Search Results for author:
Found 7 papers, 3 papers with code
Improving Plasticity in Online Continual Learning via Collaborative Learning
To this end, we propose Collaborative Continual Learning (CCL), a collaborative learning based strategy to improve the model's capability in acquiring new concepts.
Rethinking Momentum Knowledge Distillation in Online Continual Learning
While Knowledge Distillation (KD) has been extensively used in offline Continual Learning, it remains under-exploited in OCL, despite its potential.
Online Open-set Semi-supervised Object Detection with Dual Competing Head
To alleviate these issues, this paper proposes an end-to-end online OSSOD framework that improves performance and efficiency: 1) We propose a semi-supervised outlier filtering method that more effectively filters the OOD instances using both labeled and unlabeled data.
MetaMixer: A Regularization Strategy for Online Knowledge Distillation
Online knowledge distillation (KD) has received increasing attention in recent years.
Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval
Our model consistently outperforms existing attention based methods when assessed on the FashionAI (62. 8788% in MAP), DeepFashion (8. 9804% in MAP), and Zappos50k datasets (93. 32% in Prediction accuracy).
Semi-supervised Fashion Compatibility Prediction by Color Distortion Prediction
In this paper, we propose a general color distortion prediction task forcing the baseline to recognize low-level image information to learn more discriminative representation for fashion compatibility prediction.
SAT: Self-adaptive training for fashion compatibility prediction
Then, we propose a self-adaptive triplet loss (SATL), where the DS of the outfit is considered.
