M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios
- URL: http://arxiv.org/abs/2303.05122v2
- Date: Wed, 20 Dec 2023 01:08:15 GMT
- Title: M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios
- Authors: Ning Liao, Xiaopeng Zhang, Min Cao, Junchi Yan, Qi Tian
- Abstract summary: 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.
- Score: 103.6153593636399
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In realistic open-set scenarios where labels of a part of testing data are
totally unknown, when vision-language (VL) prompt learning methods encounter
inputs related to unknown classes (i.e., not seen during training), they always
predict them as one of the training classes. The exhibited label bias causes
difficulty in open set recognition (OSR), in which an image should be correctly
predicted as one of the known classes or the unknown one. To achieve this goal,
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. Besides, inspired by
the observation that classifying directly on large datasets causes a much
higher false positive rate than on small datasets, we propose a Combinatorial
Tuning and Testing (CTT) strategy for improving performance. CTT decomposes
M-Tuning on large datasets as multiple independent group-wise tuning on fewer
classes, then makes accurate and comprehensive predictions by selecting the
optimal sub-prompt. Finally, given the lack of VL-based OSR baselines in the
literature, especially for prompt methods, we contribute new baselines for fair
comparisons. Our method achieves the best performance on datasets with various
scales, and extensive ablation studies also validate its effectiveness.
Related papers
- LAMM: Label Alignment for Multi-Modal Prompt Learning [17.478967970736115]
We introduce an innovative label alignment method named textbfLAMM, which can adjust the category embeddings of downstream datasets through end-to-end training.
Our method significantly improves the performance of existing multi-modal prompt learning models in few-shot scenarios.
Our methodology exhibits the preeminence in continual learning compared to other prompt tuning methods.
arXiv Detail & Related papers (2023-12-13T15:29:52Z) - Distribution-Aware Prompt Tuning for Vision-Language Models [20.02599087680773]
A key to prompt tuning is the feature space alignment between two modalities via learnable vectors with model parameters fixed.
Inspired by this observation, we proposed distribution-aware prompt tuning (DAPT) for vision-language models.
Our experiments on 11 benchmark datasets demonstrate that our method significantly improves generalizability.
arXiv Detail & Related papers (2023-09-06T23:49:11Z) - Contextual Biasing of Named-Entities with Large Language Models [12.396054621526643]
This paper studies contextual biasing with Large Language Models (LLMs)
During second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance.
We propose to leverage prompts for a LLM without fine tuning during rescoring which incorporate a biasing list and few-shot examples.
arXiv Detail & Related papers (2023-09-01T20:15:48Z) - Towards Realistic Zero-Shot Classification via Self Structural Semantic
Alignment [53.2701026843921]
Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification.
In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary.
We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
arXiv Detail & Related papers (2023-08-24T17:56:46Z) - Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization [101.08992036691673]
This paper explores a realistic unsupervised fine-tuning scenario, considering the presence of out-of-distribution samples from unknown classes.
In particular, we focus on simultaneously enhancing out-of-distribution detection and the recognition of instances associated with known classes.
We present a simple, efficient, and effective approach called Universal Entropy Optimization (UEO)
arXiv Detail & Related papers (2023-08-24T16:47:17Z) - ProTeCt: Prompt Tuning for Taxonomic Open Set Classification [59.59442518849203]
Few-shot adaptation methods do not fare well in the taxonomic open set (TOS) setting.
We propose a prompt tuning technique that calibrates the hierarchical consistency of model predictions.
A new Prompt Tuning for Hierarchical Consistency (ProTeCt) technique is then proposed to calibrate classification across label set granularities.
arXiv Detail & Related papers (2023-06-04T02:55:25Z) - Unified Vision and Language Prompt Learning [86.1530128487077]
We present a systematic study on two representative prompt tuning methods, namely text prompt tuning and visual prompt tuning.
A major finding is that text prompt tuning fails on data with high intra-class visual variances while visual prompt tuning cannot handle low inter-class variances.
To combine the best from both worlds, we propose a simple approach called Unified Prompt Tuning (UPT), which essentially learns a tiny neural network to jointly optimize prompts across different modalities.
arXiv Detail & Related papers (2022-10-13T17:50:24Z) - Dominant Set-based Active Learning for Text Classification and its
Application to Online Social Media [0.0]
We present a novel pool-based active learning method for the training of large unlabeled corpus with minimum annotation cost.
Our proposed method does not have any parameters to be tuned, making it dataset-independent.
Our method achieves a higher performance in comparison to the state-of-the-art active learning strategies.
arXiv Detail & Related papers (2022-01-28T19:19:03Z) - SCARF: Self-Supervised Contrastive Learning using Random Feature
Corruption [72.35532598131176]
We propose SCARF, a technique for contrastive learning, where views are formed by corrupting a random subset of features.
We show that SCARF complements existing strategies and outperforms alternatives like autoencoders.
arXiv Detail & Related papers (2021-06-29T08:08:33Z)
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.