Related papers: Robustifying Deep Vision Models Through Shape Sens…
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a…
Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…
Deep learning models can perform well when evaluated on images from the same distribution as the training set. However, applying small perturbations in the forms of noise, artifacts, occlusions, blurring, etc. to a model's input image and…
Image classification has been a popular task due to its feasibility in real-world applications. Training neural networks by feeding them RGB images has demonstrated success over it. Nevertheless, improving the classification accuracy and…
Data augmentation (DA) enhances model generalization in computer vision but may introduce biases, impacting class accuracy unevenly. Our study extends this inquiry, examining DA's class-specific bias across various datasets, including those…
Statistical shape models (SSM) have been well-established as an excellent tool for identifying variations in the morphology of anatomy across the underlying population. Shape models use consistent shape representation across all the samples…
Shape and texture are two prominent and complementary cues for recognizing objects. Nonetheless, Convolutional Neural Networks are often biased towards either texture or shape, depending on the training dataset. Our ablation shows that such…
Object Detection has been a significant topic in computer vision. As the continuous development of Deep Learning, many advanced academic and industrial outcomes are established on localising and classifying the target objects, such as…
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…
In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…
Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bias in their representation, contrary to the intuition that…
Vision Transformer (ViT) has demonstrated promising performance in computer vision tasks, comparable to state-of-the-art neural networks. Yet, this new type of deep neural network architecture is vulnerable to adversarial attacks limiting…
Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency…
As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect…
We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches. We find that ViTs are surprisingly insensitive to…
Humans rely less on spurious correlations and trivial cues, such as texture, compared to deep neural networks which lead to better generalization and robustness. It can be attributed to the prior knowledge or the high-level cognitive…
In this paper we propose a novel augmentation technique that improves not only the performance of deep neural networks on clean test data, but also significantly increases their robustness to random transformations, both affine and…
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…