-
University of Pennsylvania
- Philadelphia
- https://shreyasskandan.github.io
Highlights
- Pro
Stars
This repository provides data for the VAW dataset as described in the CVPR 2021 paper titled "Learning to Predict Visual Attributes in the Wild" and the ECCV 2022 paper titled "Improving Closed and…
MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)
Pytorch implementation of One-Shot Affordance Detection
👽 Out-of-Distribution Detection with PyTorch
source code for NeurIPS'22 paper "SIREN: Shaping Representations for Detecting Out-of-Distribution Objects"
source code for CVPR'22 paper "Unknown-Aware Object Detection: Learning What You Don’t Know from Videos in the Wild"
[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer
(TPAMI 2021) iOD: Incremental Object Detection via Meta-Learning
Lvio-Fusion: A Self-adaptive Multi-sensor Fusion SLAM Framework Using Actor-critic Method (IROS 2021)
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
Python package for the evaluation of odometry and SLAM
A low latency decoder for Ouster Lidars
LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping
LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain
(TPAMI2022) The ImageNet-S benchmark/method for large-scale unsupervised/semi-supervised semantic segmentation.
Navigation and localisation dataset for self driving cars and autonomous robots
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Gradually-Warmup Learning Rate Scheduler for PyTorch
A deep learning-powered visual navigation engine to enables autonomous navigation of pocket-size quadrotor - running on PULP
Compute receptive fields of your favorite convnets
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.