Descriminative-Generative Custom Tokens for Vision-Language Models

• URL: http://arxiv.org/abs/2502.12095v1
• Date: Mon, 17 Feb 2025 18:13:42 GMT
• Title: Descriminative-Generative Custom Tokens for Vision-Language Models
• Authors: Pramuditha Perera, Matthew Trager, Luca Zancato, Alessandro Achille, Stefano Soatto,
• Abstract summary: This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs) Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well with words to form new input queries.
• Score: 101.40245125955306
• License:
• Abstract: This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well with words to form new input queries. The targeted concept is specified in terms of a small set of images and a parent concept described using text. We operate on CLIP text features and propose to use a combination of a textual inversion loss and a classification loss to ensure that text features of the learned token are aligned with image features of the concept in the CLIP embedding space. We restrict the learned token to a low-dimensional subspace spanned by tokens for attributes that are appropriate for the given super-class. These modifications improve the quality of compositions of the learned token with natural language for generating new scenes. Further, we show that learned custom tokens can be used to form queries for text-to-image retrieval task, and also have the important benefit that composite queries can be visualized to ensure that the desired concept is faithfully encoded. Based on this, we introduce the method of Generation Aided Image Retrieval, where the query is modified at inference time to better suit the search intent. On the DeepFashion2 dataset, our method improves Mean Reciprocal Retrieval (MRR) over relevant baselines by 7%.

Related papers

• CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization [14.01847471143144]
  We introduce Context Regularization (CoRe), which enhances the learning of the new concept's text embedding by regularizing its context tokens in the prompt. CoRe can be applied to arbitrary prompts without requiring the generation of corresponding images. Comprehensive experiments demonstrate that our method outperforms several baseline methods in both identity preservation and text alignment.
  arXiv  Detail & Related papers  (2024-08-28T16:27:58Z)
• Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning [41.81009725976217]
  We provide semantically-meaningful visual tokens to transformer encoders within a vision-language pre-training framework. We demonstrate notable improvements over ViTs in learned representation quality across text-to-image and image-to-text retrieval tasks.
  arXiv  Detail & Related papers  (2024-05-26T01:46:22Z)
• Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning [23.671999163027284]
  This paper proposes a novel framework for multi-label image recognition without any training data. It uses knowledge of pre-trained Large Language Model to learn prompts to adapt pretrained Vision-Language Model like CLIP to multilabel classification. Our framework presents a new way to explore the synergies between multiple pre-trained models for novel category recognition.
  arXiv  Detail & Related papers  (2024-03-02T13:43:32Z)
• Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models [59.094601993993535]
  Text-to-image (T2I) personalization allows users to combine their own visual concepts in natural language prompts. Most existing encoders are limited to a single-class domain, which hinders their ability to handle diverse concepts. We propose a domain-agnostic method that does not require any specialized dataset or prior information about the personalized concepts.
  arXiv  Detail & Related papers  (2023-07-13T17:46:42Z)
• LPN: Language-guided Prototypical Network for few-shot classification [16.37959398470535]
  Few-shot classification aims to adapt to new tasks with limited labeled examples. Recent methods explore suitable measures for the similarity between the query and support images. We propose a Language-guided Prototypical Network (LPN) for few-shot classification.
  arXiv  Detail & Related papers  (2023-07-04T06:54:01Z)
• CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels [28.42405456691034]
  We propose a two-stage strategy to facilitate a better visual representation in image re-identification tasks. The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID. The effectiveness of the proposed strategy is validated on several datasets for the person or vehicle ReID tasks.
  arXiv  Detail & Related papers  (2022-11-25T09:41:57Z)
• No Token Left Behind: Explainability-Aided Image Classification and Generation [79.4957965474334]
  We present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input. Our method yields an improvement in the recognition rate, without additional training or fine-tuning.
  arXiv  Detail & Related papers  (2022-04-11T07:16:39Z)
• 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)
• CRIS: CLIP-Driven Referring Image Segmentation [71.56466057776086]
  We propose an end-to-end CLIP-Driven Referring Image framework (CRIS) CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. Our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-11-30T07:29:08Z)
• Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild [103.51604161298512]
  We propose an adversarial learning framework for the generation and recognition of multiple characters in an image. Our framework can be integrated into recent recognition methods to achieve new state-of-the-art recognition accuracy.
  arXiv  Detail & Related papers  (2020-01-13T12:41:42Z)

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.