ServiceNow Research

Computer Vision

GEO-Bench: Toward Foundation Models for Earth Monitoring
Recent progress in self-supervision shows that pre-training large neural networks on vast amounts of unsupervised data can lead to …
Affinity Learning With Blind-spot Self-supervision for Image Denoising
In this paper, we extend the blind-spot based self-supervised denoising by using affinity learning to remove noise from affected …
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Large pre-trained models have proved to be remarkable zero- and (prompt-based) few-shot learners in unimodal vision and language tasks. …
OCR-VQGAN: Taming Text-within-Image Generation
Synthetic image generation has recently experienced significant improvements in domains such as natural image or art generation. …
Haptics-based Curiosity for Sparse-reward Tasks
Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks …
Consistency-CAM: Towards Improved Weakly Supervised Semantic Segmentation
Semantic segmentation is a popular task that has piqued the interest of many industries and research communities. However, acquiring …
OSM: An Open Set Matting Framework with OOD Detection and Few-Shot Learning
Natural image matting is the task of precisely estimating alpha mattes to separate foreground objects from background images. Existing …
A Planning based Neural-Symbolic Approach for Embodied Instruction Following
The ALFRED environment features an embodied agent following instructions and accomplishing tasks in simulated home environments. …
A Closer Look at Embedding Propagation for Manifold Smoothing
Supervised training of neural networks requires a large amount of manually annotated data and the resulting networks tend to be …
RaVAEn: Unsupervised Change Detection of Extreme Events Using ML On-Board Satellites
Applications such as disaster management enormously benefit from rapid availability of satellite observations. Traditionally, data …