Out-of-distribution (OOD) detection is essential to ensure the reliability and robustness of machine learning models in real-world applications. Post-hoc OOD detection methods have gained significant attention due to ...
Out-of-distribution (OOD) detection is essential to ensure the reliability and robustness of machine learning models in real-world applications. Post-hoc OOD detection methods have gained significant attention due to the fact that they offer the advantage of not requiring additional re-training, which could degrade model performance and increase training time. However, most existing post-hoc methods rely only on the encoder output (features), logits, or the softmax probability, meaning they have no access to information that might be lost in the feature extraction process. In this work, we address this limitation by introducing Adaptive Temperature Scaling (ATS), a novel approach that dynamically calculates a temperature value based on activations of the intermediate layers. Fusing this sample-specific adjustment with class-dependent logits, our ATS captures additional statistical information before they are lost in the feature extraction process, leading to a more robust and powerful OOD detection method. We conduct extensive experiments to demonstrate the efficacy of our approach. Notably, our method can be seamlessly combined with SOTA post-hoc OOD detection methods that rely on the logits, thereby enhancing their performance and improving their robustness.
In recent years, the rise in both natural and man-made disasters, along with armed conflicts and terrorist threats, has elevated the demand for Search and Rescue (SAR) missions worldwide. This paper underscores the cr...
详细信息
ISBN:
(数字)9798350348811
ISBN:
(纸本)9798350348828
In recent years, the rise in both natural and man-made disasters, along with armed conflicts and terrorist threats, has elevated the demand for Search and Rescue (SAR) missions worldwide. This paper underscores the critical necessity to enhance SAR capacity, safety, and capabilities, with a primary goal of reducing response times through the integration of robots into SAR operations. The examination of research on robotized SAR highlights deficiencies in both software and hardware, particularly focusing on perception systems for robotized SAR platforms.
A better understanding of interactive pedestrian behavior in critical traffic situations is essential for the development of enhanced pedestrian safety systems. Real-world traffic observations play a decisive role in ...
详细信息
Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against adversarial attacks without prior tra...
Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against adversarial attacks without prior training on adversarial samples. We propose a test-time adversarial example detector which detects the input adversarial example through quantifying the localized intermediate responses of a pretrained neural network and confidence scores of an auxiliary softmax layer. Furthermore, in order to make the network robust, we extenuate the non-relevant features by non-iterative input sample clipping. Using our approach, mean performance over 15 levels of adversarial perturbations is increased by 53.3% for the fast gradient sign method and 60.9% for both the basic iterative method and the projected gradient method when compared to adversarial training.
Medical image segmentation plays an important role in accurately identifying and isolating regions of interest within medical images. Generative approaches are particularly effective in modeling the statistical proper...
详细信息
We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features. The core idea of our work is to leverage recent progr...
详细信息
Segmentation of cardiac magnetic resonance images (MRI) is crucial for the analysis and assessment of cardiac function, helping to diagnose and treat various cardiovascular diseases. Most recent techniques rely on dee...
详细信息
We present a novel diffusion-based approach to generate synthetic histopathological Whole Slide Images (WSIs) at an unprecedented gigapixel scale. Synthetic WSIs have many potential applications: They can augment trai...
We present a novel diffusion-based approach to generate synthetic histopathological Whole Slide Images (WSIs) at an unprecedented gigapixel scale. Synthetic WSIs have many potential applications: They can augment training datasets to enhance the performance of many computational pathology applications. They allow the creation of synthesized copies of datasets that can be shared without violating privacy regulations. Or they can facilitate learning representations of WSIs without requiring data annotations. Despite this variety of applications, no existing deep-learning-based method generates WSIs at their typically high resolutions. Mainly due to the high computational complexity. Therefore, we propose a novel coarse-to-fine sampling scheme to tackle image generation of high-resolution WSIs. In this scheme, we increase the resolution of an initial low-resolution image to a high-resolution WSI. Particularly, a diffusion model sequentially adds fine details to images and increases their resolution. In our experiments, we train our method with WSIs from the TCGA-BRCA dataset. Additionally to quantitative evaluations, we also performed a user study with pathologists. The study results suggest that our generated WSIs resemble the structure of real WSIs.
Deep learning techniques for anatomical landmark localization (ALL) have shown great success, but their reliance on large annotated datasets remains a problem due to the tedious and costly nature of medical data acqui...
详细信息
Traffic safety on highways is supported by a variety of technical measures, including countless camera systems that are often only monitored by human operators. However, due to the sheer amount of data, safety monitor...
Traffic safety on highways is supported by a variety of technical measures, including countless camera systems that are often only monitored by human operators. However, due to the sheer amount of data, safety monitoring and accident prevention are limited by human resources. In this paper, we present an efficient system capable of extracting accurate vehicle trajectories from the vast amount of video data generated by modern highway infrastructures. Our proposed system conveniently leverages bird's eye view transformations estimated from aerial data or street marker geometry to generate geo-localized trajectories. Utilizing existing infrastructure, we demonstrate that the central data for video-based highway traffic monitoring can be reliably extracted. Remarkably, this can be achieved solely relying on uncalibrated cameras and noisy video streams.
暂无评论