Pre-trained Vision-Language Models Learn Discoverable Visual Concepts

• URL: http://arxiv.org/abs/2404.12652v1
• Date: Fri, 19 Apr 2024 06:41:32 GMT
• Title: Pre-trained Vision-Language Models Learn Discoverable Visual Concepts
• Authors: Yuan Zang, Tian Yun, Hao Tan, Trung Bui, Chen Sun,
• Abstract summary: We aim to answer this question as visual concepts learned "for free" would enable wide applications. We assume that the visual concepts, if captured by pre-trained VLMs, can be extracted by their vision-language interface with text-based concept prompts. Our proposed concept discovery and learning framework is thus designed to identify a diverse list of generic visual concepts.
• Score: 33.302556000017844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Do vision-language models (VLMs) pre-trained to caption an image of a "durian" learn visual concepts such as "brown" (color) and "spiky" (texture) at the same time? We aim to answer this question as visual concepts learned "for free" would enable wide applications such as neuro-symbolic reasoning or human-interpretable object classification. We assume that the visual concepts, if captured by pre-trained VLMs, can be extracted by their vision-language interface with text-based concept prompts. We observe that recent works prompting VLMs with concepts often differ in their strategies to define and evaluate the visual concepts, leading to conflicting conclusions. We propose a new concept definition strategy based on two observations: First, certain concept prompts include shortcuts that recognize correct concepts for wrong reasons; Second, multimodal information (e.g. visual discriminativeness, and textual knowledge) should be leveraged when selecting the concepts. Our proposed concept discovery and learning (CDL) framework is thus designed to identify a diverse list of generic visual concepts (e.g. "spiky" as opposed to "spiky durian"), which are ranked and selected based on visual and language mutual information. We carefully design quantitative and human evaluations of the discovered concepts on six diverse visual recognition datasets, which confirm that pre-trained VLMs do learn visual concepts that provide accurate and thorough descriptions for the recognized objects. All code and models are publicly released.

Related papers

• Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts? [62.984473889987605]
  We present a zero-shot framework for fine-grained visual concept learning by leveraging large language model and Visual Question Answering (VQA) system. We pose these questions along with the query image to a VQA system and aggregate the answers to determine the presence or absence of an object in the test images. Our experiments demonstrate comparable performance with existing zero-shot visual classification methods and few-shot concept learning approaches.
  arXiv  Detail & Related papers  (2024-10-17T15:16:10Z)
• MyVLM: Personalizing VLMs for User-Specific Queries [78.33252556805931]
  We take a first step toward the personalization of vision-language models, enabling them to learn and reason over user-provided concepts. To effectively recognize a variety of user-specific concepts, we augment the VLM with external concept heads that function as toggles for the model. Having recognized the concept, we learn a new concept embedding in the intermediate feature space of the VLM. This embedding is tasked with guiding the language model to naturally integrate the target concept in its generated response.
  arXiv  Detail & Related papers  (2024-03-21T17:51:01Z)
• Language-Informed Visual Concept Learning [22.911347501969857]
  We train a set of concept encoders to encode the information pertinent to a set of language-informed concept axes. We then anchor the concept embeddings to a set of text embeddings obtained from a pre-trained Visual Question Answering (VQA) model. At inference time, the model extracts concept embeddings along various axes from new test images, which can be remixed to generate images with novel compositions of visual concepts.
  arXiv  Detail & Related papers  (2023-12-06T16:24:47Z)
• ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models [79.10890337599166]
  We introduce ConceptBed, a large-scale dataset that consists of 284 unique visual concepts and 33K composite text prompts. We evaluate visual concepts that are either objects, attributes, or styles, and also evaluate four dimensions of compositionality: counting, attributes, relations, and actions. Our results point to a trade-off between learning the concepts and preserving the compositionality which existing approaches struggle to overcome.
  arXiv  Detail & Related papers  (2023-06-07T18:00:38Z)
• ConceptX: A Framework for Latent Concept Analysis [21.760620298330235]
  We present ConceptX, a human-in-the-loop framework for interpreting and annotating latent representational space in Language Models (pLMs) We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts.
  arXiv  Detail & Related papers  (2022-11-12T11:31:09Z)
• Visual Superordinate Abstraction for Robust Concept Learning [80.15940996821541]
  Concept learning constructs visual representations that are connected to linguistic semantics. We ascribe the bottleneck to a failure of exploring the intrinsic semantic hierarchy of visual concepts. We propose a visual superordinate abstraction framework for explicitly modeling semantic-aware visual subspaces.
  arXiv  Detail & Related papers  (2022-05-28T14:27:38Z)
• Visual Concepts Tokenization [65.61987357146997]
  We propose an unsupervised transformer-based Visual Concepts Tokenization framework, dubbed VCT, to perceive an image into a set of disentangled visual concept tokens. To obtain these concept tokens, we only use cross-attention to extract visual information from the image tokens layer by layer without self-attention between concept tokens. We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts.
  arXiv  Detail & Related papers  (2022-05-20T11:25:31Z)
• Visual Concept-Metaconcept Learning [101.62725114966211]
  We propose the visual concept-metaconcept learner (VCML) for joint learning of concepts and metaconcepts from images and associated question-answer pairs. Knowing that red and green describe the same property of objects, we generalize to the fact that cube and sphere also describe the same property of objects.
  arXiv  Detail & Related papers  (2020-02-04T18:42:30Z)

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.