Related papers: Attention Consistency on Visual Corruptions for Si…

The performance of computer vision models are susceptible to unexpected changes in input images caused by sensor errors or extreme imaging environments, known as common corruptions (e.g. noise, blur, illumination changes). These corruptions…

Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalization ability, which limits the real-world applications. The…

Real-world visual systems face time-varying perturbations, including weather, sensor noise, compression artifacts, and background distractions. Existing image restoration methods are typically designed for fixed corruption types and…

Single-image-to-3D models typically follow a sequential generation and reconstruction workflow. However, intermediate multi-view images synthesized by pre-trained generation models often lack cross-view consistency (CVC), significantly…

Despite the success of vision transformers (ViTs), they still suffer from significant drops in accuracy in the presence of common corruptions, such as noise or blur. Interestingly, we observe that the attention mechanism of ViTs tends to…

Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks to measure model…

Story continuation focuses on generating the next image in a narrative sequence so that it remains coherent with both the ongoing text description and the previously observed images. A central challenge in this setting lies in utilizing…

CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise,…

Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision. Recently, several new data augmentations have been proposed that significantly…

While Neural Networks (NNs) have surpassed human accuracy in image classification on ImageNet, they often lack robustness against image corruption, i.e., corruption robustness. Yet such robustness is seemingly effortless for human…

While some convolutional neural networks (CNNs) have surpassed human visual abilities in object classification, they often struggle to recognize objects in images corrupted with different types of common noise patterns, highlighting a major…

Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data,…

Semi-supervised semantic segmentation (SSS) has recently gained increasing research interest as it can reduce the requirement for large-scale fully-annotated training data. The current methods often suffer from the confirmation bias from…

Vision-language models (VLMs) have demonstrated impressive capabilities in understanding and reasoning about visual and textual content. However, their robustness to common image corruptions remains under-explored. In this work, we present…

In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this…

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…

We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together.…

Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training…

Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…

Learning Invariant Representations has been successfully applied for reconciling a source and a target domain for Unsupervised Domain Adaptation. By investigating the robustness of such methods under the prism of the cluster assumption, we…