Related papers: Dual Prototypes for Adaptive Pre-Trained Model in …
Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves…
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…
In this work we introduce an incremental learning framework for Click-Through-Rate (CTR) prediction and demonstrate its effectiveness for Taboola's massive-scale recommendation service. Our approach enables rapid capture of emerging trends…
Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task…
This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data…
Multi-task learning (MTL) is a machine learning paradigm that aims to improve the generalization performance of a model on multiple related tasks by training it simultaneously on those tasks. Unlike MTL, where the model has instant access…
The online learning of deep neural networks is an interesting problem of machine learning because, for example, major IT companies want to manage the information of the massive data uploaded on the web daily, and this technology can…
With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…
Continual learning (or class incremental learning) is a realistic learning scenario for computer vision systems, where deep neural networks are trained on episodic data, and the data from previous episodes are generally inaccessible to the…
Autonomous systems (AS) often use Deep Neural Network (DNN) classifiers to allow them to operate in complex, high-dimensional, non-linear, and dynamically changing environments. Due to the complexity of these environments, DNN classifiers…
Significant advancements have been made in single label incremental learning (SLCIL),yet the more practical and challenging multi label class incremental learning (MLCIL) remains understudied. Recently,visual language models such as CLIP…
Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However,…
The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…
Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired knowledge. Recently, Parameter-Efficient Fine-Tuning (PEFT)…
In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's transferability towards the continually changing target domain.…
In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…
Class-Incremental learning (CIL) refers to the ability of artificial agents to integrate new classes as they appear in a stream. It is particularly interesting in evolving environments where agents have limited access to memory and…
Conventional online multi-task learning algorithms suffer from two critical limitations: 1) Heavy communication caused by delivering high velocity of sequential data to a central machine; 2) Expensive runtime complexity for building task…
Existing federated learning methods have effectively dealt with decentralized learning in scenarios involving data privacy and non-IID data. However, in real-world situations, each client dynamically learns new classes, requiring the global…
This article focuses on making discrete-time Adaptive Iterative Learning Control (ILC) more effective using multiple estimation models. Existing strategies use the tracking error to adjust the parametric estimates. Our strategy uses the…