Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In
contrast, synthetic data can be freely available using a generative model (eg, DALL-E …

Utilizing auxiliary outlier datasets to regularize the machine learning model has
demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the …

Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often
lets those tasks learn better jointly. Multi-tasking models have become successful and often …

We present MosaicFusion, a simple yet effective diffusion-based data augmentation
approach for large vocabulary instance segmentation. Our method is training-free and does …

Text-to-image diffusion models produce high quality images but do not offer control over
individual instances in the image. We introduce InstanceDiffusion that adds precise instance …

The open road poses many challenges to autonomous perception, including poor visibility
from extreme weather conditions. Models trained on good-weather datasets frequently fail at …

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive
performance on image classification benchmarks and their zero-shot generalization ability is …

Camouflaged vision perception is an important vision task with numerous practical
applications. Due to the expensive collection and labeling costs this community struggles …

A major challenge in monocular 3D object detection is the limited diversity and quantity of
objects in real datasets. While augmenting real scenes with virtual objects holds promise to …

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 …