Related papers: A Causally Grounded Taxonomy for Image Degradation…
Due to the increase in computational resources and accessibility of data, an increase in large, deep learning models trained on copious amounts of multi-modal data using self-supervised or semi-supervised learning have emerged. These…
The state-of-the-art deep neural networks are vulnerable to common corruptions (e.g., input data degradations, distortions, and disturbances caused by weather changes, system error, and processing). While much progress has been made in…
Accuracies of deep learning (DL) classifiers are often unstable in that they may change significantly when retested on adversarial images, imperfect images, or perturbed images. This paper adds to the fundamental body of work on…
This paper proposes a new end-to-end trainable model for lossy image compression, which includes several novel components. The method incorporates 1) an adequate perceptual similarity metric; 2) saliency in the images; 3) a hierarchical…
Object detection is a vital task in computer vision and has become an integral component of numerous critical systems. However, state-of-the-art object detectors, similar to their classification counterparts, are susceptible to small…
Human visual systems are robust to a wide range of image transformations that are challenging for artificial networks. We present the first study of image model robustness to the minute transformations found across video frames, which we…
Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze,…
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We…
With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…
This work addresses the certification of the local robustness of vision-based two-stage 6D object pose estimation. The two-stage method for object pose estimation achieves superior accuracy by first employing deep neural network-driven…
Cameras play a crucial role in modern driver assistance systems and are an essential part of the sensor technology for automated driving. The quality of images captured by in-vehicle cameras highly influences the performance of visual…
Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on correlation-based measures to attribute model decisions to…
Models for image segmentation, node classification and many other tasks map a single input to multiple labels. By perturbing this single shared input (e.g. the image) an adversary can manipulate several predictions (e.g. misclassify several…
Deep neural networks have significantly improved the performance of low-level vision tasks but also increased the difficulty of interpretability. A deep understanding of deep models is beneficial for both network design and practical…
Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single…
Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep-learning neural networks, especially the Convolutional Neural Networks (CNN). Most of the existing works are…
Semantic communications have gained significant attention as a promising approach to address the transmission bottleneck, especially with the continuous development of 6G techniques. Distinct from the well investigated physical channel…
Deep learning-based visual perception models lack robustness when faced with camera motion perturbations in practice. The current certification process for assessing robustness is costly and time-consuming due to the extensive number of…
Vision-based control relies on accurate perception to achieve robustness. However, image distribution changes caused by sensor noise, adverse weather, and dynamic lighting can degrade perception, leading to suboptimal control decisions.…
Semantic correspondence aims to identify semantically meaningful relationships between different images and is a fundamental challenge in computer vision. It forms the foundation for numerous tasks such as 3D reconstruction, object…