Search Results for author: Kashyap Chitta

Found 12 papers, 5 papers with code

NEAT: Neural Attention Fields for End-to-End Autonomous Driving

1 code implementation9 Sep 2021 Kashyap Chitta, Aditya Prakash, Andreas Geiger

Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving.

Autonomous Driving Imitation Learning

Benchmarking Unsupervised Object Representations for Video Sequences

1 code implementation12 Jun 2020 Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker

Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding.

Multi-Object Tracking Object Detection +1

Label Efficient Visual Abstractions for Autonomous Driving

2 code implementations20 May 2020 Aseem Behl, Kashyap Chitta, Aditya Prakash, Eshed Ohn-Bar, Andreas Geiger

Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.

Autonomous Driving Semantic Segmentation

Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions

1 code implementation27 Jul 2019 Kashyap Chitta, Jose M. Alvarez, Martial Hebert

Semantic segmentation with Convolutional Neural Networks is a memory-intensive task due to the high spatial resolution of feature maps and output predictions.

Scene Parsing Semantic Segmentation

Training Data Subset Search with Ensemble Active Learning

no code implementations29 May 2019 Kashyap Chitta, Jose M. Alvarez, Elmar Haussmann, Clement Farabet

In this paper, we propose to scale up ensemble Active Learning (AL) methods to perform acquisition at a large scale (10k to 500k samples at a time).

Active Learning Autonomous Driving +2

Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels

no code implementations8 Nov 2018 Kashyap Chitta, Jianwei Feng, Martial Hebert

With our design, the network progressively learns features specific to the target domain using annotation from only the source domain.

Semantic Segmentation Unsupervised Domain Adaptation

Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization

no code implementations6 Nov 2018 Kashyap Chitta, Jose M. Alvarez, Adam Lesnikowski

In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep Bayesian Neural Network (BNN).

Active Learning General Classification +1

Targeted Kernel Networks: Faster Convolutions with Attentive Regularization

no code implementations1 Jun 2018 Kashyap Chitta

We propose Attentive Regularization (AR), a method to constrain the activation maps of kernels in Convolutional Neural Networks (CNNs) to specific regions of interest (ROIs).

Learning Sampling Policies for Domain Adaptation

no code implementations19 May 2018 Yash Patel, Kashyap Chitta, Bhavan Jasani

We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning.

Classification Domain Adaptation +2

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