Related papers: Boosting Domain Incremental Learning: Selecting th…
Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform…
Cross-domain imitation learning (CDIL) accelerates policy learning by transferring expert knowledge across domains, which is valuable in applications where the collection of expert data is costly. Existing methods are either supervised,…
Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a…
Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training…
Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. To compensate for the over-parameterized models, numerous regularization techniques have been introduced such as those based on dropout.…
While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient…
Despite deep learning's broad success, its abstract-reasoning bottleneck persists. We tackle Raven's Progressive Matrices (RPM), the benchmark for pattern, reasoning and problem-solving intelligence. We model the full causal chain image…
While computer vision and machine learning have made great progress, their robustness is still challenged by two key issues: data distribution shift and label noise. When domain generalization (DG) encounters noise, noisy labels further…
Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a…
Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the distribution of the…
Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging. These methods can be broadly divided into two groups: (1) learn a network to map measurements to the signal…
Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…
Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data selection methods suffer from severe domain specificity:…
Domain adaptive person Re-Identification (ReID) is challenging owing to the domain gap and shortage of annotations on target scenarios. To handle those two challenges, this paper proposes a coupling optimization method including the…
This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…
With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three…
The area of domain adaptation has been instrumental in addressing the domain shift problem encountered by many applications. This problem arises due to the difference between the distributions of source data used for training in comparison…
Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them…
Large Language Models (LLMs) often suffer from performance degradation when faced with domain shifts, primarily due to catastrophic forgetting. In this work, we propose KILO (Knowledge-Instructed Learning for Continual Adaptation), a novel…
In the realm of class-incremental learning (CIL), alleviating the catastrophic forgetting problem is a pivotal challenge. This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting…