no code implementations • ICCV 2023 • Daiqing Li, Huan Ling, Amlan Kar, David Acuna, Seung Wook Kim, Karsten Kreis, Antonio Torralba, Sanja Fidler
In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones.
3 code implementations • 26 Sep 2022 • Ahmad Darkhalil, Dandan Shan, Bin Zhu, Jian Ma, Amlan Kar, Richard Higgins, Sanja Fidler, David Fouhey, Dima Damen
VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets.
no code implementations • 8 Feb 2022 • Cinjon Resnick, Or Litany, Amlan Kar, Karsten Kreis, James Lucas, Kyunghyun Cho, Sanja Fidler
Our main contribution is a pseudo-automatic method to discover such groups in foresight by performing causal interventions on simulated scenes.
1 code implementation • NeurIPS 2021 • Despoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis, Andreas Geiger, Sanja Fidler
The ability to synthesize realistic and diverse indoor furniture layouts automatically or based on partial input, unlocks many applications, from better interactive 3D tools to data synthesis for training and simulation.
Ranked #3 on Indoor Scene Synthesis on PRO-teXt
2D Semantic Segmentation task 1 (8 classes) 3D Semantic Scene Completion +1
no code implementations • 29 Sep 2021 • Cinjon Resnick, Or Litany, Amlan Kar, Karsten Kreis, James Lucas, Kyunghyun Cho, Sanja Fidler
We verify that the prioritized groups found via intervention are challenging for the object detector and show that retraining with data collected from these groups helps inordinately compared to adding more IID data.
1 code implementation • CVPR 2021 • Yuan-Hong Liao, Amlan Kar, Sanja Fidler
This is expensive, and guaranteeing the quality of the labels is a major challenge.
no code implementations • 1 Sep 2020 • Daiqing Li, Amlan Kar, Nishant Ravikumar, Alejandro F. Frangi, Sanja Fidler
Since the model of geometry and material is disentangled from the imaging sensor, it can effectively be trained across multiple medical centers.
no code implementations • ECCV 2020 • Tianchang Shen, Jun Gao, Amlan Kar, Sanja Fidler
We implement our framework as a web service and conduct a user study, where we show that user annotated data using our method effectively facilitates real-world learning tasks.
no code implementations • ECCV 2020 • Jeevan Devaranjan, Amlan Kar, Sanja Fidler
In Meta-Sim2, we aim to learn the scene structure in addition to parameters, which is a challenging problem due to its discrete nature.
no code implementations • CVPR 2020 • Jonah Philion, Amlan Kar, Sanja Fidler
The downside of these metrics is that, at worst, they penalize all incorrect detections equally without conditioning on the task or scene, and at best, heuristics need to be chosen to ensure that different mistakes count differently.
no code implementations • ICCV 2019 • Hang Chu, Daiqing Li, David Acuna, Amlan Kar, Maria Shugrina, Xinkai Wei, Ming-Yu Liu, Antonio Torralba, Sanja Fidler
We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts.
no code implementations • ICCV 2019 • Amlan Kar, Aayush Prakash, Ming-Yu Liu, Eric Cameracci, Justin Yuan, Matt Rusiniak, David Acuna, Antonio Torralba, Sanja Fidler
Training models to high-end performance requires availability of large labeled datasets, which are expensive to get.
1 code implementation • CVPR 2019 • David Acuna, Amlan Kar, Sanja Fidler
We further reason about true object boundaries during training using a level set formulation, which allows the network to learn from misaligned labels in an end-to-end fashion.
2 code implementations • CVPR 2019 • Huan Ling, Jun Gao, Amlan Kar, Wenzheng Chen, Sanja Fidler
Our model runs at 29. 3ms in automatic, and 2. 6ms in interactive mode, making it 10x and 100x faster than Polygon-RNN++.
1 code implementation • 1 Dec 2018 • Kevin Shen, Amlan Kar, Sanja Fidler
In order to bring artificial agents into our lives, we will need to go beyond supervised learning on closed datasets to having the ability to continuously expand knowledge.
no code implementations • 7 Jun 2018 • Maria Shugrina, Amlan Kar, Karan Singh, Sanja Fidler
Then, the user can adjust color sail parameters to change the base colors, their blending behavior and the number of colors, exploring a wide range of options for the original design.
3 code implementations • CVPR 2018 • David Acuna, Huan Ling, Amlan Kar, Sanja Fidler
Manually labeling datasets with object masks is extremely time consuming.
no code implementations • CVPR 2017 • Amlan Kar, Nishant Rai, Karan Sikka, Gaurav Sharma
We propose a novel method for temporally pooling frames in a video for the task of human action recognition.