Search Results for author: Andrew Gallagher

Found 11 papers, 4 papers with code

Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models

no code implementations26 May 2023 Yunhao Ge, Jie Ren, Jiaping Zhao, KaiFeng Chen, Andrew Gallagher, Laurent Itti, Balaji Lakshminarayanan

Despite considerable effort, the problem remains significantly challenging in deep learning models due to their propensity to output over-confident predictions for OOD inputs.

Out of Distribution (OOD) Detection

Automatic Differentiation Variational Inference with Mixtures

no code implementations3 Mar 2020 Warren R. Morningstar, Sharad M. Vikram, Cusuh Ham, Andrew Gallagher, Joshua V. Dillon

Automatic Differentiation Variational Inference (ADVI) is a useful tool for efficiently learning probabilistic models in machine learning.

Variational Inference

Modeling Uncertainty with Hedged Instance Embedding

1 code implementation30 Sep 2018 Seong Joon Oh, Kevin Murphy, Jiyan Pan, Joseph Roth, Florian Schroff, Andrew Gallagher

Instance embeddings are an efficient and versatile image representation that facilitates applications like recognition, verification, retrieval, and clustering.

Clustering Metric Learning +1

AVA-Speech: A Densely Labeled Dataset of Speech Activity in Movies

1 code implementation2 Aug 2018 Sourish Chaudhuri, Joseph Roth, Daniel P. W. Ellis, Andrew Gallagher, Liat Kaver, Radhika Marvin, Caroline Pantofaru, Nathan Reale, Loretta Guarino Reid, Kevin Wilson, Zhonghua Xi

Speech activity detection (or endpointing) is an important processing step for applications such as speech recognition, language identification and speaker diarization.

Sound Audio and Speech Processing

Finding your Lookalike: Measuring Face Similarity Rather than Face Identity

no code implementations13 Jun 2018 Amir Sadovnik, Wassim Gharbi, Thanh Vu, Andrew Gallagher

In this work we propose the new, subjective task of quantifying perceived face similarity between a pair of faces.

Face Recognition General Classification

Revisiting Depth Layers from Occlusions

no code implementations CVPR 2013 Adarsh Kowdle, Andrew Gallagher, Tsuhan Chen

We cast the problem of depth-layer segmentation as a discrete labeling problem on a spatiotemporal Markov Random Field (MRF) that uses the motion occlusion cues along with monocular cues and a smooth motion prior for the moving object.

Object

3D-Based Reasoning with Blocks, Support, and Stability

no code implementations CVPR 2013 Zhaoyin Jia, Andrew Gallagher, Ashutosh Saxena, Tsuhan Chen

Our algorithm incorporates the intuition that a good 3D representation of the scene is the one that fits the data well, and is a stable, self-supporting (i. e., one that does not topple) arrangement of objects.

Object

Describing Clothing by Semantic Attributes

no code implementations ECCV 2012 Huizhong Chen, Andrew Gallagher, Bernd Girod

Describing clothing appearance with semantic attributes is an appealing technique for many important applications.

Attribute Clothing Attribute Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.