Learning from True-False Labels via Multi-modal Prompt Retrieving

• URL: http://arxiv.org/abs/2405.15228v1
• Date: Fri, 24 May 2024 05:39:15 GMT
• Title: Learning from True-False Labels via Multi-modal Prompt Retrieving
• Authors: Zhongnian Li, Jinghao Xu, Peng Ying, Meng Wei, Tongfeng Sun, Xinzheng Xu,
• Abstract summary: We propose a novel weakly supervised labeling setting, namely True-False Labels (TFLs) which can achieve high accuracy when generated by vision-language models (VLMs) We theoretically derive a risk-consistent estimator to explore and utilize the conditional probability distribution information of TFLs. Experimental results demonstrate the effectiveness of the proposed TFL setting and MRP learning method.
• Score: 4.940676168993664
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weakly supervised learning has recently achieved considerable success in reducing annotation costs and label noise. Unfortunately, existing weakly supervised learning methods are short of ability in generating reliable labels via pre-trained vision-language models (VLMs). In this paper, we propose a novel weakly supervised labeling setting, namely True-False Labels (TFLs) which can achieve high accuracy when generated by VLMs. The TFL indicates whether an instance belongs to the label, which is randomly and uniformly sampled from the candidate label set. Specifically, we theoretically derive a risk-consistent estimator to explore and utilize the conditional probability distribution information of TFLs. Besides, we propose a convolutional-based Multi-modal Prompt Retrieving (MRP) method to bridge the gap between the knowledge of VLMs and target learning tasks. Experimental results demonstrate the effectiveness of the proposed TFL setting and MRP learning method. The code to reproduce the experiments is at https://github.com/Tranquilxu/TMP.

Related papers

• On Unsupervised Prompt Learning for Classification with Black-box Language Models [71.60563181678323]
  Large language models (LLMs) have achieved impressive success in text-formatted learning problems. LLMs can label datasets with even better quality than skilled human annotators. In this paper, we propose unsupervised prompt learning for classification with black-box LLMs.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Tabular Transfer Learning via Prompting LLMs [52.96022335067357]
  We propose a novel framework, Prompt to Transfer (P2T), that utilizes unlabeled (or heterogeneous) source data with large language models (LLMs) P2T identifies a column feature in a source dataset that is strongly correlated with a target task feature to create examples relevant to the target task, thus creating pseudo-demonstrations for prompts.
  arXiv  Detail & Related papers  (2024-08-09T11:30:52Z)
• Self-Knowledge Distillation for Learning Ambiguity [11.755814660833549]
  Recent language models often over-confidently predict a single label without consideration for its correctness. We propose a novel self-knowledge distillation method that enables models to learn label distributions more accurately. We validate our method on diverse NLU benchmark datasets and the experimental results demonstrate its effectiveness in producing better label distributions.
  arXiv  Detail & Related papers  (2024-06-14T05:11:32Z)
• Open-Vocabulary Federated Learning with Multimodal Prototyping [14.95283651408951]
  We present a novel adaptation framework tailored for vision-language models (VLMs) in the context of federated learning (FL) Fed-MP adaptively aggregates the local model weights based on light-weight client residuals, and makes predictions based on a novel multimodal prototyping mechanism. Our empirical evaluation on various datasets validates the effectiveness of Fed-MP.
  arXiv  Detail & Related papers  (2024-04-01T16:51:13Z)
• Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning [23.932500424117244]
  In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs) Previous studies have shown that using LLMs' outputs as labels is effective in training models to select demonstrations. This paper presents an analysis on different utility functions by focusing on LLMs' output probability given ground-truth output.
  arXiv  Detail & Related papers  (2023-11-16T07:03:54Z)
• Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models [76.410400238974]
  We propose TTA with feedback to rectify the model output and prevent the model from becoming blindly confident. A CLIP model is adopted as the reward model during TTA and provides feedback for the VLM. The proposed textitreinforcement learning with CLIP feedback(RLCF) framework is highly flexible and universal.
  arXiv  Detail & Related papers  (2023-05-29T11:03:59Z)
• M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios [103.6153593636399]
  We propose a vision-language prompt tuning method with mitigated label bias (M-Tuning) It introduces open words from the WordNet to extend the range of words forming the prompt texts from only closed-set label words to more, and thus prompts are tuned in a simulated open-set scenario. Our method achieves the best performance on datasets with various scales, and extensive ablation studies also validate its effectiveness.
  arXiv  Detail & Related papers  (2023-03-09T09:05:47Z)
• Weakly Supervised Label Learning Flows [8.799674132085931]
  We develop label learning flows (LLF), a general framework for weakly supervised learning problems. Our method is a generative model based on normalizing flows. Experiment results show that our method outperforms many baselines we compare against.
  arXiv  Detail & Related papers  (2023-02-19T18:31:44Z)
• Learning with Partial Labels from Semi-supervised Perspective [28.735185883881172]
  Partial Label (PL) learning refers to the task of learning from partially labeled data. We propose a novel PL learning method, namely Partial Label learning with Semi-Supervised Perspective (PLSP) PLSP significantly outperforms the existing PL baseline methods, especially on high ambiguity levels.
  arXiv  Detail & Related papers  (2022-11-24T15:12:16Z)
• Label Noise-Resistant Mean Teaching for Weakly Supervised Fake News Detection [93.6222609806278]
  We propose a novel label noise-resistant mean teaching approach (LNMT) for weakly supervised fake news detection. LNMT leverages unlabeled news and feedback comments of users to enlarge the amount of training data. LNMT establishes a mean teacher framework equipped with label propagation and label reliability estimation.
  arXiv  Detail & Related papers  (2022-06-10T16:01:58Z)
• One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement [71.9401831465908]
  We investigate single-positive multi-label learning (SPMLL) where each example is annotated with only one relevant label. A novel method named proposed, i.e., Single-positive MultI-label learning with Label Enhancement, is proposed. Experiments on benchmark datasets validate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-06-01T14:26:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.