1

LAB: Learnable Activation Binarizer for Binary Neural Networks

Self-Attention Message Passing for Contrastive Few-Shot Learning

Self-Supervised Class-Cognizant Few-Shot Classification

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

We provide a high bandwidth, alias-free convolutional kernel parameterization with learnable kernel size and constant parameter cost.

Humans disagree with the IoU for measuring object detector localization error

The localization quality of automatic object detectors is typically evaluated by the Intersection over Union (IoU) score. In this work, we show that humans have a different view on localization quality. To evaluate this, we conduct a survey with more …

Self-Supervised 3D Hand Pose Estimation from monocular RGB via Contrastive Learning

Zero-Shot Day-Night Domain Adaptation with a Physics Prior

We explore the zero-shot setting for day-night domain adaptation. We cast a number of color invariant edge detectors as trainable layers in a convolutional neural network and evaluate their robustness to illumination changes.

Exploiting Learned Symmetries in Group Equivariant Convolutions

We show that GConvs can be efficiently decomposed into depthwise separable convolutions while preserving equivariance properties and demonstrate improved performance and data efficiency on two datasets.

No frame left behind: Full Video Action Recognition

We cluster video frames end-to-end to use all frames in action recognition.

Self-Learning Transformations for Improving Gaze and Head Redirection