Learning to Transform for Generalizable Instance-wise Invariance
Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too much or too little invariance can hurt, and the correct amount is unknown a priori and dependent on the instance. Ideally, the appropriate invariance would be learned from data and inferred at test-time. We treat invariance as a prediction problem. Given any image, we use a normalizing flow to predict a distribution over transformations and average the predictions over them. Since this distribution only depends on the instance, we can align instances before classifying them and generalize invariance across classes. The same distribution can also be used to adapt to out-of-distribution poses. This normalizing flow is trained end-to-end and can learn a much larger range of transformations than Augerino and InstaAug. When used as data augmentation, our method shows accuracy and robustness gains on CIFAR 10, CIFAR10-LT, and TinyImageNet.
Code (1)
Tasks
Data AugmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Scale-invariant unconstrained online learning
We consider a variant of online convex optimization in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale invariance symmetry in our unconstrained se…
PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering
Feature invariance under different data transformations, i.e., transformation invariance, can be regarded as a type of self-supervision for representation learning. In this paper, we present PointClustering, a new un…
ClusteringDeep ClusteringInductive BiasPhilosophy+2Volumetric Transformer Networks
Existing techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account for the fact that the individual feature c…
DecoderFine-Grained Image RecognitionImage RetrievalRetrievalGroup-based Learning of Disentangled Representations with Generalizability for Novel Contents
Sensory data are often comprised of independent content and transformation factors. For example, face images may have shapes as content and poses as transformation. To infer separately these factors from given data, vari…
AttributeConsistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning
Inductive biases steer learning toward generalizable solutions by encoding task structure. In this work, we identify a crucial missing bias in MLLMs: cross-view consistency, \textit{i.e.}, semantically invariant views of…
Reinforcement LearningMultimodal ReasoningData Augmentation