[HTML][HTML] Data augmentation: A comprehensive survey of modern approaches
A Mumuni, F Mumuni - Array, 2022 - Elsevier
To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …
Image data augmentation approaches: A comprehensive survey and future directions
Deep learning algorithms have exhibited impressive performance across various computer
vision tasks; however, the challenge of overfitting persists, especially when dealing with …
vision tasks; however, the challenge of overfitting persists, especially when dealing with …
When vision transformers outperform resnets without pre-training or strong data augmentations
Vision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features
or inductive biases with general-purpose neural architectures. Existing works empower the …
or inductive biases with general-purpose neural architectures. Existing works empower the …
Enhance the visual representation via discrete adversarial training
Adversarial Training (AT), which is commonly accepted as one of the most effective
approaches defending against adversarial examples, can largely harm the standard …
approaches defending against adversarial examples, can largely harm the standard …
[PDF][PDF] Shape-texture debiased neural network training
Shape and texture are two prominent and complementary cues for recognizing objects.
Nonetheless, Convolutional Neural Networks are often biased towards either texture or …
Nonetheless, Convolutional Neural Networks are often biased towards either texture or …
Coco-o: A benchmark for object detectors under natural distribution shifts
Practical object detection application can lose its effectiveness on image inputs with natural
distribution shifts. This problem leads the research community to pay more attention on the …
distribution shifts. This problem leads the research community to pay more attention on the …
Adversarial attacks and defenses in deep learning for image recognition: A survey
In recent years, researches on adversarial attacks and defense mechanisms have obtained
much attention. It's observed that adversarial examples crafted with small malicious …
much attention. It's observed that adversarial examples crafted with small malicious …
Gsrformer: Grounded situation recognition transformer with alternate semantic attention refinement
Grounded Situation Recognition (GSR) aims to generate structured semantic summaries of
images for" human-like''event understanding. Specifically, GSR task not only detects the …
images for" human-like''event understanding. Specifically, GSR task not only detects the …
Does robustness on imagenet transfer to downstream tasks?
As clean ImageNet accuracy nears its ceiling, the research community is increasingly more
concerned about robust accuracy under distributional shifts. While a variety of methods have …
concerned about robust accuracy under distributional shifts. While a variety of methods have …
Harnessing perceptual adversarial patches for crowd counting
Crowd counting, which has been widely adopted for estimating the number of people in
safety-critical scenes, is shown to be vulnerable to adversarial examples in the physical …
safety-critical scenes, is shown to be vulnerable to adversarial examples in the physical …