publications

2025

1. ICLR

   PooDLe: Pooled and Dense Self-supervised Learning from Naturalistic Videos

   Alex N. Wang^*, Christopher Hoang^*, Yuwen Xiong, and 2 more authors

   2025

   arXiv Website

2024

1. CogSci

   Self-supervised Learning of Video Representations from a Child’s Perspective

   A Emin Orhan, Wentao Wang, Alex N. Wang, and 2 more authors

   2024

   arXiv Code

2021

1. NeurIPSw

   Studying BatchNorm Learning Rate Decay on Meta-Learning Inner-Loop Adaptation

   Alex N. Wang^*, Gary Leung^*, and Sasha Doubov^*

   In MetaLearn Workshop, Neural Information Processing Systems, 2021

   Abs PDF

   Meta-learning for few-shot classification has been challenged on its effectiveness compared to simpler pretraining methods and the validity of its claim of "learning to learn". Recent work has suggested that MAML-based models do not perform "rapid-learning" in the inner-loop but reuse features by only adapting the final linear layer. Separately, BatchNorm, a near ubiquitous inclusion in model architectures, has been shown to have an implicit learning rate decay effect on the preceding layers of a network. We study the impact of BatchNorm’s implicit learning rate decay on feature reuse in meta-learning methods and find that counteracting it increases change in intermediate layers during adaptation. We also find that counteracting this learning rate decay sometimes improves performance on few-shot classification tasks.

2. ICML

   SketchEmbedNet: Learning Novel Concepts by Imitating Drawings

   Alex N. Wang^*, Mengye Ren^*, and Richard Zemel

   In Proceedings of the 38th International Conference on Machine Learning, 18–24 jul 2021

   Abs arXiv PDF Code

   Sketch drawings capture the salient information of visual concepts. Previous work has shown that neural networks are capable of producing sketches of natural objects drawn from a small number of classes. While earlier approaches focus on generation quality or retrieval, we explore properties of image representations learned by training a model to produce sketches of images. We show that this generative, class-agnostic model produces informative embeddings of images from novel examples, classes, and even novel datasets in a few-shot setting. Additionally, we find that these learned representations exhibit interesting structure and compositionality.