More Like this

1. Deep Learning Methods of Cross-Modal Tasks for Conceptual Design of Product Shapes: A Review

   https://doi.org/10.1115/1.4056436  

   Li, Xingang; Wang, Ye; Sha, Zhenghui (April 2023, Journal of Mechanical Design)

   Conceptual design is the foundational stage of a design process that translates ill-defined design problems into low-fidelity design concepts and prototypes through design search, creation, and integration. In this stage, product shape design is one of the most paramount aspects. When applying deep learning-based methods to product shape design, two major challenges exist: (1) design data exhibit in multiple modalities and (2) an increasing demand for creativity. With recent advances in deep learning of cross-modal tasks (DLCMTs), which can transfer one design modality to another, we see opportunities to develop artificial intelligence (AI) to assist the design of product shapes in a new paradigm. In this paper, we conduct a systematic review of the retrieval, generation, and manipulation methods for DLCMT that involve three cross-modal types: text-to-3D shape, text-to-sketch, and sketch-to-3D shape. The review identifies 50 articles from a pool of 1341 papers in the fields of computer graphics, computer vision, and engineering design. We review (1) state-of-the-art DLCMT methods that can be applied to product shape design and (2) identify the key challenges, such as lack of consideration of engineering performance in the early design phase that need to be addressed when applying DLCMT methods. In the end, we discuss the potential solutions to these challenges and propose a list of research questions that point to future directions of data-driven conceptual design. 

   more » « less
2. How Domain Experts Create Conceptual Diagrams and Implications for Tool Design

   https://doi.org/10.1145/3313831.3376253  

   Ma'ayan, Dor; Ni, Wode; Ye, Katherine; Kulkarni, Chinmay; Sunshine, Joshua (April 2020, CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems)

   Conceptual diagrams are used extensively to understand abstract relationships, explain complex ideas, and solve difficult problems. To illustrate concepts effectively, experts find appropriate visual representations and translate concepts into concrete shapes. This translation step is not supported explicitly by current diagramming tools. This paper investigates how domain experts create conceptual diagrams via semi-structured interviews with 18 participants from diverse backgrounds. Our participants create, adapt, and reuse visual representations using both sketches and digital tools. However, they had trouble using current diagramming tools to transition from sketches and reuse components from earlier diagrams. Our participants also expressed frustration with the slow feedback cycles and barriers to automation of their tools. Based on these results, we suggest four opportunities of diagramming tools — exploration support, representation salience, live engagement, and vocabulary correspondence — that together enable a natural diagramming experience. Finally, we discuss possibilities to leverage recent research advances to develop natural diagramming tools. 

   more » « less
3. Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models

   Zhiqiu Lin, Samuel Yu (June 2023, CVPR)

   The ability to quickly learn a new task with minimal instruction - known as few-shot learning - is a central aspect of intelligent agents. Classical few-shot benchmarks make use of few-shot samples from a single modality, but such samples may not be sufficient to characterize an entire concept class. In contrast, humans use cross-modal information to learn new concepts efficiently. In this work, we demonstrate that one can indeed build a better visual dog classifier by reading about dogs and listening to them bark. To do so, we exploit the fact that recent multimodal foundation models such as CLIP are inherently cross-modal, mapping different modalities to the same representation space. Specifically, we propose a simple cross-modal adaptation approach that learns from few-shot examples spanning different modalities. By repurposing class names as additional one-shot training samples, we achieve SOTA results with an embarrassingly simple linear classifier for vision-language adaptation. Furthermore, we show that our approach can benefit existing methods such as prefix tuning, adapters, and classifier ensembling. Finally, to explore other modalities beyond vision and language, we construct the first (to our knowledge) audiovisual few-shot benchmark and use cross-modal training to improve the performance of both image and audio classification. 

   more » « less
4. Explainable Semantic Space by Grounding Language to Vision with Cross-Modal Contrastive Learning

   Yizhen Zhang, Minkyu Choi (December 2021, Advances in neural information processing systems)

   In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the “distributional semantics” but fail to connect to any knowledge about the physical world. In contrast, humans learn language by grounding concepts in perception and action and the brain encodes “grounded semantics” for cognition. Inspired by this notion and recent work in vision-language learning, we design a two-stream model for grounding language learning in vision. The model includes a VGG-based visual stream and a Bert-based language stream. The two streams merge into a joint representational space. Through cross-modal contrastive learning, the model first learns to align visual and language representations with the MS COCO dataset. The model further learns to retrieve visual objects with language queries through a cross-modal attention module and to infer the visual relations between the retrieved objects through a bilinear operator with the Visual Genome dataset. After training, the model’s language stream is a stand-alone language model capable of embedding concepts in a visually grounded semantic space. This semantic space manifests principal dimensions explainable with human intuition and neurobiological knowledge. Word embeddings in this semantic space are predictive of human-defined norms of semantic features and are segregated into perceptually distinctive clusters. Furthermore, the visually grounded language model also enables compositional language understanding based on visual knowledge and multimodal image search with queries based on images, texts, or their combinations. 

   more » « less
5. Enabling multi-modal search for inspirational design stimuli using deep learning

   https://doi.org/10.1017/S0890060422000130  

   Kwon, Elisa; Huang, Forrest; Goucher-Lambert, Kosa (January 2022, Artificial Intelligence for Engineering Design, Analysis and Manufacturing)

   Abstract Inspirational stimuli are known to be effective in supporting ideation during early-stage design. However, prior work has predominantly constrained designers to using text-only queries when searching for stimuli, which is not consistent with real-world design behavior where fluidity across modalities (e.g., visual, semantic, etc.) is standard practice. In the current work, we introduce a multi-modal search platform that retrieves inspirational stimuli in the form of 3D-model parts using text, appearance, and function-based search inputs. Computational methods leveraging a deep-learning approach are presented for designing and supporting this platform, which relies on deep-neural networks trained on a large dataset of 3D-model parts. This work further presents the results of a cognitive study ( n = 21) where the aforementioned search platform was used to find parts to inspire solutions to a design challenge. Participants engaged with three different search modalities: by keywords, 3D parts, and user-assembled 3D parts in their workspace. When searching by parts that are selected or in their workspace, participants had additional control over the similarity of appearance and function of results relative to the input. The results of this study demonstrate that the modality used impacts search behavior, such as in search frequency, how retrieved search results are engaged with, and how broadly the search space is covered. Specific results link interactions with the interface to search strategies participants may have used during the task. Findings suggest that when searching for inspirational stimuli, desired results can be achieved both by direct search inputs (e.g., by keyword) as well as by more randomly discovered examples, where a specific goal was not defined. Both search processes are found to be important to enable when designing search platforms for inspirational stimuli retrieval. 

   more » « less