An official website of the United States government
People grasp flexible visual concepts from a few examples. We explore a neurosymbolic system that learns how to infer programs that capture visual concepts in a domain-general fashion. We introduce Template Programs: programmatic expressions from a domain-specific language that specify structural and parametric patterns common to an input concept. Our framework supports multiple concept-related tasks, including few-shot generation and co-segmentation through parsing. We develop a learning paradigm that allows us to train networks that infer Template Programs directly from visual datasets that contain concept groupings. We run experiments across multiple visual domains: 2D layouts, Omniglot characters, and 3D shapes. We find that our method outperforms task-specific alternatives, and performs competitively against domain-specific approaches for the limited domains where they exist.
more »
« less
This content will become publicly available on December 10, 2025
Learning to Edit Visual Programs with Self-Supervision
We design a system that learns how to edit visual programs. Our edit network consumes a complete input program and a visual target. From this input, we task our network with predicting a local edit operation that could be applied to the input program to improve its similarity to the target. In order to apply this scheme for domains that lack program annotations, we develop a self-supervised learning approach that integrates this edit network into a bootstrapped finetuning loop along with a network that predicts entire programs in one-shot. Our joint finetuning scheme, when coupled with an inference procedure that initializes a population from the one-shot model and evolves members of this population with the edit network, helps to infer more accurate visual programs. Over multiple domains, we experimentally compare our method against the alternative of using only the one-shot model, and find that even under equal search-time budgets, our editing-based paradigm provides significant advantages.
more »
« less
- Award ID(s):
- 1941808
- PAR ID:
- 10580887
- Publisher / Repository:
- NeurIPS '24: 2024 Conference on Neural Information Processing Systems
- Date Published:
- Format(s):
- Medium: X
- Location:
- Vancouver, BC, Canada
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recently, speech foundation models have gained popularity due to their superiority in finetuning downstream ASR tasks. However, models finetuned on certain domains, such as LibriSpeech (adult read speech), behave poorly on other domains (child or noisy speech). One solution could be collecting as much labeled and diverse data as possible for joint finetuning on various domains. However, collecting target domain speech-text paired data and retraining the model is often costly and computationally expensive. In this paper, we introduce a simple yet effective method, speech only adaptation (SOA), based on speech foundation models (Wav2vec 2.0), which requires only speech input data from the target domain. Specifically, the Wav2vec 2.0 feature encoder is continually pretrained with the Wav2vec 2.0 loss on both the source and target domain data for domain adaptation, while the contextual encoder is frozen. Compared to a source domain finetuned model with the feature encoder being frozen during training, we find that replacing the frozen feature encoder with the adapted one provides significant WER improvements to the target domain while preserving the performance of the source domain. The effectiveness of SOA is examined on various low resource or domain mismatched ASR settings, including adult-child and clean-noisy speech.more » « less
-
Structure editors operate directly on a program’s syntactic tree structure. At first glance, this allows for the exciting possibility that such an editor could enforce correctness properties: programs could be well-formed and sometimes even well-typed by construction. Unfortunately, traditional approaches to structure editing that attempt to rigidly enforce these properties face a seemingly fundamental problem, known in the literature asviscosity. Making changes to existing programs often requires temporarily breaking program structure—but disallowing such changes makes it difficult to edit programs! In this paper, we present a scheme for structure editing which always maintains a valid program structure without sacrificing the fluidity necessary to freely edit programs. Two key pieces help solve this puzzle: first, we develop a novel generalization ofselectionfor tree-based structures that properly generalizes text-based selection and editing, allowing users to freely rearrange pieces of code by cutting and pasting one-hole contexts; second, we type these one-hole contexts with a category oftype diffsand explore the metatheory of the system that arises for maintaining well-typedness systematically. We implement our approach as an editor calledPantograph, and we conduct a study in which we successfully taught students to program with Pantograph and compare their performance against a traditional text editor.more » « less
-
Procedural functionality enables visual creators to rapidly edit, explore alternatives, and fine-tune artwork in many domains including illustration, motion graphics, and interactive animation. Symbolic procedural tools, such as textual programming languages, are highly expressive but often limit directly manipulating concrete artwork; whereas direct manipulation tools support some procedural expression but limit creators to pre-defined behaviors and inputs. Inspired by visions of using geometric input to create procedural relationships, we identify an opportunity to use vector geometry from artwork to specify expressive user-defined procedural functions. We present Drawing Transforms (DTs), a technique that enables the use of any drawing to procedurally transform the stylistic, spatial, and temporal properties of target artwork. We apply DTs in a prototype motion graphics system to author continuous and discrete transformations, modify multiple elements in a composition simultaneously, create animations, and control fine-grained procedural instantiation. We discuss how DTs can unify procedural authoring through direct manipulation across visual media domains.more » « less
-
We present a new domain-agnostic synthesis technique for generating programs from input-output examples. Our method, called metric program synthesis, relaxes the well-known observational equivalence idea (used widely in bottom-up enumerative synthesis) into a weaker notion of observational similarity, with the goal of reducing the search space that the synthesizer needs to explore. Our method clusters programs into equivalence classes based on a distance metric and constructs a version space that compactly represents ""approximately correct"" programs. Then, given a ""close enough"" program sampled from this version space, our approach uses a distance-guided repair algorithm to find a program that exactly matches the given input-output examples. We have implemented our proposed metric program synthesis technique in a tool called SyMetric and evaluate it in three different domains considered in prior work. Our evaluation shows that SyMetric outperforms other domain-agnostic synthesizers that use observational equivalence and that it achieves results competitive with domain-specific synthesizers that are either designed for or trained on those domains.more » « less
