Search Results for author:
Found 22 papers, 13 papers with code
Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards.
Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning
We assess the accuracy and computational cost of various continual learning techniques enhanced with early-exits and TLC across standard class-incremental learning benchmarks such as 10 split CIFAR100 and ImageNetSubset and show that TLC can achieve the accuracy of the standard methods using less than 70\% of their computations.
GUIDE: Guidance-based Incremental Learning with Diffusion Models
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten.
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know.
Revisiting Supervision for Continual Representation Learning
In the field of continual learning, models are designed to learn tasks one after the other.
Technical Report for ICCV 2023 Visual Continual Learning Challenge: Continuous Test-time Adaptation for Semantic Segmentation
Each sequence is composed of 401 images and starts with the source domain, then gradually drifts to a different one (changing weather or time of day) until the middle of the sequence.
Bayesian Flow Networks in Continual Learning
Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type.
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous.
AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation
Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision.
Looking through the past: better knowledge retention for generative replay in continual learning
We notice that in VAE-based generative replay, this could be attributed to the fact that the generated features are far from the original ones when mapped to the latent space.
Generalized Continual Category Discovery
However, these settings are not well aligned with real-life scenarios, where a learning agent has access to a vast amount of unlabeled data encompassing both novel (entirely unlabeled) classes and examples from known classes.
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting.
MM-GEF: Multi-modal representation meet collaborative filtering
In modern e-commerce, item content features in various modalities offer accurate yet comprehensive information to recommender systems.
Augmentation-aware Self-supervised Learning with Conditioned Projector
By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with supervised approaches.
ICICLE: Interpretable Class Incremental Continual Learning
Continual learning enables incremental learning of new tasks without forgetting those previously learned, resulting in positive knowledge transfer that can enhance performance on both new and old tasks.
Online Meta-Learning for Model Update Aggregation in Federated Learning for Click-Through Rate Prediction
In Federated Learning (FL) of click-through rate (CTR) prediction, users' data is not shared for privacy protection.
Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training
The data augmentations used are of crucial importance to the quality of learned feature representations.
On the importance of cross-task features for class-incremental learning
We also define a new forgetting measure for class-incremental learning, and see that forgetting is not the principal cause of low performance.
Metric Learning for Session-based Recommendations
Session-based recommenders, used for making predictions out of users' uninterrupted sequences of actions, are attractive for many applications.
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
We call our method Recurrent Attention to Transient Tasks (RATT), and also show how to adapt continual learning approaches based on weight egularization and knowledge distillation to recurrent continual learning problems.
On Class Orderings for Incremental Learning
The influence of class orderings in the evaluation of incremental learning has received very little attention.
Semantic Drift Compensation for Class-Incremental Learning
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
