Search Results for author:
Found 11 papers, 6 papers with code
DiaLoc: An Iterative Approach to Embodied Dialog Localization
However, most existing works in embodied dialog research focus on navigation and leave the localization task understudied.
Revisiting Recurrent Reinforcement Learning with Memory Monoids
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states.
ReCoRe: Regularized Contrastive Representation Learning of World Model
To address these challenges, we present a world model that learns invariant features using (i) contrastive unsupervised learning and (ii) an intervention-invariant regularizer.
POPGym: Benchmarking Partially Observable Reinforcement Learning
Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory.
Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval
In global consistent quantization, we employ contrastive learning for both embedding and quantized representations and fuses these representations for consistent contrastive regularization between instances.
Graph Convolutional Memory using Topological Priors
Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world.
Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
We present NavACL, a method of automatic curriculum learning tailored to the navigation task.
Orientation-aware Semantic Segmentation on Icosahedron Spheres
For the spherical domain, several methods recently adopt an icosahedron mesh, but systems are typically rotation invariant or require significant memory and parameters, thus enabling execution only at very low resolutions.
Ranked #21 on
Semantic Segmentation
on Stanford2D3D Panoramic
Fast-SCNN: Fast Semantic Segmentation Network
The encoder-decoder framework is state-of-the-art for offline semantic image segmentation.
Ranked #7 on
Semantic Segmentation
on SynPASS
ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time
Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets.
Ranked #79 on
Semantic Segmentation
on Cityscapes val
Full-Angle Quaternions for Robustly Matching Vectors of 3D Rotations
In this paper we introduce a new distance for robustly matching vectors of 3D rotations.
