Related papers: Towards Robust Semantic Correspondence: A Benchmar…

Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the semantics of the objects they are asked to generate. In this…

Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question. Recent advancements in few-shot language models trained on code have demonstrated superior performance in…

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent…

Recent advances in semantic correspondence have been largely driven by the use of pre-trained large-scale models. However, a limitation of these approaches is their dependence on high-resolution input images to achieve optimal performance,…

With the increasing use of large language models (LLMs), ensuring reliable performance in diverse, real-world environments is essential. Despite their remarkable achievements, LLMs often struggle with adversarial inputs, significantly…

We evaluate the robustness of several large language models on multiple datasets. Robustness here refers to the relative insensitivity of the model's answers to meaning-preserving variants of their input. Benchmark datasets are constructed…

Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific…

Semantic communications offer promising prospects for enhancing data transmission efficiency. However, existing schemes have predominantly concentrated on point-to-point transmissions. In this paper, we aim to investigate the validity of…

When artificial agents are jointly trained to perform collaborative tasks using a communication channel, they develop opaque goal-oriented communication protocols. Good task performance is often considered sufficient evidence that…

Deep learning models suffer from the problem of semantic discontinuity: small perturbations in the input space tend to cause semantic-level interference to the model output. We argue that the semantic discontinuity results from these…

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

Deep neural networks for computer vision are deployed in increasingly safety-critical and socially-impactful applications, motivating the need to close the gap in model performance under varied, naturally occurring imaging conditions.…

The growing demands of artificial intelligence and immersive media require communication beyond bit-level accuracy to meaning awareness. Conventional optical systems that focused on syntactic precision suffer significant inefficiencies.…

Adversarial robustness evaluates the worst-case performance scenario of a machine learning model to ensure its safety and reliability. This study is the first to investigate the robustness of visually grounded dialog models towards textual…

The robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts, which becomes an important research problem in the development of deep learning. Although new deep learning…

Deep features have been proven powerful in building accurate dense semantic correspondences in various previous works. However, the multi-scale and pyramidal hierarchy of convolutional neural networks has not been well studied to learn…

Establishing dense correspondences across image pairs is essential for tasks such as shape reconstruction and robot manipulation. In the challenging setting of matching across different categories, the function of an object, i.e., the…

The robustness of deep neural networks is a crucial factor in safety-critical applications, particularly in complex and dynamic environments (e.g., medical or driving scenarios) where localized corruptions can arise. While previous studies…

As the global demand for data has continued to rise exponentially, some have begun turning to the idea of semantic communication as a means of efficiently meeting this demand. Pushing beyond the boundaries of conventional communication…

Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking the critical question of resolution robustness - whether…