Search Results for author:
Found 26 papers, 17 papers with code
Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning
Class prototypes are evolved continually in the same latent space, enabling learning and prediction at any point.
Calibrated Out-of-Distribution Detection with a Generic Representation
In this work, we take a different approach and propose to leverage generic pre-trained representations.
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
In this work, we develop a baseline method, First Session Adaptation (FSA), that sheds light on the efficacy of existing CIL approaches and allows us to assess the relative performance contributions from head and body adaption.
Contrastive Classification and Representation Learning with Probabilistic Interpretation
In this work, we investigate the possibility of learning both the representation and the classifier using one objective function that combines the robustness of contrastive learning and the probabilistic interpretation of cross entropy loss.
A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning
With the success of pretraining techniques in representation learning, a number of continual learning methods based on pretrained models have been proposed.
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
Continual Learning research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks.
New Insights on Reducing Abrupt Representation Change in Online Continual Learning
In this work, we focus on the change in representations of observed data that arises when previously unobserved classes appear in the incoming data stream, and new classes must be distinguished from previous ones.
Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection
In order to robustly deploy object detectors across a wide range of scenarios, they should be adaptable to shifts in the input distribution without the need to constantly annotate new data.
Multi-Source Unsupervised Domain Adaptation
Object Detection
+1
Continual Novelty Detection
This work identifies the crucial link between the two problems and investigates the Novelty Detection problem under the Continual Learning setting.
New Insights on Reducing Abrupt Representation Change in Online Continual Learning
In this work, we focus on the change in representations of observed data that arises when previously unobserved classes appear in the incoming data stream, and new classes must be distinguished from previous ones.
Road Anomaly Detection by Partial Image Reconstruction With Segmentation Coupling
To that end, we propose a reconstruction module that can be used with many existing semantic segmentation networks, and that is trained to recognize and reconstruct road (drivable) surface from a small bottleneck.
Identifying Wrongly Predicted Samples: A Method for Active Learning
State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance.
Online Continual Learning with Maximal Interfered Retrieval
Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks.
Continual Learning in Neural Networks
A key component of such a never-ending learning process is to overcome the catastrophic forgetting of previously seen data, a problem that neural networks are well known to suffer from.
A continual learning survey: Defying forgetting in classification tasks
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase.
Online Continual Learning with Maximally Interfered Retrieval
Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks.
Gradient based sample selection for online continual learning
To prevent forgetting, a replay buffer is usually employed to store the previous data for the purpose of rehearsal.
Exploring the Challenges towards Lifelong Fact Learning
So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups.
Task-Free Continual Learning
A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or future tasks.
Selfless Sequential Learning
In particular, we propose a novel regularizer, that encourages representation sparsity by means of neural inhibition.
Memory Aware Synapses: Learning what (not) to forget
We show state-of-the-art performance and, for the first time, the ability to adapt the importance of the parameters based on unlabeled data towards what the network needs (not) to forget, which may vary depending on test conditions.
Encoder Based Lifelong Learning
This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks.
Who's that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images
In this work, we aim at automatically labeling actors in a TV series.
Expert Gate: Lifelong Learning with a Network of Experts
Further, the autoencoders inherently capture the relatedness of one task to another, based on which the most relevant prior model to be used for training a new expert, with finetuning or learning without-forgetting, can be selected.
Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
To this end, we first analyze the output of each convolutional layer from a domain adaptation perspective.
Landmarks-Based Kernelized Subspace Alignment for Unsupervised Domain Adaptation
Domain adaptation (DA) has gained a lot of success in the recent years in computer vision to deal with situations where the learning process has to transfer knowledge from a source to a target domain.
