Related papers: Learn2Augment: Learning to Composite Videos for Da…

Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment…

Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production. However, generalization - the ability to perform well in related but unseen scenarios - is an essential…

Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…

Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is…

Video behavior recognition demands stable and discriminative representations under complex spatiotemporal variations. However, prevailing data augmentation strategies for videos remain largely perturbation-driven, often introducing…

Few-shot learning aims to classify unseen classes with a few training examples. While recent works have shown that standard mini-batch training with a carefully designed training strategy can improve generalization ability for unseen…

Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the model learns a more robust set of features which are shared…

Character animation is a transformative field in computer graphics and vision, enabling dynamic and realistic video animations from static images. Despite advancements, maintaining appearance consistency in animations remains a challenge.…

The standard approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of the target task. However, in many scenarios, it is often…

Distilling knowledge from human demonstrations is a promising way for robots to learn and act. Existing methods, which often rely on coarsely-aligned video pairs, are typically constrained to learning global or task-level features. As a…

We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data…

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Machine learning models for camera-based physiological measurement can have weak generalization due to a lack of representative training data. Body motion is one of the most significant sources of noise when attempting to recover the subtle…

Data augmentation methods such as Copy-Paste have been studied as effective ways to expand training datasets while incurring minimal costs. While such methods have been extensively implemented for image level tasks, we found no scalable…

Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of…

Imitation learning is a promising approach for training autonomous vehicles (AV) to navigate complex traffic environments by mimicking expert driver behaviors. While existing imitation learning frameworks focus on leveraging expert…

Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We…

Video stabilization is a longstanding computer vision problem, particularly pixel-level synthesis solutions for video stabilization which synthesize full frames add to the complexity of this task. These techniques aim to stabilize videos by…

We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods…

Video harmonization aims to adjust the foreground of a composite video to make it compatible with the background. So far, video harmonization has only received limited attention and there is no public dataset for video harmonization. In…