Related papers: Data-Efficient Finetuning Using Cross-Task Nearest…
In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural…
We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks. This problem has broad applications in NLP, such as targeted instruction tuning and data selection in…
We propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning. Pre-finetuning is massively multi-task learning (around 50 datasets, over 4.8 million total labeled examples), and is…
Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples. An effective approach to few-shot classification involves a prior model trained on a large-sample base…
Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…
In recent years, multi-task prompt tuning has garnered considerable attention for its inherent modularity and potential to enhance parameter-efficient transfer learning across diverse tasks. This paper aims to analyze and improve the…
Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an unsolved problem with myriad challenges. A popular paradigm for tackling this problem is through leveraging large unlabeled datasets that have many…
We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…
Most few-shot learning techniques are pre-trained on a large, labeled "base dataset". In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training…
Data-efficient image classification using deep neural networks in settings, where only small amounts of labeled data are available, has been an active research area in the recent past. However, an objective comparison between published…
Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks…
Most of the recent few-shot learning (FSL) algorithms are based on transfer learning, where a model is pre-trained using a large amount of source data, and the pre-trained model is fine-tuned using a small amount of target data. In transfer…
In this work, we investigate multi-task learning as a way of pre-training models for classification tasks in digital pathology. It is motivated by the fact that many small and medium-size datasets have been released by the community over…
For the task of fine-grained entity typing (FET), due to the use of a large number of entity types, it is usually considered too costly to manually annotating a training dataset that contains an ample number of examples for each type. A…
Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the…
In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks.…
Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on…
Recently introduced instruction-paradigm empowers non-expert users to leverage NLP resources by defining a new task in natural language. Instruction-tuned models have significantly outperformed multitask learning models (without…
Despite the recent advances showing that a model pre-trained on large-scale source code data is able to gain appreciable generalization capability, it still requires a sizeable amount of data on the target task for fine-tuning. And the…
Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate…