Search Results for author:
Found 10 papers, 4 papers with code
Benchmarking Data Efficiency and Computational Efficiency of Temporal Action Localization Models
This work explores and measures how current deep temporal action localization models perform in settings constrained by the amount of data or computational power.
Using and Abusing Equivariance
In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries.
VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
The third edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop featured four data-impaired challenges, focusing on addressing the limitations of data availability in training deep learning models for computer vision tasks.
Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation
For unsupervised semantic segmentation of urban scenes, our method surpasses the previous state-of-the-art baseline by +7. 14% in mIoU on Cityscapes and +6. 65% on KITTI.
VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samples for various key computer vision tasks.
Domain Adaptation for Rare Classes Augmented with Synthetic Samples
While domain adaptation is generally applied on completely synthetic source domains and real target domains, we explore how domain adaptation can be applied when only a single rare class is augmented with simulated samples.
Zero-Shot Day-Night Domain Adaptation with a Physics Prior
The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set.
Ranked #2 on
Image Retrieval
on 24/7 Tokyo
Exploiting Learned Symmetries in Group Equivariant Convolutions
Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost.
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
We present the first edition of "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges.
Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification task
In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them.
