相关论文: Characterizing and Improving the Robustness of Sel…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Deep networks for visual recognition are known to leverage "easy to recognise" portions of objects such as faces and distinctive texture patterns. The lack of a holistic understanding of objects may increase fragility and overfitting. In…

Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

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…

Self-supervised learning (SSL) methods have achieved remarkable success in learning image representations allowing invariances in them - but therefore discarding transformation information that some computer vision tasks actually require.…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Recently, a number of new Semi-Supervised Learning methods have emerged. As the accuracy for ImageNet and similar datasets increased over time, the performance on tasks beyond the classification of natural images is yet to be explored. Most…

Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing. This paper introduces a novel self-supervised constraint for single image super-resolution,…

Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information.…

We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the…

What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations…

Advancing Machine Learning (ML)-based perception models for autonomous systems necessitates addressing weak spots within the models, particularly in challenging Operational Design Domains (ODDs). These are environmental operating conditions…

Grounding-based vision and language models have been successfully applied to low-level vision tasks, aiming to precisely locate objects referred in captions. The effectiveness of grounding representation learning heavily relies on the scale…

When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data…

Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a…

For safety-critical applications such as autonomous driving, CNNs have to be robust with respect to unavoidable image corruptions, such as image noise. While previous works addressed the task of robust prediction in the context of…

Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of groundtruth images in datasets due to practical constraints in data…

Boosting is a commonly used technique to enhance the performance of a set of base models by combining them into a strong ensemble model. Though widely adopted, boosting is typically used in supervised learning where the data is labeled…