skip to main content

Title: Cross-Modal Center Loss for 3D Cross-Modal Retrieval
Cross-modal retrieval aims to learn discriminative and modal-invariant features for data from different modalities. Unlike the existing methods which usually learn from the features extracted by offline networks, in this paper, we pro- pose an approach to jointly train the components of cross- modal retrieval framework with metadata, and enable the network to find optimal features. The proposed end-to-end framework is updated with three loss functions: 1) a novel cross-modal center loss to eliminate cross-modal discrepancy, 2) cross-entropy loss to maximize inter-class variations, and 3) mean-square-error loss to reduce modality variations. In particular, our proposed cross-modal center loss minimizes the distances of features from objects belonging to the same class across all modalities. Extensive experiments have been conducted on the retrieval tasks across multi-modalities including 2D image, 3D point cloud and mesh data. The proposed framework significantly outperforms the state-of-the-art methods for both cross-modal and in-domain retrieval for 3D objects on the ModelNet10 and ModelNet40 datasets.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. 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. null (Ed.)
    The success of supervised learning requires large-scale ground truth labels which are very expensive, time- consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike most existing self-supervised methods to learn only 2D image features or only 3D point cloud features, this paper presents a novel and effective self-supervised learning approach to jointly learn both 2D image features and 3D point cloud features by exploiting cross-modality and cross-view correspondences without using any human annotated labels. Specifically, 2D image features of rendered images from different views are extracted by a 2D convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network. Two types of features are fed into a two-layer fully connected neural network to estimate the cross-modality correspondence. The three networks are jointly trained (i.e. cross-modality) by verifying whether two sampled data of different modalities belong to the same object, meanwhile, the 2D convolutional neural network is additionally optimized through minimizing intra-object distance while maximizing inter-object distance of rendered images in different views (i.e. cross-view). The effectiveness of the learned 2D and 3D features is evaluated by transferring them on five different tasks including multi-view 2D shape recognition, 3D shape recognition, multi-view 2D shape retrieval, 3D shape retrieval, and 3D part-segmentation. Extensive evaluations on all the five different tasks across different datasets demonstrate strong generalization and effectiveness of the learned 2D and 3D features by the proposed self-supervised method. 
    more » « less
  3. With benefits of fast query speed and low storage cost, hashing-based image retrieval approaches have garnered considerable attention from the research community. In this paper, we propose a novel Error-Corrected Deep Cross Modal Hashing (CMH-ECC) method which uses a bitmap specifying the presence of certain facial attributes as an input query to retrieve relevant face images from the database. In this architecture, we generate compact hash codes using an end-to-end deep learning module, which effectively captures the inherent relationships between the face and attribute modality. We also integrate our deep learning module with forward error correction codes to further reduce the distance between different modalities of the same subject. Specifically, the properties of deep hashing and forward error correction codes are exploited to design a cross modal hashing framework with high retrieval performance. Experimental results using two standard datasets with facial attributes-image modalities indicate that our CMH-ECC face image retrieval model outperforms most of the current attribute-based face image retrieval approaches. 
    more » « less
  4. 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
  5. Abstract

    Conceptual design is the foundational stage of a design process, translating ill-defined design problems to low-fidelity design concepts and prototypes. While deep learning approaches are widely applied in later design stages for design automation, we see fewer attempts in conceptual design for three reasons: 1) the data in this stage exhibit multiple modalities: natural language, sketches, and 3D shapes, and these modalities are challenging to represent in deep learning methods; 2) it requires knowledge from a larger source of inspiration instead of focusing on a single design task; and 3) it requires translating designers’ intent and feedback, and hence needs more interaction with designers and/or users. With recent advances in deep learning of cross-modal tasks (DLCMT) and the availability of large cross-modal datasets, we see opportunities to apply these learning methods to the conceptual design of product shapes. In this paper, we review 30 recent journal articles and conference papers across computer graphics, computer vision, and engineering design fields that involve DLCMT of three modalities: natural language, sketches, and 3D shapes. Based on the review, we identify the challenges and opportunities of utilizing DLCMT in 3D shape concepts generation, from which we propose a list of research questions pointing to future research directions.

    more » « less