3.6k citations · 10.6k across the 54 of their papers we have counts for
15 papers · 1 filter
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
Zichao Li, Cihang Xie, Ekin Dogus Cubuk
This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimension…
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
Emirhan Kurtulus, Zichao Li, Yann Dauphin +1
Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi…
LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations
Zhaoqi Leng, Guowang Li, Chenxi Liu +5
Data augmentations are important in training high-performance 3D object detectors for point clouds. Despite recent efforts on designing new data augmentations, perhaps surprisingly…
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Zhaoqi Leng, Mingxing Tan, Chenxi Liu +4
Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can…
Do better ImageNet classifiers assess perceptual similarity better?
Manoj Kumar, Neil Houlsby, Nal Kalchbrenner +1
Perceptual distances between images, as measured in the space of pre-trained deep features, have outperformed prior low-level, pixel-based metrics on assessing perceptual similarit…
Multi-Task Self-Training for Learning General Representations
Golnaz Ghiasi, Barret Zoph, Ekin D. Cubuk +2
Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision.…