Search Results for author:
Found 22 papers, 10 papers with code
PANDAS: Prototype-based Novel Class Discovery and Detection
In this work, we look at ways to extend a detector trained for a set of base classes so it can i) spot the presence of novel classes, and ii) automatically enrich its repertoire to be able to detect those newly discovered classes together with the base ones.
Continual Learning: Applications and the Road Forward
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past.
How Efficient Are Today's Continual Learning Algorithms?
There is more to continual learning than mitigating catastrophic forgetting.
SIESTA: Efficient Online Continual Learning with Sleep
Compared to REMIND and prior arts, SIESTA is far more computationally efficient, enabling continual learning on ImageNet-1K in under 2 hours on a single GPU; moreover, in the augmentation-free setting it matches the performance of the offline learner, a milestone critical to driving adoption of continual learning in real-world applications.
System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
In this paper, we introduce the Lifelong Reinforcement Learning Components Framework (L2RLCF), which standardizes L2RL systems and assimilates different continual learning components (each addressing different aspects of the lifelong learning problem) into a unified system.
Online Continual Learning for Embedded Devices
Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets.
Can I see an Example? Active Learning the Long Tail of Attributes and Relations
Using this framing, we introduce an active sampling method that asks for examples from the tail of the data distribution and show that it outperforms classical active learning methods on Visual Genome.
Disentangling Transfer and Interference in Multi-Domain Learning
Humans are incredibly good at transferring knowledge from one domain to another, enabling rapid learning of new tasks.
Avalanche: an End-to-End Library for Continual Learning
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning.
Replay in Deep Learning: Current Approaches and Missing Biological Elements
Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences.
Self-Supervised Training Enhances Online Continual Learning
In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting.
Selective Replay Enhances Learning in Online Continual Analogical Reasoning
Analogical reasoning tests such as Raven's Progressive Matrices (RPMs) are commonly used to measure non-verbal abstract reasoning in humans, and recently offline neural networks for the RPM problem have been proposed.
Improved Robustness to Open Set Inputs via Tempered Mixup
Supervised classification methods often assume that evaluation data is drawn from the same distribution as training data and that all classes are present for training.
RODEO: Replay for Online Object Detection
Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems.
Stream-51: Streaming Classification and Novelty Detection from Videos
In this work, we introduce Stream-51, a new dataset for streaming classification consisting of temporally correlated images from 51 distinct object categories and additional evaluation classes outside of the training distribution to test novelty recognition.
Do We Need Fully Connected Output Layers in Convolutional Networks?
Traditionally, deep convolutional neural networks consist of a series of convolutional and pooling layers followed by one or more fully connected (FC) layers to perform the final classification.
Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?
We found that input perturbation and temperature scaling yield the best performance on large scale datasets regardless of the feature space regularization strategy.
REMIND Your Neural Network to Prevent Catastrophic Forgetting
While there is neuroscientific evidence that the brain replays compressed memories, existing methods for convolutional networks replay raw images.
Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis
By combining streaming linear discriminant analysis with deep learning, we are able to outperform both incremental batch learning and streaming learning algorithms on both ImageNet ILSVRC-2012 and CORe50, a dataset that involves learning to classify from temporally ordered samples.
Memory Efficient Experience Replay for Streaming Learning
We find that full rehearsal can eliminate catastrophic forgetting in a variety of streaming learning settings, with ExStream performing well using far less memory and computation.
Compassionately Conservative Balanced Cuts for Image Segmentation
The Normalized Cut (NCut) objective function, widely used in data clustering and image segmentation, quantifies the cost of graph partitioning in a way that biases clusters or segments that are balanced towards having lower values than unbalanced partitionings.
Efficiently Computing Piecewise Flat Embeddings for Data Clustering and Image Segmentation
Image segmentation is a popular area of research in computer vision that has many applications in automated image processing.
