Search Results for author:
Found 9 papers, 6 papers with code
Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation
As VFMs' popularity grows, there is an increasing interest in understanding their effectiveness for dense prediction tasks.
LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models
Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level understanding.
Renovating Names in Open-Vocabulary Segmentation Benchmarks
Names are essential to both human cognition and vision-language models.
SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization
The voluminous nature of geospatial temporal data from physical monitors and simulation models poses challenges to efficient data access, often resulting in cumbersome temporal selection experiences in web-based data portals.
GOOD: Exploring Geometric Cues for Detecting Objects in an Open World
We address the task of open-world class-agnostic object detection, i. e., detecting every object in an image by learning from a limited number of base object classes.
Ranked #1 on
Open World Object Detection
on COCO VOC to non-VOC
Decomposing Representations for Deterministic Uncertainty Estimation
Uncertainty estimation is a key component in any deployed machine learning system.
Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
ResNets constrained to be bi-Lipschitz, that is, approximately distance preserving, have been a crucial component of recently proposed techniques for deterministic uncertainty quantification in neural models.
Feature Space Singularity for Out-of-Distribution Detection
Our analysis of the phenomenon reveals why our algorithm works.
Ranked #1 on
Out-of-Distribution Detection
on MS-1M vs. IJB-C
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate
NosAdam can be regarded as a fix to the non-convergence issue of Adam in alternative to the recent work of [Reddi et al., 2018].
