Machine Learning Blog | ML@CMU | Carnegie Mellon University

computer vision machine learning Research

Bottom-up Top-Down Detection Transformers For Open Vocabulary Object Detection

by Ayush Jain / January 13, 2023

We perform open vocabulary detection of the objects mentioned in the sentence using both bottom-up and top-down feedback. Object detection is the fundamental computer vision task of finding all “objects” that are present in a visual scene. However, this raises the question, what is an object? Typically, this question is side-stepped by defining a vocabulary of categories and then training a model to detect instances of this vocabulary. This means that if “apple” is not in this vocabulary, the model…

36 4023

machine learning Research

Causal Confounds in Sequential Decision Making

November 28, 2022

A standard assumption in sequential decision making is that we observe everything required to make good decisions. In practice however, this isn’t always the case. We discuss two specific examples (temporally correlated noise (a) and unobserved contexts (c)) that have…

75 8145

Research

How do Authors’ Perceptions about their Papers Compare with Co-authors’ Perceptions and Peer-review Decisions?

November 22, 2022

Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan(NeurIPS 2021 Program Chairs) Charvi Rastogi, Ivan Stelmakh, Zhenyu Xue, Hal Daumé III, Emma Pierson, and Nihar B. Shah There is a considerable body of research on peer review. Within the…

236 7737 3

automl deep learning machine learning Research

Tackling Diverse Tasks with Neural Architecture Search

October 14, 2022

DASH searches for the optimal kernel size and dilation rate efficiently from a large set of options for each convolutional layer in a CNN backbone. The resulting model can achieve task-specific feature extraction and work as well as hand-designed expert…

92 7279

computer vision deep learning machine learning Research

Tracking Any Pixel in a Video

September 9, 2022

We upgrade pixels into PIPs: “Persistent Independent Particles”. With this representation, we track any pixel over time, and overcome visibility issues with a learned temporal prior. Motion estimation is a fundamental task of computer vision, with extremely broad applications. By…

133 10877

machine learning Research

Long-term Dynamics of Fairness Intervention in Connection Recommender Systems

September 2, 2022

Figure 1: Modeled recommendation cycle. We demonstrate how enforcing group-fairness in every recommendation slate separately does not necessarily promote equity in second order variables of interest like network size. Connection recommendation is at the heart of user experience in many…

130 3096

machine learning reinforcement learning Research

Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

August 26, 2022

Figure 1. Our implementation of recurrent model-free RL outperforms the on-policy version (PPO/A2C-GRU), and a recent model-based POMDP algorithm (VRM) on most tasks of a POMDP benchmark where VRM was evaluated in their paper. While algorithms for decision-making typically focus…

139 3445

machine learning Research

Galaxies on Graph Neural Networks

August 19, 2022

The current accelerated expansion of the Universe is driven by the mysterious dark energy. Upcoming astronomical imaging surveys, such as LSST at Rubin Observatory, are set to provide unprecedented precise measurement of cosmological parameters, including this dark energy, using measurements…

150 5018

Educational machine learning

auton-survival: An Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping Censored Time-to-Event Data

August 5, 2022

Real-world decision-making often requires reasoning about when an event will occur. The overarching goal of such reasoning is to help aid decision-making for optimal triage and subsequent intervention. Such problems involving estimation of Times-to-an-Event frequently arise across multiple…

169 5086

artificial intelligence automl deep learning machine learning Research

Does AutoML work for diverse tasks?

July 7, 2022

Over the past decade, machine learning (ML) has grown rapidly in both popularity and complexity. Driven by advances in deep neural networks, ML is now being applied far beyond its traditional domains like computer vision and text processing, with applications…

175 7026 1

Older Posts

Machine Learning Blog | ML@CMU | Carnegie Mellon University

Statistics:

Categories: