Pietro Perona

is this you? claim profile

∙ 0 followers
Amazon ∙ California Institute of Technology

Allen E. Puckett Professor of Electrical Engineering and of Computation and Neural Systems at California Institute of Technology

PanDA: Panoptic Data Augmentation

The recently proposed panoptic segmentation task presents a significant ...
11/27/2019 ∙ by Yang Liu, et al. ∙ 37 ∙ share

read it
From Google Maps to a Fine-Grained Catalog of Street trees

Up-to-date catalogs of the urban tree population are important for munic...
10/07/2019 ∙ by Steve Branson, et al. ∙ 21 ∙ share

read it
Synthetic Examples Improve Generalization for Rare Classes

The ability to detect and classify rare occurrences in images has import...
04/11/2019 ∙ by Sara Beery, et al. ∙ 18 ∙ share

read it
Anchor Loss: Modulating Loss Scale based on Prediction Difficulty

We propose a novel loss function that dynamically rescales the cross ent...
09/24/2019 ∙ by Serim Ryou, et al. ∙ 16 ∙ share

read it
Geocoding of trees from street addresses and street-level images

We introduce an approach for updating older tree inventories with geogra...
02/05/2020 ∙ by Daniel Laumer, et al. ∙ 16 ∙ share

read it
HMM-guided frame querying for bandwidth-constrained video search

We design an agent to search for frames of interest in video stored on a...
12/31/2019 ∙ by Bhairav Chidambaram, et al. ∙ 11 ∙ share

read it
Task2Vec: Task Embedding for Meta-Learning

We introduce a method to provide vectorial representations of visual cla...
02/10/2019 ∙ by Alessandro Achille, et al. ∙ 10 ∙ share

read it
Recognition in Terra Incognita

It is desirable for detection and classification algorithms to generaliz...
07/13/2018 ∙ by Sara Beery, et al. ∙ 4 ∙ share

read it
The iWildCam 2019 Challenge Dataset

Camera Traps (or Wild Cams) enable the automatic collection of large qua...
07/15/2019 ∙ by Sara Beery, et al. ∙ 2 ∙ share

read it
Context Embedding Networks

Low dimensional embeddings that capture the main variations of interest ...
09/22/2017 ∙ by Kun ho Kim, et al. ∙ 0 ∙ share

read it
The Devil is in the Tails: Fine-grained Classification in the Wild

The world is long-tailed. What does this mean for computer vision and vi...
09/05/2017 ∙ by Grant Van Horn, et al. ∙ 0 ∙ share

read it
The iNaturalist Challenge 2017 Dataset

Existing image classification datasets used in computer vision tend to h...
07/20/2017 ∙ by Grant Van Horn, et al. ∙ 0 ∙ share

read it
Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation

We propose a new method to analyze the impact of errors in algorithms fo...
07/17/2017 ∙ by Matteo Ruggero Ronchi, et al. ∙ 0 ∙ share

read it
Estimating Causal Direction and Confounding of Two Discrete Variables

We propose a method to classify the causal relationship between two disc...
11/04/2016 ∙ by Krzysztof Chalupka, et al. ∙ 0 ∙ share

read it
Deciding How to Decide: Dynamic Routing in Artificial Neural Networks

We propose and systematically evaluate three strategies for training dyn...
03/17/2017 ∙ by Mason McGill, et al. ∙ 0 ∙ share

read it
Unsupervised Discovery of El Nino Using Causal Feature Learning on Microlevel Climate Data

We show that the climate phenomena of El Nino and La Nina arise naturall...
05/30/2016 ∙ by Krzysztof Chalupka, et al. ∙ 0 ∙ share

read it
Learning recurrent representations for hierarchical behavior modeling

We propose a framework for detecting action patterns from motion sequenc...
11/01/2016 ∙ by Eyrun Eyjolfsdottir, et al. ∙ 0 ∙ share

read it
Multi-Level Cause-Effect Systems

We present a domain-general account of causation that applies to setting...
12/25/2015 ∙ by Krzysztof Chalupka, et al. ∙ 0 ∙ share

read it
Seeing into Darkness: Scotopic Visual Recognition

Images are formed by counting how many photons traveling from a given se...
10/03/2016 ∙ by Bo Chen, et al. ∙ 0 ∙ share

read it
Improved Multi-Class Cost-Sensitive Boosting via Estimation of the Minimum-Risk Class

We present a simple unified framework for multi-class cost-sensitive boo...
07/12/2016 ∙ by Ron Appel, et al. ∙ 0 ∙ share

read it
Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art

A video dataset that is designed to study fine-grained categorisation of...
05/20/2016 ∙ by David Hall, et al. ∙ 0 ∙ share

read it
Describing Common Human Visual Actions in Images

Which common human actions and interactions are recognizable in monocula...
06/07/2015 ∙ by Matteo Ruggero Ronchi, et al. ∙ 0 ∙ share

read it
Visual Causal Feature Learning

We provide a rigorous definition of the visual cause of a behavior that ...
12/07/2014 ∙ by Krzysztof Chalupka, et al. ∙ 0 ∙ share

read it
Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling

We frame the task of predicting a semantic labeling as a sparse reconstr...
10/16/2014 ∙ by Michael Maire, et al. ∙ 0 ∙ share

read it
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets

We propose an architecture for fine-grained visual categorization that a...
06/11/2014 ∙ by Steve Branson, et al. ∙ 0 ∙ share

read it
Microsoft COCO: Common Objects in Context

We present a new dataset with the goal of advancing the state-of-the-art...
05/01/2014 ∙ by Tsung-Yi Lin, et al. ∙ 0 ∙ share

read it
Semisupervised Classifier Evaluation and Recalibration

How many labeled examples are needed to estimate a classifier's performa...
10/08/2012 ∙ by Peter Welinder, et al. ∙ 0 ∙ share

read it
Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners

In real-world applications of education and human teaching, an effective...
02/14/2018 ∙ by Yuxin Chen, et al. ∙ 0 ∙ share

read it
Teaching Categories to Human Learners with Visual Explanations

We study the problem of computer-assisted teaching with explanations. Co...
02/20/2018 ∙ by Oisin Mac Aodha, et al. ∙ 0 ∙ share

read it
Fast Conditional Independence Test for Vector Variables with Large Sample Sizes

We present and evaluate the Fast (conditional) Independence Test (FIT) -...
04/08/2018 ∙ by Krzysztof Chalupka, et al. ∙ 0 ∙ share

read it
It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data

We address the problem of 3D human pose estimation from 2D input images ...
05/17/2018 ∙ by Matteo Ruggero Ronchi, et al. ∙ 0 ∙ share

read it
Teaching Multiple Concepts to Forgetful Learners

How can we help a forgetful learner learn multiple concepts within a lim...
05/21/2018 ∙ by Anette Hunziker, et al. ∙ 0 ∙ share

read it
The iWildCam 2018 Challenge Dataset

Camera traps are a valuable tool for studying biodiversity, but research...
04/11/2019 ∙ by Sara Beery, et al. ∙ 0 ∙ share

read it
Presence-Only Geographical Priors for Fine-Grained Image Classification

Appearance information alone is often not sufficient to accurately diffe...
06/12/2019 ∙ by Oisin Mac Aodha, et al. ∙ 0 ∙ share

read it

Pietro Perona

Featured Co-authors