202 citations · 507 across the 33 of their papers we have counts for
33 papers
Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing
Chenxu Peng, Chongtian zhou, Dicheng Liu +5
Fusing standard RGB frames with asynchronous event streams has emerged as a definitive paradigm for robust perception in degraded environments. Although unified backbones have rece…
Position: Modular Memory is the Key to Continual Learning Agents
Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov +21
Foundation models have transformed machine learning through large-scale pretraining and increased test-time compute. Despite surpassing human performance in several domains, these…
Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
Yuyang Liu, Qiuhe Hong, Linlan Huang +6
Vision-language models (VLMs), spanning predictive architectures to generative Multimodal Large Language Models (MLLMs), have revolutionized artificial intelligence through powerfu…
Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion
Linlan Huang, Xusheng Cao, Haori Lu +1
Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement…
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
Zhengyuan Xie, Haiquan Lu, Jia-wen Xiao +3
Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prio…
Generative Multi-modal Models are Good Class-Incremental Learners
Xusheng Cao, Haori Lu, Linlan Huang +2
In class-incremental learning (CIL) scenarios, the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant chall…
GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Enguang Wang, Zhimao Peng, Zhengyuan Xie +3
Given unlabelled datasets containing both old and new categories, generalized category discovery (GCD) aims to accurately discover new classes while correctly classifying old class…
Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning
Jiang-Tian Zhai, Xialei Liu, Lu Yu +1
Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty…
Class Incremental Learning with Pre-trained Vision-Language Models
Xialei Liu, Xusheng Cao, Haori Lu +3
With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exp…
Masked Autoencoders are Efficient Class Incremental Learners
Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov +2
Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) a…
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
Xin Jin, Jia-Wen Xiao, Ling-Hao Han +4
Explicit calibration-based methods have dominated RAW image denoising under extremely low-light environments. However, these methods are impeded by several critical limitations: a)…
Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
Xialei Liu, Jiang-Tian Zhai, Andrew D. Bagdanov +2
Exemplar-free Class Incremental Learning (EFCIL) aims to sequentially learn tasks with access only to data from the current one. EFCIL is of interest because it mitigates concerns…
Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
Kai Wang, Chenshen Wu, Andy Bagdanov +4
Lifelong object re-identification incrementally learns from a stream of re-identification tasks. The objective is to learn a representation that can be applied to all tasks and tha…
Long-Tailed Class Incremental Learning
Xialei Liu, Yu-Song Hu, Xu-Sheng Cao +3
In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distrib…
Universal Representations: A Unified Look at Multiple Task and Domain Learning
Wei-Hong Li, Xialei Liu, Hakan Bilen
We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems s…
Representation Compensation Networks for Continual Semantic Segmentation
Chang-Bin Zhang, Jia-Wen Xiao, Xialei Liu +2
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetti…
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition
Kai Wang, Xialei Liu, Andy Bagdanov +3
Most meta-learning approaches assume the existence of a very large set of labeled data available for episodic meta-learning of base knowledge. This contrasts with the more realisti…
Learning Multiple Dense Prediction Tasks from Partially Annotated Data
Wei-Hong Li, Xialei Liu, Hakan Bilen
Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient appro…
HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification
Kai Wang, Xialei Liu, Luis Herranz +1
Human beings learn and accumulate hierarchical knowledge over their lifetime. This knowledge is associated with previous concepts for consolidation and hierarchical construction. H…
Cross-domain Few-shot Learning with Task-specific Adapters
Wei-Hong Li, Xialei Liu, Hakan Bilen
In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples. R…
Universal Representation Learning from Multiple Domains for Few-shot Classification
Wei-Hong Li, Xialei Liu, Hakan Bilen
In this paper, we look at the problem of few-shot classification that aims to learn a classifier for previously unseen classes and domains from few labeled samples. Recent methods…
Self-Training for Class-Incremental Semantic Segmentation
Lu Yu, Xialei Liu, Joost van de Weijer
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer…
Class-incremental learning: survey and performance evaluation on image classification
Marc Masana, Xialei Liu, Bartlomiej Twardowski +3
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new…
Learning to Rank for Active Learning: A Listwise Approach
Minghan Li, Xialei Liu, Joost van de Weijer +1
Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous…