research
∙
05/19/2023
AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
Continual learning aims to enable a model to incrementally learn knowled...
share
research
∙
04/23/2023
PiClick: Picking the desired mask in click-based interactive segmentation
Click-based interactive segmentation enables productive pixel-level anno...
research
∙
03/09/2023
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
The goal of continual learning is to improve the performance of recognit...
research
∙
11/28/2022
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a...
research
∙
06/04/2021
Few-Shot Segmentation via Cycle-Consistent Transformer
Few-shot segmentation aims to train a segmentation model that can fast a...
research
∙
10/31/2020
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
Domain adaptive semantic segmentation aims to train a model performing s...
research
∙
02/01/2020
Training-free Monocular 3D Event Detection System for Traffic Surveillance
We focus on the problem of detecting traffic events in a surveillance sc...
research
∙
08/06/2019
Attract or Distract: Exploit the Margin of Open Set
Open set domain adaptation aims to diminish the domain shift across doma...
research
∙
04/17/2019
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
Industrial recommender systems usually consist of the matching stage and...
research
∙
04/13/2019
Shakeout: A New Approach to Regularized Deep Neural Network Training
Recent years have witnessed the success of deep neural networks in deali...
research
∙
01/04/2019
Contrastive Adaptation Network for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) makes predictions for the target do...
research
∙
08/22/2018
Progressive Deep Neural Networks Acceleration via Soft Filter Pruning
This paper proposed a Progressive Soft Filter Pruning method (PSFP) to p...
research
∙
08/21/2018
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
This paper proposed a Soft Filter Pruning (SFP) method to accelerate the...
research
∙
07/24/2018
Self-produced Guidance for Weakly-supervised Object Localization
Weakly supervised methods usually generate localization results based on...
research
∙
01/30/2018
Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
In this paper we make two contributions to unsupervised domain adaptatio...
research
∙
11/19/2017
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
Person re-identification (re-ID) models trained on one domain often fail...
research
∙
09/22/2017
EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
For most state-of-the-art architectures, Rectified Linear Unit (ReLU) be...
research
∙
07/22/2017