2022-03-18 更新
Modulated Contrast for Versatile Image Synthesis
Authors:Fangneng Zhan, Jiahui Zhang, Yingchen Yu, Rongliang Wu, Shijian Lu
Perceiving the similarity between images has been a long-standing and fundamental problem underlying various visual generation tasks. Predominant approaches measure the inter-image distance by computing pointwise absolute deviations, which tends to estimate the median of instance distributions and leads to blurs and artifacts in the generated images. This paper presents MoNCE, a versatile metric that introduces image contrast to learn a calibrated metric for the perception of multifaceted inter-image distances. Unlike vanilla contrast which indiscriminately pushes negative samples from the anchor regardless of their similarity, we propose to re-weight the pushing force of negative samples adaptively according to their similarity to the anchor, which facilitates the contrastive learning from informative negative samples. Since multiple patch-level contrastive objectives are involved in image distance measurement, we introduce optimal transport in MoNCE to modulate the pushing force of negative samples collaboratively across multiple contrastive objectives. Extensive experiments over multiple image translation tasks show that the proposed MoNCE outperforms various prevailing metrics substantially. The code is available at https://github.com/fnzhan/MoNCE.
PDF Accepted to CVPR 2022
论文截图
DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
Authors:Luyang Huang, Guocheng Niu, Jiachen Liu, Xinyan Xiao, Hua Wu
Due to the limitations of the model structure and pre-training objectives, existing vision-and-language generation models cannot utilize pair-wise images and text through bi-directional generation. In this paper, we propose DU-VLG, a framework which unifies vision-and-language generation as sequence generation problems. DU-VLG is trained with novel dual pre-training tasks: multi-modal denoising autoencoder tasks and modality translation tasks. To bridge the gap between image understanding and generation, we further design a novel commitment loss. We compare pre-training objectives on image captioning and text-to-image generation datasets. Results show that DU-VLG yields better performance than variants trained with uni-directional generation objectives or the variant without the commitment loss. We also obtain higher scores compared to previous state-of-the-art systems on three vision-and-language generation tasks. In addition, human judges further confirm that our model generates real and relevant images as well as faithful and informative captions.
PDF To appear at Findings of ACL 2022
论文截图
On Vision Features in Multimodal Machine Translation
Authors:Bei Li, Chuanhao Lv, Zefan Zhou, Tao Zhou, Tong Xiao, Anxiang Ma, JingBo Zhu
Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models on MMT. Given the fact that Transformer is becoming popular in computer vision, we experiment with various strong models (such as Vision Transformer) and enhanced features (such as object-detection and image captioning). We develop a selective attention model to study the patch-level contribution of an image in MMT. On detailed probing tasks, we find that stronger vision models are helpful for learning translation from the visual modality. Our results also suggest the need of carefully examining MMT models, especially when current benchmarks are small-scale and biased. Our code could be found at \url{https://github.com/libeineu/fairseq_mmt}.
PDF Long paper accepted by ACL2022 main conference
论文截图
Synthetic-to-Real Domain Adaptation using Contrastive Unpaired Translation
Authors:Benedikt T. Imbusch, Max Schwarz, Sven Behnke
The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We propose a multi-step method to obtain training data without manual annotation effort: From 3D object meshes, we generate images using a modern synthesis pipeline. We utilize a state-of-the-art image-to-image translation method to adapt the synthetic images to the real domain, minimizing the domain gap in a learned manner. The translation network is trained from unpaired images, i.e. just requires an un-annotated collection of real images. The generated and refined images can then be used to train deep learning models for a particular task. We also propose and evaluate extensions to the translation method that further increase performance, such as patch-based training, which shortens training time and increases global consistency. We evaluate our method and demonstrate its effectiveness on two robotic datasets. We finally give insight into the learned refinement operations.
PDF
论文截图