121 citations · 165 across the 13 of their papers we have counts for
7 papers · 1 filter
PatchBlender: A Motion Prior for Video Transformers
Gabriele Prato, Yale Song, Janarthanan Rajendran +3
Transformers have become one of the dominant architectures in the field of computer vision. However, there are yet several challenges when applying such architectures to video data…
Neural-Sim: Learning to Generate Training Data with NeRF
Yunhao Ge, Harkirat Behl, Jiashu Xu +6
Training computer vision models usually requires collecting and labeling vast amounts of imagery under a diverse set of scene configurations and properties. This process is incredi…
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
Tyler LaBonte, Yale Song, Xin Wang +2
A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and e…
DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +3
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-toimage synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.).…
Visual Attention Emerges from Recurrent Sparse Reconstruction
Baifeng Shi, Yale Song, Neel Joshi +2
Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We…
One Network Doesn't Rule Them All: Moving Beyond Handcrafted Architectures in Self-Supervised Learning
Sharath Girish, Debadeepta Dey, Neel Joshi +5
The current literature on self-supervised learning (SSL) focuses on developing learning objectives to train neural networks more effectively on unlabeled data. The typical developm…