Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting

• URL: http://arxiv.org/abs/2410.19294v1
• Date: Fri, 25 Oct 2024 04:00:45 GMT
• Title: Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
• Authors: Xingyu Zhu, Beier Zhu, Yi Tan, Shuo Wang, Yanbin Hao, Hanwang Zhang,
• Abstract summary: Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. We propose a label-Free prompt distribution learning and bias correction framework, dubbed as **Frolic**, which boosts zero-shot performance without the need for labeled data.
• Score: 55.361337202198925
• License:
• Abstract: Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data has proven effective in improving performance, these methods entail labor costs for annotations and are limited by their quality. Additionally, since CLIP is pre-trained on highly imbalanced Web-scale data, it suffers from inherent label bias that leads to suboptimal performance. To tackle the above challenges, we propose a label-Free prompt distribution learning and bias correction framework, dubbed as **Frolic**, which boosts zero-shot performance without the need for labeled data. Specifically, our Frolic learns distributions over prompt prototypes to capture diverse visual representations and adaptively fuses these with the original CLIP through confidence matching. This fused model is further enhanced by correcting label bias via a label-free logit adjustment. Notably, our method is not only training-free but also circumvents the necessity for hyper-parameter tuning. Extensive experimental results across 16 datasets demonstrate the efficacy of our approach, particularly outperforming the state-of-the-art by an average of $2.6\%$ on 10 datasets with CLIP ViT-B/16 and achieving an average margin of $1.5\%$ on ImageNet and its five distribution shifts with CLIP ViT-B/16. Codes are available in https://github.com/zhuhsingyuu/Frolic.

Related papers

• Online Zero-Shot Classification with CLIP [9.099027915077698]
  We study a novel online zero-shot transfer scenario, where each image arrives in a random order for classification and is visited only once to obtain prediction. Compared with the vanilla zero-shot classification, the proposed framework preserves its flexibility for online service. Our online zero-shot transfer method (OnZeta) achieves $78.94%$ accuracy on ImageNet without accessing the entire data set.
  arXiv  Detail & Related papers  (2024-08-23T18:12:12Z)
• Transductive Zero-Shot and Few-Shot CLIP [24.592841797020203]
  This paper addresses the transductive zero-shot and few-shot CLIP classification challenge. Inference is performed jointly across a mini-batch of unlabeled query samples, rather than treating each instance independently. Our approach yields near 20% improvement in ImageNet accuracy over CLIP's zero-shot performance.
  arXiv  Detail & Related papers  (2024-04-08T12:44:31Z)
• A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification [61.473485511491795]
  Semi-supervised learning (SSL) is a practical challenge in computer vision. Pseudo-label (PL) methods, e.g., FixMatch and FreeMatch, obtain the State Of The Art (SOTA) performances in SSL. We propose a lightweight channel-based ensemble method to consolidate multiple inferior PLs into the theoretically guaranteed unbiased and low-variance one.
  arXiv  Detail & Related papers  (2024-03-27T09:49:37Z)
• ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation [20.57370550156505]
  ReCLIP is a source-free domain adaptation method for vision-language models. We demonstrate ReCLIP reduces the average error rate of CLIP from 30.17% to 25.06% on 22 image classification benchmarks.
  arXiv  Detail & Related papers  (2023-08-04T18:11:40Z)
• Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration [18.376601653387315]
  Longtailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications. This problem is often aggravated by discrepancies between labeled and unlabeled class distributions. We introduce Flexible Distribution Alignment (FlexDA), a novel adaptive logit-adjusted loss framework.
  arXiv  Detail & Related papers  (2023-06-07T17:50:59Z)
• SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning [101.86916775218403]
  This paper revisits the popular pseudo-labeling methods via a unified sample weighting formulation. We propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.
  arXiv  Detail & Related papers  (2023-01-26T03:53:25Z)
• FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning [46.95063831057502]
  We propose emphFreeMatch to define and adjust the confidence threshold in a self-adaptive manner according to the model's learning status. FreeMatch achieves textbf5.78%, textbf13.59%, and textbf1.28% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class.
  arXiv  Detail & Related papers  (2022-05-15T10:07:52Z)
• Class-Aware Contrastive Semi-Supervised Learning [51.205844705156046]
  We propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL) to improve pseudo-label quality and enhance the model's robustness in the real-world setting. Our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10.
  arXiv  Detail & Related papers  (2022-03-04T12:18:23Z)
• Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition [98.25592165484737]
  We propose a more effective pseudo-labeling scheme, called Cross-Model Pseudo-Labeling (CMPL) CMPL achieves $17.6%$ and $25.1%$ Top-1 accuracy on Kinetics-400 and UCF-101 using only the RGB modality and $1%$ labeled data, respectively.
  arXiv  Detail & Related papers  (2021-12-17T18:59:41Z)

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.