Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models

• URL: http://arxiv.org/abs/2403.10287v1
• Date: Fri, 15 Mar 2024 13:29:41 GMT
• Title: Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models
• Authors: Tian Meng, Yang Tao, Ruilin Lyu, Wuliang Yin,
• Abstract summary: We introduce the Vision-Instructed and Evaluation (VISE) method that transforms the FS-CS problem into the Visual Questioning (VQA) problem. Our approach achieves state-of-the-art performance on the Pascal-5i and COCO-20i datasets.
• Score: 0.6149772262764599
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The task of few-shot image classification and segmentation (FS-CS) involves classifying and segmenting target objects in a query image, given only a few examples of the target classes. We introduce the Vision-Instructed Segmentation and Evaluation (VISE) method that transforms the FS-CS problem into the Visual Question Answering (VQA) problem, utilising Vision-Language Models (VLMs), and addresses it in a training-free manner. By enabling a VLM to interact with off-the-shelf vision models as tools, the proposed method is capable of classifying and segmenting target objects using only image-level labels. Specifically, chain-of-thought prompting and in-context learning guide the VLM to answer multiple-choice questions like a human; vision models such as YOLO and Segment Anything Model (SAM) assist the VLM in completing the task. The modular framework of the proposed method makes it easily extendable. Our approach achieves state-of-the-art performance on the Pascal-5i and COCO-20i datasets.

Related papers

• Teaching VLMs to Localize Specific Objects from In-context Examples [56.797110842152]
  Vision-Language Models (VLMs) have shown remarkable capabilities across diverse visual tasks. Current VLMs lack a fundamental cognitive ability: learning to localize objects in a scene by taking into account the context. This work is the first to explore and benchmark personalized few-shot localization for VLMs.
  arXiv  Detail & Related papers  (2024-11-20T13:34:22Z)
• VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks [89.24440488456405]
  VisionLLM v2 is an end-to-end generalist multimodal large model (MLLM) It unifies visual perception, understanding, and generation within a single framework.
  arXiv  Detail & Related papers  (2024-06-12T16:44:50Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• CoLLaVO: Crayon Large Language and Vision mOdel [42.182009352159]
  It remains unexplored whether current Vision Language Models genuinely possess quality object-level image understanding capabilities. Our findings reveal that the image understanding capabilities of current VLMs are strongly correlated with their zero-shot performance on vision language (VL) tasks. To enhance object-level image understanding, we propose Crayon Large Language and Vision mOdel (CoLLaVO) We present a learning strategy of Dual QLoRA to preserve object-level image understanding without forgetting it during visual instruction tuning.
  arXiv  Detail & Related papers  (2024-02-17T11:03:02Z)
• Few-Shot Classification & Segmentation Using Large Language Models Agent [0.7550566004119158]
  We introduce a method that utilises large language models (LLM) as an agent to address the FS-CS problem in a training-free manner. Our approach achieves state-of-the-art performance on the Pascal-5i dataset.
  arXiv  Detail & Related papers  (2023-11-19T00:33:41Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)
• Exploring Open-Vocabulary Semantic Segmentation without Human Labels [76.15862573035565]
  We present ZeroSeg, a novel method that leverages the existing pretrained vision-language model (VL) to train semantic segmentation models. ZeroSeg overcomes this by distilling the visual concepts learned by VL models into a set of segment tokens, each summarizing a localized region of the target image. Our approach achieves state-of-the-art performance when compared to other zero-shot segmentation methods under the same training data.
  arXiv  Detail & Related papers  (2023-06-01T08:47:06Z)
• IFSeg: Image-free Semantic Segmentation via Vision-Language Model [67.62922228676273]
  We introduce a novel image-free segmentation task where the goal is to perform semantic segmentation given only a set of the target semantic categories. We construct this artificial training data by creating a 2D map of random semantic categories and another map of their corresponding word tokens. Our model not only establishes an effective baseline for this novel task but also demonstrates strong performances compared to existing methods.
  arXiv  Detail & Related papers  (2023-03-25T08:19:31Z)
• Integrative Few-Shot Learning for Classification and Segmentation [37.50821005917126]
  We introduce the integrative task of few-shot classification and segmentation (FS-CS) FS-CS aims to classify and segment target objects in a query image when the target classes are given with a few examples. We propose the integrative few-shot learning framework for FS-CS, which trains a learner to construct class-wise foreground maps.
  arXiv  Detail & Related papers  (2022-03-29T16:14:40Z)

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.