Text-Guided Mixup Towards Long-Tailed Image Categorization

• URL: http://arxiv.org/abs/2409.03583v1
• Date: Thu, 5 Sep 2024 14:37:43 GMT
• Title: Text-Guided Mixup Towards Long-Tailed Image Categorization
• Authors: Richard Franklin, Jiawei Yao, Deyang Zhong, Qi Qian, Juhua Hu,
• Abstract summary: In many real-world applications, the frequency distribution of class labels for training data can exhibit a long-tailed distribution. We propose a novel text-guided mixup technique that takes advantage of the semantic relations between classes recognized by the pre-trained text encoder.
• Score: 7.207351201912651
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In many real-world applications, the frequency distribution of class labels for training data can exhibit a long-tailed distribution, which challenges traditional approaches of training deep neural networks that require heavy amounts of balanced data. Gathering and labeling data to balance out the class label distribution can be both costly and time-consuming. Many existing solutions that enable ensemble learning, re-balancing strategies, or fine-tuning applied to deep neural networks are limited by the inert problem of few class samples across a subset of classes. Recently, vision-language models like CLIP have been observed as effective solutions to zero-shot or few-shot learning by grasping a similarity between vision and language features for image and text pairs. Considering that large pre-trained vision-language models may contain valuable side textual information for minor classes, we propose to leverage text supervision to tackle the challenge of long-tailed learning. Concretely, we propose a novel text-guided mixup technique that takes advantage of the semantic relations between classes recognized by the pre-trained text encoder to help alleviate the long-tailed problem. Our empirical study on benchmark long-tailed tasks demonstrates the effectiveness of our proposal with a theoretical guarantee. Our code is available at https://github.com/rsamf/text-guided-mixup.

Related papers

• Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model [43.738677778740325]
  We propose a novel framework to achieve efficient and long-tailed generalization, which can be termed as Candle. Candle achieves state-of-the-art performance over extensive experiments on 11 diverse datasets.
  arXiv  Detail & Related papers  (2024-06-18T14:07:13Z)
• MaPLe: Multi-modal Prompt Learning [54.96069171726668]
  We propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations. Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes.
  arXiv  Detail & Related papers  (2022-10-06T17:59:56Z)
• DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting [91.56988987393483]
  We present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones.
  arXiv  Detail & Related papers  (2021-12-02T18:59:32Z)
• A Simple Long-Tailed Recognition Baseline via Vision-Language Model [92.2866546058082]
  The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Recent advances in contrastive visual-language pretraining shed light on a new pathway for visual recognition. We propose BALLAD to leverage contrastive vision-language models for long-tailed recognition.
  arXiv  Detail & Related papers  (2021-11-29T17:49:24Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• NewsEmbed: Modeling News through Pre-trained DocumentRepresentations [5.007237648361745]
  We propose a novel approach to mine semantically-relevant fresh documents, and their topic labels, with little human supervision. We show that the proposed approach can provide billions of high quality organic training examples and can be naturally extended to multilingual setting.
  arXiv  Detail & Related papers  (2021-06-01T15:59:40Z)
• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification [56.98218530073927]
  Graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task. Despite the success, their performance could be largely jeopardized in practice since they are unable to capture high-order interaction between words. We propose a principled model -- hypergraph attention networks (HyperGAT) which can obtain more expressive power with less computational consumption for text representation learning.
  arXiv  Detail & Related papers  (2020-11-01T00:21:59Z)
• Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification [52.69730591919885]
  We present a semi-supervised adversarial training process that minimizes the maximal loss for label-preserving input perturbations. We observe significant gains in effectiveness on document and intent classification for a diverse set of languages.
  arXiv  Detail & Related papers  (2020-07-29T19:38:35Z)
• NeuCrowd: Neural Sampling Network for Representation Learning with Crowdsourced Labels [19.345894148534335]
  We propose emphNeuCrowd, a unified framework for supervised representation learning (SRL) from crowdsourced labels. The proposed framework is evaluated on both one synthetic and three real-world data sets.
  arXiv  Detail & Related papers  (2020-03-21T13:38:18Z)

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.