55 citations · 177 across the 11 of their papers we have counts for
7 papers · 1 filter
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
Chen Huang, Xianhang Li, Vimal Thilak +2
Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inhe…
DUET: 2D Structured and Approximately Equivariant Representations
Xavier Suau, Federico Danieli, T. Anderson Keller +5
Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transfor…
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
Chen Huang, Hanlin Goh, Jiatao Gu +1
Recent Self-Supervised Learning (SSL) methods are able to learn feature representations that are invariant to different data augmentations, which can then be transferred to downstr…
An Attention Free Transformer
Shuangfei Zhai, Walter Talbott, Nitish Srivastava +4
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are…
MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
Chen Huang, Shuangfei Zhai, Pengsheng Guo +1
We study the problem of directly optimizing arbitrary non-differentiable task evaluation metrics such as misclassification rate and recall. Our method, named MetricOpt, operates in…
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
Chen Huang, Shuangfei Zhai, Walter Talbott +4
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this…