Search Results for author: Steven Mills

Found 7 papers, 0 papers with code

RocNet: Recursive Octree Network for Efficient 3D Deep Representation

no code implementations10 Aug 2020 Juncheng Liu, Steven Mills, Brendan McCane

Our network compresses a voxel grid of any size down to a very small latent space in an autoencoder-like network.

3D Reconstruction 3D Shape Classification +1

Distance Metric Learned Collaborative Representation Classifier

no code implementations3 May 2019 Tapabrata Chakraborti, Brendan McCane, Steven Mills, Umapada Pal

We present a simple effective way of achieving this by learning a generic Mahalanabis distance in a collaborative loss function in an end-to-end fashion with any standard convolutional network as the feature learner.

General Classification

PProCRC: Probabilistic Collaboration of Image Patches

no code implementations21 Mar 2019 Tapabrata Chakraborti, Brendan McCane, Steven Mills, Umapada Pal

We present a conditional probabilistic framework for collaborative representation of image patches.

Face Recognition

CoCoNet: A Collaborative Convolutional Network

no code implementations28 Jan 2019 Tapabrata Chakraborti, Brendan McCane, Steven Mills, Umapada Pal

We present an end-to-end deep network for fine-grained visual categorization called Collaborative Convolutional Network (CoCoNet).

Fine-Grained Visual Categorization Fine-Grained Visual Recognition +1

Fair Forests: Regularized Tree Induction to Minimize Model Bias

no code implementations21 Dec 2017 Edward Raff, Jared Sylvester, Steven Mills

The potential lack of fairness in the outputs of machine learning algorithms has recently gained attention both within the research community as well as in society more broadly.

Attribute Fairness

LOOP Descriptor: Local Optimal Oriented Pattern

no code implementations25 Oct 2017 Tapabrata Chakraborti, Brendan McCane, Steven Mills, Umapada Pal

This letter introduces the LOOP binary descriptor (local optimal oriented pattern) that encodes rotation invariance into the main formulation itself.

Auto-JacoBin: Auto-encoder Jacobian Binary Hashing

no code implementations25 Feb 2016 Xiping Fu, Brendan McCane, Steven Mills, Michael Albert, Lech Szymanski

Binary codes can be used to speed up nearest neighbor search tasks in large scale data sets as they are efficient for both storage and retrieval.

Retrieval

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