Related papers: P2DT: Mitigating Forgetting in task-incremental Le…

Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID information at the inference time. Recent vast pre-trained…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While excelling at zero-shot generation of robust behaviors, BFMs…

This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism, aimed at dynamically managing class information for better adaptation to streaming data. GCIL is one of the hot…

Large-scale pre-trained models (PTMs) provide remarkable zero-shot classification capability covering a wide variety of object classes. However, practical applications do not always require the classification of all kinds of objects, and…

The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

By learning a sequence of tasks continually, an agent in continual learning (CL) can improve the learning performance of both a new task and `old' tasks by leveraging the forward knowledge transfer and the backward knowledge transfer,…

Transfer learning paradigm has driven substantial advancements in various vision tasks. However, as state-of-the-art models continue to grow, classical full fine-tuning often becomes computationally impractical, particularly in multi-task…

Despite the recent advancements in offline reinforcement learning via supervised learning (RvS) and the success of the decision transformer (DT) architecture in various domains, DTs have fallen short in several challenging benchmarks. The…

Continual learning requires the model to maintain the learned knowledge while learning from a non-i.i.d data stream continually. Due to the single-pass training setting, online continual learning is very challenging, but it is closer to the…

Catastrophic forgetting is a problem caused by neural networks' inability to learn data in sequence. After learning two tasks in sequence, performance on the first one drops significantly. This is a serious disadvantage that prevents many…

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…

To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has made some progress. In contrast, video captioning is a more…

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…

Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned, termed "catastrophic forgetting". Many state-of-the-art solutions to continual learning rely on biasing and/or…

Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to…

Decision Transformer (DT), which employs expressive sequence modeling techniques to perform action generation, has emerged as a promising approach to offline policy optimization. However, DT generates actions conditioned on a desired future…

Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory…