Recent advances in generative adversarial networks (GANs) have achieved great success in automated image composition that generates new images by embedding interested foreground objects into background images automatically. On the other hand, most existing works deal with foreground objects in two-dimensional (2D) images though foreground objects in three-dimensional (3D) models are more flexible with 360-degree view freedom. This paper presents an innovative View Alignment GAN (VA-GAN) that composes new images by embedding 3D models into 2D background images realistically and automatically. VA-GAN consists of a texture generator and a differential discriminator that are inter-connected and end-to-end trainable. The differential discriminator guides to learn geometric transformation from background images so that the composed 3D models can be aligned with the background images with realistic poses and views. The texture generator adopts a novel view encoding mechanism for generating accurate object textures for the 3D models under the estimated views. Extensive experiments over two synthesis tasks (car synthesis with KITTI and pedestrian synthesis with Cityscapes) show that VA-GAN achieves high-fidelity composition qualitatively and quantitatively as compared with state-of-the-art generation methods.
University of California, Irvine（加利福尼亚大学欧文分校）；Tencent Medical AI Lab（腾讯医疗人工智能实验室）；Academia Sinica（中央研究院）
Hand pose estimation from a monocular RGB image is an important but challenging task. The main factor affecting its performance is the lack of a sufficiently large training dataset with accurate hand-keypoint annotations. In this work, we circumvent this problem by proposing an effective method for generating realistic hand poses and show that state-of-the-art algorithms for hand pose estimation can be greatly improved by utilizing the generated hand poses as training data. Specifically, we first adopt an augmented reality (AR) simulator to synthesize hand poses with accurate hand-keypoint lab…
Georgia Institute of Technology（佐治亚理工学院）；Wuhan University of Technology（武汉理工大学）
This paper presents a three-tier modality alignment approach to learning text-image joint embedding, coined as JEMA, for cross-modal retrieval of cooking recipes and food images. The first tier improves recipe text embedding by optimizing the LSTM networks with term extraction and ranking enhanced sequence patterns, and optimizes the image embedding by combining the ResNeXt-101 image encoder with the category embedding using wideResNet-50 with word2vec. The second tier modality alignment optimizes the textual-visual joint embedding loss function using a double batch-hard triplet loss with soft…
Pontifícia Universidade Católica do Rio Grande do Sul（南里奥格兰德天主教大学）
With the novel and fast advances in the area of deep neural networks, several challenging image-based tasks have been recently approached by researchers in pattern recognition and computer vision. In this paper, we address one of these tasks, which is to match image content with natural language descriptions, sometimes referred as multimodal content retrieval. Such a task is particularly challenging considering that we must find a semantic correspondence between captions and the respective image, a challenge for both computer vision and natural language processing areas. For such, we propose a…
Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object detection, which involves the non-semantic task of localization as well as semantic task of classification. To solve this problem, we introduce a vision-language embedding alignment method that transfers the generalization capabilities of a pretrained model such as CLIP to an object detector like YOLOv5. We formulate a loss function that allows us to align the image…
University of Chinese Academy of Sciences（中国科学院大学）；Australian National University（澳大利亚国立大学）
Deep domain adaptation methods can reduce the distribution discrepancy by learning domain-invariant embedddings. However, these methods only focus on aligning the whole data distributions, without considering the class-level relations among source and target images. Thus, a target embeddings of a bird might be aligned to source embeddings of an airplane. This semantic misalignment can directly degrade the classifier performance on the target dataset. To alleviate this problem, we present a similarity constrained alignment (SCA) method for unsupervised domain adaptation. When aligning the distr…
Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
College of Computer Science, Sichuan University（四川大学计算机学院）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）
Beijing Jiaotong University（北京交通大学）；National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
In zero-shot learning (ZSL), the samples to be classified are usually projected into side information templates such as attributes. However, the irregular distribution of templates makes classification results confused. To alleviate this issue, we propose a novel framework called Discriminative Anchor Generation and Distribution Alignment Model (DAGDA). Firstly, in order to rectify the distribution of original templates, a diffusion based graph convolutional network, which can explicitly model the interaction between class and side information, is proposed to produce discriminative anchors. Se…
XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Association
School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Xinjiang Multimodal Information Technology Engineering Research Center（新疆多模态信息处理工程技术研究中心）；Urumqi Branch, China Mobile Group Xinjiang Co., Ltd（中国移动新疆乌鲁木齐分公司）；School of Intelligence Science and Technology, Xinjiang University（新疆大学智能科学与技术学院）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
University of Glasgow（格拉斯哥大学）；TAL Education Group（好未来教育集团）；National University of Singapore（新加坡国立大学）
The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic correspondences. However, the retrieval performance remains unsatisfactory due to a lack of consistent representation in both semantics and structural spaces. In this work, we propose to address the above issue from two aspects: (i) constructing intrinsic structure (along with relations) among the fragments of respective modalities, e.g., "dog $\to$ play $\to$ ba…
SHED: Style-Homogenized Embedding Alignment for Domain Generalization
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China（1 东南大学计算机科学与工程学院，南京 210096，中国）；Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China（2 教育部计算机网络与信息集成重点实验室（东南大学），中国）
Many robotics applications require alignment and fusion of observations obtained at multiple views to form a global model of the environment. Multi-way data association methods provide a mechanism to improve alignment accuracy of pairwise associations and ensure their consistency. However, existing methods that solve this computationally challenging problem are often too slow for real-time applications. Furthermore, some of the existing techniques can violate the cycle consistency principle, thus drastically reducing the fusion accuracy. This work presents the CLEAR (Consistent Lifting, Embedd…
University of Tübingen（蒂宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Heidelberg（海德堡大学）
Recent advances have indicated the strengths of self-supervised pre-training for improving representation learning on downstream tasks. Existing works often utilize self-supervised pre-trained models by fine-tuning on downstream tasks. However, fine-tuning does not generalize to the case when one needs to build a customized model architecture different from the self-supervised model. In this work, we formulate a new knowledge distillation framework to transfer the knowledge from self-supervised pre-trained models to any other student network by a novel approach named Embedding Graph Alignment.…
DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications
Laboratoire des Sciences du Climat et de l’Environnement, LSCE/IPSL, France；Department for AI in Society, Science；Technology, Zuse Institute Berlin, Germany；Department of Information Systems, University of Münster, Germany；Department of Computer Science, CNRS, INRIA \& École Normale Supérieure, Paris 75230, France
提出 DUNIA 方法，通过图像与全波形 LiDAR 跨模态对比对齐学习像素级嵌入，在零样本和微调设置下的多项地球观测环境监测任务中表现优于专门监督模型并接近或超越 SOTA。
Sun Yat-Sen University（中山大学）；JiaYing University（嘉应学院）；Guangzhou University（广州大学）
Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of features, there are two issues to be further explored. First, the hard-assigned pseudo labels on the target domain are risky to the intrinsic data structure. Second, the batch-wise training manner in deep learning limits the description of the global structure. In this paper, a Riemannian manifold learning framework is proposed to achieve transferability and di…
Georgia Institute of Technology（佐治亚理工学院）；Wuhan University of Technology（武汉理工大学）
This paper introduces a two-phase deep feature calibration framework for efficient learning of semantics enhanced text-image cross-modal joint embedding, which clearly separates the deep feature calibration in data preprocessing from training the joint embedding model. We use the Recipe1M dataset for the technical description and empirical validation. In preprocessing, we perform deep feature calibration by combining deep feature engineering with semantic context features derived from raw text-image input data. We leverage LSTM to identify key terms, NLP methods to produce ranking scores for k…
