for…

In this paper, we propose a model protection method by using block-wise pixel shuffling with a secret key as a preprocessing technique to input images for the first time. The protected model is built by training with such preprocessed…

Semantic segmentation is the problem of assigning a class label to every pixel in an image, and is an important component of an autonomous vehicle vision stack for facilitating scene understanding and object detection. However, many of the…

With the widespread adoption of edge computing technologies and the increasing prevalence of deep learning models in these environments, the security risks and privacy threats to models and data have grown more acute. Attackers can exploit…

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…

Personal and home sensors generate valuable information that could be used in Smart Cities. Unfortunately, typically, this data is locked out and used only by application/system developer. While vendors are to blame, one should consider…

Semantic segmentation has achieved remarkable progress but remains challenging due to the complex scene, object occlusion, and so on. Some research works have attempted to use extra information such as a depth map to help RGB based semantic…

Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be…

Semantic segmentation is one of the most challenging tasks in computer vision. However, in many applications, a frequent obstacle is the lack of labeled images, due to the high cost of pixel-level labeling. In this scenario, it makes sense…

Image segmentation is important in medical imaging, providing valuable, quantitative information for clinical decision-making in diagnosis, therapy, and intervention. The state-of-the-art in automated segmentation remains supervised…

Recently, learned image compression has attracted considerable attention due to its superior performance over traditional methods. However, most existing approaches employ a single entropy model to estimate the probability distribution of…

SpanKey is a lightweight way to gate inference without encrypting weights or chasing leaderboard accuracy on gated inference. The idea is to condition activations on secret keys. A basis matrix $B$ defines a low-dimensional key subspace…

Introducing explicit constraints on the structural predictions has been an effective way to improve the performance of semantic segmentation models. Existing methods are mainly based on insufficient hand-crafted rules that only partially…

State-of-the-art approaches for semantic segmentation rely on deep convolutional neural networks trained on fully annotated datasets, that have been shown to be notoriously expensive to collect, both in terms of time and money. To remedy…

In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies…

Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for building high-performance deep learning methods. Most existing…

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as…

Large-scale datasets play a fundamental role in training deep learning models. However, dataset collection is difficult in domains that involve sensitive information. Collaborative learning techniques provide a privacy-preserving solution,…

Semantic segmentation is an important and popular research area in computer vision that focuses on classifying pixels in an image based on their semantics. However, supervised deep learning requires large amounts of data to train models and…