Related papers: Clarifying Myths About the Relationship Between Sh…
Data augmentation refers to a group of techniques whose goal is to battle limited amount of available data to improve model generalization and push sample distribution toward the true distribution. While different augmentation strategies…
Data augmentation has become a standard practice in software engineering to address limited or imbalanced data sets, particularly in specialized domains like test classification and bug detection where data can be scarce. Although…
Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using…
Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this…
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…
Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation…
Improving out-of-distribution (OOD) generalization during in-distribution (ID) adaptation is a primary goal of robust fine-tuning of zero-shot models beyond naive fine-tuning. However, despite decent OOD generalization performance from…
Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…
We introduce several new datasets namely ImageNet-A/O and ImageNet-R as well as a synthetic environment and testing suite we called CAOS. ImageNet-A/O allow researchers to focus in on the blind spots remaining in ImageNet. ImageNet-R was…
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…
Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintaining the general performance of the model while allowing it to gain new skills. A valuable goal…
The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning…
Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust…
Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision applications, where shifts in image background, style, and acquisition instruments always degrade model performance. Generic augmentations show…
In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples. While these…
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on…
Deep learning algorithms have shown promising results in visual question answering (VQA) tasks, but a more careful look reveals that they often do not understand the rich signal they are being fed with. To understand and better measure the…
Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…
Data augmentation is one of the most effective techniques to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability in medical image analysis, it is frequently underutilized. This…