Search Results for author:
Found 10 papers, 7 papers with code
FACET: Fairness in Computer Vision Evaluation Benchmark
We present a new benchmark named FACET (FAirness in Computer Vision EvaluaTion), a large, publicly available evaluation set of 32k images for some of the most common vision tasks - image classification, object detection and segmentation.
Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies
As an example, we show that mitigating a model's vulnerability to texture can improve performance on the lower income level.
Segment Anything
We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation.
Ranked #2 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers
These metrics successfully incentivized performance improvements on person-centric tasks such as face analysis and are used to understand risks of modern models.
Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities
With these capabilities in mind, we ask: Do vision-language models exhibit gender bias when performing zero-shot image classification, object detection and semantic segmentation?
A Systematic Study of Bias Amplification
To enable this study, we design a simple image-classification problem in which we can tightly control (synthetic) biases.
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Model pre-training is a cornerstone of modern visual recognition systems.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
(using extra training data)
Fine-Grained Image Classification
Out-of-Distribution Generalization
+3
Forward Prediction for Physical Reasoning
Physical reasoning requires forward prediction: the ability to forecast what will happen next given some initial world state.
Ranked #2 on
Visual Reasoning
on PHYRE-1B-Within
PHYRE: A New Benchmark for Physical Reasoning
The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles.
Ranked #3 on
Visual Reasoning
on PHYRE-1B-Within
Growing Action Spaces
In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress.
