Related papers: Incremental Object Keypoint Learning
We propose a novel class incremental learning approach by incorporating a feature augmentation technique motivated by adversarial attacks. We employ a classifier learned in the past to complement training examples rather than simply play a…
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average…
Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…
Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…
Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data…
Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge. Several approaches have been proposed in the literature, such as experience rehearsal,…
Scenarios in which restrictions in data transfer and storage limit the possibility to compose a single dataset -- also exploiting different data sources -- to perform a batch-based training procedure, make the development of robust models…
Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…
Incremental Learning is well known machine learning approach wherein the weights of the learned model are dynamically and gradually updated to generalize on new unseen data without forgetting the existing knowledge. Incremental learning…
Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the…
Uncertainty estimation is at the core of Active Learning (AL). Most existing methods resort to complex auxiliary models and advanced training fashions to estimate uncertainty for unlabeled data. These models need special design and hence…
Category-level object pose estimation, which predicts the pose of objects within a known category without prior knowledge of individual instances, is essential in applications like warehouse automation and manufacturing. Existing methods…
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the…
Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the frame-level prediction paradigm to learn from the sparse…
In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…
Modern machine learning suffers from catastrophic forgetting when learning new classes incrementally. The performance dramatically degrades due to the missing data of old classes. Incremental learning methods have been proposed to retain…
We present Language-mediated, Object-centric Representation Learning (LORL), a paradigm for learning disentangled, object-centric scene representations from vision and language. LORL builds upon recent advances in unsupervised object…
Incremental learning often encounter challenges such as overfitting to new data and catastrophic forgetting of old data. Existing methods can effectively extend the model for new tasks while freezing the parameters of the old model, but…
The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of complete ground-truth labels throughout the training process,…