1.7k citations
- Huawei Technologies (China)CN34 papers
- University of OttawaCA18 papers
- University of AlbertaCA13 papers
- Queen's UniversityCA12 papers
- McGill UniversityCA11 papers
- University of WaterlooCA11 papers
- University of TorontoCA10 papers
- University of British ColumbiaCA8 papers
- Carleton UniversityCA6 papers
- McMaster UniversityCA5 papers
- Simon Fraser UniversityCA5 papers
- York UniversityCA5 papers
12 papers · 1 filter
Multi-label Cluster Discrimination for Visual Representation Learning
Xiang An, Kaicheng Yang, Xiangzi Dai +2
Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive lea…
AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
Keith G. Mills, Di Niu, Mohammad Salameh +6
Evaluating neural network performance is critical to deep neural network design but a costly procedure. Neural predictors provide an efficient solution by treating architectures as…
SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding
Morgan Heisler, Amin Banitalebi-Dehkordi, Yong Zhang
Data augmentation is an essential technique in improving the generalization of deep neural networks. The majority of existing image-domain augmentations either rely on geometric an…
Cascading Convolutional Temporal Colour Constancy
Matteo Rizzo, Cristina Conati, Daesik Jang +1
Computational Colour Constancy (CCC) consists of estimating the colour of one or more illuminants in a scene and using them to remove unwanted chromatic distortions. Much research…
Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions
Ryan Razani, Ran Cheng, Ehsan Taghavi +1
Autonomous driving vehicles and robotic systems rely on accurate perception of their surroundings. Scene understanding is one of the crucial components of perception modules. Among…
S3Net: 3D LiDAR Sparse Semantic Segmentation Network
Ran Cheng, Ryan Razani, Yuan Ren +1
Semantic Segmentation is a crucial component in the perception systems of many applications, such as robotics and autonomous driving that rely on accurate environmental perception…