Pix2Code: Learning to Compose Neural Visual Concepts as Programs

• URL: http://arxiv.org/abs/2402.08280v2
• Date: Sat, 6 Jul 2024 15:07:57 GMT
• Title: Pix2Code: Learning to Compose Neural Visual Concepts as Programs
• Authors: Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting,
• Abstract summary: We propose Pix2Code, a framework that extends program synthesis to visual relational reasoning. We show that Pix2Code's representations remain human interpretable and can be easily revised for improved performance.
• Score: 23.122886870560247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it necessary for human users to be able to understand a model's learnt concepts and potentially revise false behaviours. To tackle both the generalizability and interpretability constraints of visual concept learning, we propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of both explicit, compositional symbolic and implicit neural representations. This is achieved by retrieving object representations from images and synthesizing relational concepts as lambda-calculus programs. We evaluate the diverse properties of Pix2Code on the challenging reasoning domains, Kandinsky Patterns and CURI, thereby testing its ability to identify compositional visual concepts that generalize to novel data and concept configurations. Particularly, in stark contrast to neural approaches, we show that Pix2Code's representations remain human interpretable and can be easily revised for improved performance.

Related papers

• CusConcept: Customized Visual Concept Decomposition with Diffusion Models [13.95568624067449]
  We propose a two-stage framework, CusConcept, to extract customized visual concept embedding vectors. In the first stage, CusConcept employs a vocabularies-guided concept decomposition mechanism. In the second stage, joint concept refinement is performed to enhance the fidelity and quality of generated images.
  arXiv  Detail & Related papers  (2024-10-01T04:41:44Z)
• Explainable Concept Generation through Vision-Language Preference Learning [7.736445799116692]
  Concept-based explanations have become a popular choice for explaining deep neural networks post-hoc. We devise a reinforcement learning-based preference optimization algorithm that fine-tunes the vision-language generative model. In addition to showing the efficacy and reliability of our method, we show how our method can be used as a diagnostic tool for analyzing neural networks.
  arXiv  Detail & Related papers  (2024-08-24T02:26:42Z)
• 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)
• Does Visual Pretraining Help End-to-End Reasoning? [81.4707017038019]
  We investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks. We propose a simple and general self-supervised framework which "compresses" each video frame into a small set of tokens. We observe that pretraining is essential to achieve compositional generalization for end-to-end visual reasoning.
  arXiv  Detail & Related papers  (2023-07-17T14:08:38Z)
• 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)
• Formal Conceptual Views in Neural Networks [0.0]
  We introduce two notions for conceptual views of a neural network, specifically a many-valued and a symbolic view. We test the conceptual expressivity of our novel views through different experiments on the ImageNet and Fruit-360 data sets. We demonstrate how conceptual views can be applied for abductive learning of human comprehensible rules from neurons.
  arXiv  Detail & Related papers  (2022-09-27T16:38:24Z)
• 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)
• Separating Skills and Concepts for Novel Visual Question Answering [66.46070380927372]
  Generalization to out-of-distribution data has been a problem for Visual Question Answering (VQA) models. "Skills" are visual tasks, such as counting or attribute recognition, and are applied to "concepts" mentioned in the question. We present a novel method for learning to compose skills and concepts that separates these two factors implicitly within a model.
  arXiv  Detail & Related papers  (2021-07-19T18:55:10Z)
• Interpretable Visual Reasoning via Induced Symbolic Space [75.95241948390472]
  We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images. We first design a new framework named object-centric compositional attention model (OCCAM) to perform the visual reasoning task with object-level visual features. We then come up with a method to induce concepts of objects and relations using clues from the attention patterns between objects' visual features and question words.
  arXiv  Detail & Related papers  (2020-11-23T18:21:49Z)
• Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs [106.15931418425906]
  We present the first study focused on generating natural language rationales across several complex visual reasoning tasks. We present RationaleVT Transformer, an integrated model that learns to generate free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs. Our experiments show that the base pretrained language model benefits from visual adaptation and that free-text rationalization is a promising research direction to complement model interpretability for complex visual-textual reasoning tasks.
  arXiv  Detail & Related papers  (2020-10-15T05:08:56Z)

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.