activity
20152023
most citedCascade R-CNN: Delving into High Quality Object Detection

398 citations · 766 across the 26 of their papers we have counts for

collaborators
Showing 2020Show all

12 papers · 1 filter

cs.CV202019 cited

MicroNet: Towards Image Recognition with Extremely Low FLOPs

Yunsheng Li, Yinpeng Chen, Xiyang Dai +6

In this paper, we present MicroNet, which is an efficient convolutional neural network using extremely low computational cost (e.g. 6 MFLOPs on ImageNet classification). Such a low…

cs.CV202022 cited

Learning Representations from Audio-Visual Spatial Alignment

Pedro Morgado, Yi Li, Nuno Vasconcelos

We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondenc…

cs.CV2020

Contrastive Learning with Adversarial Examples

Chih-Hui Ho, Nuno Vasconcelos

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to defi…

cs.CV2020

Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings

Pedro Morgado, Yunsheng Li, Jose Costa Pereira +2

Image hash codes are produced by binarizing the embeddings of convolutional neural networks (CNN) trained for either classification or retrieval. While proxy embeddings achieve goo…

cs.CV20204 cited

Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier

Tz-Ying Wu, Pedro Morgado, Pei Wang +2

Long-tail recognition tackles the natural non-uniformly distributed data in real-world scenarios. While modern classifiers perform well on populated classes, its performance degrad…

cs.CV20205 cited

Few-Shot Open-Set Recognition using Meta-Learning

Bo Liu, Hao Kang, Haoxiang Li +2

The problem of open-set recognition is considered. While previous approaches only consider this problem in the context of large-scale classifier training, we seek a unified solutio…