activity
20172023
most citedSqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

57 citations · 142 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2023

UPSCALE: Unconstrained Channel Pruning

Alvin Wan, Hanxiang Hao, Kaushik Patnaik +5

As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels fr…

cs.CV2023

AutoFocusFormer: Image Segmentation off the Grid

Chen Ziwen, Kaushik Patnaik, Shuangfei Zhai +5

Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small object…

cs.CV20204 cited

SegNBDT: Visual Decision Rules for Segmentation

Alvin Wan, Daniel Ho, Younjin Song +3

The black-box nature of neural networks limits model decision interpretability, in particular for high-dimensional inputs in computer vision and for dense pixel prediction tasks li…

cs.CV2020

Visual Transformers: Token-based Image Representation and Processing for Computer Vision

Bichen Wu, Chenfeng Xu, Xiaoliang Dai +7

Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions tr…

cs.CV2020

FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining

Xiaoliang Dai, Alvin Wan, Peizhao Zhang +8

Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for archite…

cs.CV202029 cited

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Alvin Wan, Xiaoliang Dai, Peizhao Zhang +9

Differentiable Neural Architecture Search (DNAS) has demonstrated great success in designing state-of-the-art, efficient neural networks. However, DARTS-based DNAS's search space i…