Related papers: Candidate Pseudolabel Learning: Enhancing Vision-L…

Vision language models (VLMs) like CLIP show stellar zero-shot capability on classification benchmarks. However, selecting the VLM with the highest performance on the unlabeled downstream task is non-trivial. Existing VLM selection methods…

Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…

Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Semi-supervised learning (SSL) leverages abundant unlabeled data alongside limited labeled data to enhance learning. As vision foundation models (VFMs) increasingly serve as the backbone of vision applications, it remains unclear how SSL…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…

Partial-label learning is a popular weakly supervised learning setting that allows each training example to be annotated with a set of candidate labels. Previous studies on partial-label learning only focused on the classification setting…

Fine-tuning pre-trained language models (PLMs) has demonstrated its effectiveness on various downstream NLP tasks recently. However, in many low-resource scenarios, the conventional fine-tuning strategies cannot sufficiently capture the…

Finding relevant and high-quality datasets to train machine learning models is a major bottleneck for practitioners. Furthermore, to address ambitious real-world use-cases there is usually the requirement that the data come labelled with…

Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot select the most…

Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…

Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is…

Change Detection (CD) aims to identify pixels with semantic changes between images. However, annotating massive numbers of pixel-level images is labor-intensive and costly, especially for multi-temporal images, which require pixel-wise…

Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for addressing label-scarce scenarios. Recently, growing attention has been given to combining…

Current long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.e., long-tailed, uniform, or inverse long-tailed). However,…

Unsupervised Federated Learning (UFL) aims to collaboratively train a global model across distributed clients without sharing data or accessing label information. Previous UFL works have predominantly focused on representation learning and…

The current dominant approach for neural speech enhancement is via purely-supervised deep learning on simulated pairs of far-field noisy-reverberant speech (i.e., mixtures) and clean speech. The trained models, however, often exhibit…

Detection of anomalous events in videos is an important problem in applications such as surveillance. Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings. However, fully…

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…