相关论文: LT-Soups: Bridging Head and Tail Classes via Subsa…

Training large foundation models from scratch for domain-specific applications is almost impossible due to data limits and long-tailed distributions -- taking remote sensing (RS) as an example. Fine-tuning natural image pre-trained models…

Large language models are increasingly adapted to downstream tasks through fine-tuning. Full supervised fine-tuning (SFT) and parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), are two dominant approaches.…

Long-tailed semi-supervised learning (LTSSL) presents a formidable challenge where models must overcome the scarcity of tail samples while mitigating the noise from unreliable pseudo-labels. Most prior LTSSL methods are designed to train…

The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remains unexplored. In…

Parameter-efficient fine-tuning (PEFT) has attracted significant attention due to the growth of pre-trained model sizes and the need to fine-tune (FT) them for superior downstream performance. Despite a surge in new PEFT methods, a…

Food classification serves as the basic step of image-based dietary assessment to predict the types of foods in each input image. However, food image predictions in a real world scenario are usually long-tail distributed among different…

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage…

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified.…

Transfer learning via fine-tuning pre-trained transformer models has gained significant success in delivering state-of-the-art results across various NLP tasks. In the absence of centralized data, Federated Learning (FL) can benefit from…

Federated learning offers a paradigm to the challenge of preserving privacy in distributed machine learning. However, datasets distributed across each client in the real world are inevitably heterogeneous, and if the datasets can be…

Recently, we have observed that Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world, unlocking new possibilities across various multi-modal applications. To adapt LMMs for downstream tasks,…

The large models, as predicted by scaling raw forecasts, have made groundbreaking progress in many fields, particularly in natural language generation tasks, where they have approached or even surpassed human levels. However, the…

The entry of large language models (LLMs) into research and commercial spaces has led to a trend of ever-larger models, with initial promises of generalisability, followed by a widespread desire to downsize and create specialised models…

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We…

Imbalanced classification datasets pose significant challenges in machine learning, often leading to biased models that perform poorly on underrepresented classes. With the rise of foundation models, recent research has focused on the full,…

Large language models have recently surpassed specialized systems on code generation, yet their effectiveness on other code-analysis tasks remains less clear. At the same time, multi-task learning offers a way to unify diverse objectives…

Parameter Efficient Finetuning (PEFT) has emerged as a viable solution for improving the performance of Large Language Models (LLMs) without requiring massive resources and compute. Prior work on multilingual evaluation has shown that there…

The imbalanced distribution of long-tailed data presents a significant challenge for deep learning models, causing them to prioritize head classes while neglecting tail classes. Two key factors contributing to low recognition accuracy are…

Large models represent a groundbreaking advancement in multiple application fields, enabling remarkable achievements across various tasks. However, their unprecedented scale comes with significant computational costs. These models, often…

The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of…