348 citations · 861 across the 19 of their papers we have counts for
20 papers
From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
Yuxin Ren, Maxwell D Collins, Miao Hu +1
Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with si…
FAR: Function-preserving Attention Replacement for IMC-friendly Inference
Yuxin Ren, Maxwell D Collins, Miao Hu +1
While transformers dominate modern vision and language models, their attention mechanism remains poorly suited for in-memory computing (IMC) devices due to intensive activation-to-…
Learning to Generate Image Embeddings with User-level Differential Privacy
Zheng Xu, Maxwell Collins, Yuxiao Wang +6
Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past. However, existi…
kMaX-DeepLab: k-means Mask Transformer
Qihang Yu, Huiyu Wang, Siyuan Qiao +5
The rise of transformers in vision tasks not only advances network backbone designs, but also starts a brand-new page to achieve end-to-end image recognition (e.g., object detectio…
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
Qihang Yu, Huiyu Wang, Dahun Kim +6
We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer archi…
DeepLab2: A TensorFlow Library for Deep Labeling
Mark Weber, Huiyu Wang, Siyuan Qiao +12
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer…