相关论文: Learning from Noisy Preferences: A Semi-Supervised…

Semi-supervised learning methods are usually employed in the classification of data sets where only a small subset of the data items is labeled. In these scenarios, label noise is a crucial issue, since the noise may easily spread to a…

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels,…

Direct Preference Optimization (DPO) controls the trade-off between fitting preference labels and staying close to a reference model using a single global temperature beta, implicitly treating all preference pairs as equally informative.…

While supervised learning has achieved remarkable success, obtaining large-scale labeled datasets in biomedical imaging is often impractical due to high costs and the time-consuming annotations required from radiologists. Semi-supervised…

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement…

Computer vision systems recently made a big leap thanks to deep neural networks. However, these systems require correctly labeled large datasets in order to be trained properly, which is very difficult to obtain for medical applications.…

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-scale finetuning often shows a generalization gap. We take…

Conventional multi-label recognition methods often focus on label confidence, frequently overlooking the pivotal role of partial order relations consistent with human preference. To resolve these issues, we introduce a novel method for…

Training deep neural networks(DNN) with noisy labels is challenging since DNN can easily memorize inaccurate labels, leading to poor generalization ability. Recently, the meta-learning based label correction strategy is widely adopted to…

Direct Preference Optimization (DPO) trains a language model using human preference data, bypassing the explicit reward modeling phase of Reinforcement Learning from Human Feedback (RLHF). By iterating over sentence pairs in a preference…

Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance. Self-supervised learning…

In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators. With the emergence of high-performance pre-trained vision-language models…

Direct Preference Optimization (DPO) has emerged as a simple and effective approach for aligning large language models (LLMs) with human preferences, bypassing the need for a learned reward model. Despite its growing adoption, a fundamental…

Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…

Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the prevalent…

In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled…

Person re-identification aims to match a person's identity across multiple camera streams. Deep neural networks have been successfully applied to the challenging person re-identification task. One remarkable bottleneck is that the existing…

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…