Related papers: Learning New Tasks from a Few Examples with Soft-L…
Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes…
Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a…
Many real-world classification problems often have classes with very few labeled training samples. Moreover, all possible classes may not be initially available for training, and may be given incrementally. Deep learning models need to deal…
In this work, we propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning. Specifically, we exploit the easily available out-of-distribution samples to drive…
Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to…
Selecting an effective training signal for machine learning tasks is difficult: expert annotations are expensive, and crowd-sourced annotations may not be reliable. Recent work has demonstrated that learning from a distribution over labels…
Learning from Label Proportions (LLP) is a weakly supervised learning method that aims to perform instance classification from training data consisting of pairs of bags containing multiple instances and the class label proportions within…
This paper describes a method of domain adaptive training for semantic segmentation using multiple source datasets that are not necessarily relevant to the target dataset. We propose a soft pseudo-label generation method by integrating…
Few-shot NLP research is highly active, yet conducted in disjoint research threads with evaluation suites that lack challenging-yet-realistic testing setups and fail to employ careful experimental design. Consequently, the community does…
Thanks to the availability of powerful computing resources, big data and deep learning algorithms, we have made great progress on computer vision in the last few years. Computer vision systems begin to surpass humans in some tasks, such as…
Prompt-based learning, with its capability to tackle zero-shot and few-shot NLP tasks, has gained much attention in community. The main idea is to bridge the gap between NLP downstream tasks and language modeling (LM), by mapping these…
There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a…
We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as…
Large pretrained Transformer-based language models like BERT and GPT have changed the landscape of Natural Language Processing (NLP). However, fine tuning such models still requires a large number of training examples for each target task,…
Given base classes with sufficient labeled samples, the target of few-shot classification is to recognize unlabeled samples of novel classes with only a few labeled samples. Most existing methods only pay attention to the relationship…
The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen…
Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels…
Foundation Vision-Language Models (VLMs) like CLIP exhibit strong generalization capabilities due to large-scale pretraining on diverse image-text pairs. However, their performance often degrades when applied to target datasets with…
In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated data. The fine-tuning…
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…