430 citations · 471 across the 10 of their papers we have counts for
9 papers · 1 filter
Hyperbolic Contrastive Learning for Visual Representations beyond Objects
Songwei Ge, Shlok Mishra, Simon Kornblith +2
Although self-/un-supervised methods have led to rapid progress in visual representation learning, these methods generally treat objects and scenes using the same lens. In this pap…
Decoder Denoising Pretraining for Semantic Segmentation
Emmanuel Brempong Asiedu, Simon Kornblith, Ting Chen +3
Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the…
Why Do Better Loss Functions Lead to Less Transferable Features?
Simon Kornblith, Ting Chen, Honglak Lee +1
Previous work has proposed many new loss functions and regularizers that improve test accuracy on image classification tasks. However, it is not clear whether these loss functions…
Revisiting Spatial Invariance with Low-Rank Local Connectivity
Gamaleldin F. Elsayed, Prajit Ramachandran, Jonathon Shlens +1
Convolutional neural networks are among the most successful architectures in deep learning with this success at least partially attributable to the efficacy of spatial invariance a…
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
Katherine L. Hermann, Ting Chen, Simon Kornblith
Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come fro…
Saccader: Improving Accuracy of Hard Attention Models for Vision
Gamaleldin F. Elsayed, Simon Kornblith, Quoc V. Le
Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One appro…