Search Results for author:
Found 18 papers, 7 papers with code
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
To facilitate a systematic evaluation of VLM progress, we introduce UniBench: a unified implementation of 50+ VLM benchmarks spanning a comprehensive range of carefully categorized capabilities from object recognition to spatial awareness, counting, and much more.
The Bias of Harmful Label Associations in Vision-Language Models
Despite the remarkable performance of foundation vision-language models, the shared representation space for text and vision can also encode harmful label associations detrimental to fairness.
VPA: Fully Test-Time Visual Prompt Adaptation
Inspired by the success of textual prompting, several studies have investigated the efficacy of visual prompt tuning.
Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis
To highlight the importance of privacy issues and motivate future research, we motivate and introduce the Pedestrian Dataset De-Identification (PDI) task.
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.
The Casual Conversations v2 Dataset
This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in regards to 11 attributes that are self-provided or labeled by trained annotators.
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
Key to advancing the reliability of vision systems is understanding whether existing methods can overcome multiple shortcuts or struggle in a Whac-A-Mole game, i. e., where mitigating one shortcut amplifies reliance on others.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements.
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
Equipped with ImageNet-X, we investigate 2, 200 current recognition models and study the types of mistakes as a function of model's (1) architecture, e. g. transformer vs. convolutional, (2) learning paradigm, e. g. supervised vs. self-supervised, and (3) training procedures, e. g., data augmentation.
Generating High Fidelity Data from Low-density Regions using Diffusion Models
We observe that uniform sampling from diffusion models predominantly samples from high-density regions of the data manifold.
Fairness Indicators for Systematic Assessments of Visual Feature Extractors
Systematic diagnosis of fairness, harms, and biases of computer vision systems is an important step towards building socially responsible systems.
Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions
This paper presents initial Speech Recognition results on "Casual Conversations" -- a publicly released 846 hour corpus designed to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of metadata, including age, gender, and skin tone.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Localized Uncertainty Attacks
Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain.
Towards Measuring Fairness in AI: the Casual Conversations Dataset
The videos were recorded in multiple U. S. states with a diverse set of adults in various age, gender and apparent skin tone groups.
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations.
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks.
Deep Depth From Focus
Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision.
Image-based localization using LSTMs for structured feature correlation
In this work we propose a new CNN+LSTM architecture for camera pose regression for indoor and outdoor scenes.
