Accelerating DETR Convergence via Semantic-Aligned Matching

The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR suffers from extremely slow convergence, which increases the training cost significantly. We observe that the slow convergence is largely attributed to the complication in matching object queries with target features in different feature embedding spaces. This paper presents SAM-DETR, a Semantic-Aligned-Matching DETR that greatly accelerates DETR's convergence without sacrificing its accuracy. SAM-DETR addresses the convergence issue from two perspectives. First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics. Second, it explicitly searches salient points with the most discriminative features for semantic-aligned matching, which further speeds up the convergence and boosts detection accuracy as well. Being like a plug and play, SAM-DETR complements existing convergence solutions well yet only introduces slight computational overhead. Extensive experiments show that the proposed SAM-DETR achieves superior convergence as well as competitive detection accuracy. The implementation codes are available at https://github.com/ZhangGongjie/SAM-DETR.

Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting

Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited various vision-language tasks by jointly learning visual and textual representations, which intuitively helps in Optical Character Recognition (OCR) tasks due to the rich visual and textual information in scene text images. However, these methods cannot well cope with OCR tasks because of the difficulty in both instance-level text encoding and image-text pair acquisition (i.e. images and captured texts in them). This paper presents a weakly supervised pre-training method that can acquire effective scene text representations by jointly learning and aligning visual and textual information. Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features, respectively, as well as a visual-textual decoder that models the interaction among textual and visual features for learning effective scene text representations. With the learning of textual features, the pre-trained model can attend texts in images well with character awareness. Besides, these designs enable the learning from weakly annotated texts (i.e. partial texts in images without text bounding boxes) which mitigates the data annotation constraint greatly. Experiments over the weakly annotated images in ICDAR2019-LSVT show that our pre-trained model improves F-score by +2.5% and +4.8% while transferring its weights to other text detection and spotting networks, respectively. In addition, the proposed method outperforms existing pre-training techniques consistently across multiple public datasets (e.g., +3.2% and +1.3% for Total-Text and CTW1500).

Unsupervised Representation Learning for Point Clouds: A Survey

Point cloud data have been widely explored due to its superior accuracy and robustness under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved very impressive success in various applications such as surveillance and autonomous driving. The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data. Unsupervised point cloud representation learning, which aims to learn general and useful point cloud representations from unlabelled point cloud data, has recently attracted increasing attention due to the constraint in large-scale point cloud labelling. This paper provides a comprehensive review of unsupervised point cloud representation learning using DNNs. It first describes the motivation, general pipelines as well as terminologies of the recent studies. Relevant background including widely adopted point cloud datasets and DNN architectures is then briefly presented. This is followed by an extensive discussion of existing unsupervised point cloud representation learning methods according to their technical approaches. We also quantitatively benchmark and discuss the reviewed methods over multiple widely adopted point cloud datasets. Finally, we share our humble opinion about several challenges and problems that could be pursued in the future research in unsupervised point cloud representation learning. A project associated with this survey has been built at https://github.com/xiaoaoran/3d_url_survey.

Dual Learning Music Composition and Dance Choreography

Music and dance have always co-existed as pillars of human activities, contributing immensely to the cultural, social, and entertainment functions in virtually all societies. Notwithstanding the gradual systematization of music and dance into two independent disciplines, their intimate connection is undeniable and one art-form often appears incomplete without the other. Recent research works have studied generative models for dance sequences conditioned on music. The dual task of composing music for given dances, however, has been largely overlooked. In this paper, we propose a novel extension, where we jointly model both tasks in a dual learning approach. To leverage the duality of the two modalities, we introduce an optimal transport objective to align feature embeddings, as well as a cycle consistency loss to foster overall consistency. Experimental results demonstrate that our dual learning framework improves individual task performance, delivering generated music compositions and dance choreographs that are realistic and faithful to the conditioned inputs.

Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction

Predicting human motion from historical pose sequence is crucial for a machine to succeed in intelligent interactions with humans. One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results. Yet there is no effort that investigates across different pose representation schemes. We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. Moreover, recent approaches build upon off-the-shelf RNN units for motion prediction. These approaches process input pose sequence sequentially and inherently have difficulties in capturing long-term dependencies. In this paper, we propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction which simultaneously models local motion contexts and a global context. We further explore a geodesic loss and a forward kinematics loss for the motion prediction task, which have more geometric significance than the widely employed L2 loss. Interestingly, we applied our method to a range of articulate objects including human, fish, and mouse. Empirical results show that our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency, such as retaining natural human-like motions over 50 seconds predictions. Our codes are released.

Multimodal Image Synthesis and Editing: A Survey

As information exists in various modalities in real world, effective interaction and fusion among multimodal information plays a key role for the creation and perception of multimodal data in computer vision and deep learning research. With superb power in modelling the interaction among multimodal information, multimodal image synthesis and editing have become a hot research topic in recent years. Different from traditional visual guidance which provides explicit clues, multimodal guidance offers intuitive and flexible means in image synthesis and editing. On the other hand, this field is also facing several challenges in alignment of features with inherent modality gaps, synthesis of high-resolution images, faithful evaluation metrics, etc. In this survey, we comprehensively contextualize the advance of the recent multimodal image synthesis \& editing and formulate taxonomies according to data modality and model architectures. We start with an introduction to different types of guidance modalities in image synthesis and editing. We then describe multimodal image synthesis and editing approaches extensively with detailed frameworks including Generative Adversarial Networks (GANs), GAN Inversion, Transformers, and other methods such as NeRF and Diffusion models. This is followed by a comprehensive description of benchmark datasets and corresponding evaluation metrics as widely adopted in multimodal image synthesis and editing, as well as detailed comparisons of different synthesis methods with analysis of respective advantages and limitations. Finally, we provide insights into the current research challenges and possible future research directions. A project associated with this survey is available at https://github.com/fnzhan/MISE

PTTR: Relational 3D Point Cloud Object Tracking with Transformer

In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in the current search point cloud given a template point cloud. Motivated by the success of transformers, we propose Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations. PTTR consists of three novel designs. 1) Instead of random sampling, we design Relation-Aware Sampling to preserve relevant points to given templates during subsampling. 2) Furthermore, we propose a Point Relation Transformer (PRT) consisting of a self-attention and a cross-attention module. The global self-attention operation captures long-range dependencies to enhance encoded point features for the search area and the template, respectively. Subsequently, we generate the coarse tracking results by matching the two sets of point features via cross-attention. 3) Based on the coarse tracking results, we employ a novel Prediction Refinement Module to obtain the final refined prediction. In addition, we create a large-scale point cloud single object tracking benchmark based on the Waymo Open Dataset. Extensive experiments show that PTTR achieves superior point cloud tracking in both accuracy and efficiency.

Music-to-Dance Generation with Optimal Transport

Dance choreography for a piece of music is a challenging task, having to be creative in presenting distinctive stylistic dance elements while taking into account the musical theme and rhythm. It has been tackled by different approaches such as similarity retrieval, sequence-to-sequence modeling and generative adversarial networks, but their generated dance sequences are often short of motion realism, diversity and music consistency. In this paper, we propose a Music-to-Dance with Optimal Transport Network (MDOT-Net) for learning to generate 3D dance choreographs from music. We introduce an optimal transport distance for evaluating the authenticity of the generated dance distribution and a Gromov-Wasserstein distance to measure the correspondence between the dance distribution and the input music. This gives a well defined and non-divergent training objective that mitigates the limitation of standard GAN training which is frequently plagued with instability and divergent generator loss issues. Extensive experiments demonstrate that our MDOT-Net can synthesize realistic and diverse dances which achieve an organic unity with the input music, reflecting the shared intentionality and matching the rhythmic articulation.

Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data

Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled target domain, but it requires to access the source data which often raises concerns in data privacy, data portability and data transmission efficiency. We study unsupervised model adaptation (UMA), or called Unsupervised Domain Adaptation without Source Data, an alternative setting that aims to adapt source-trained models towards target distributions without accessing source data. To this end, we design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA. HCL addresses the UMA challenge from two perspectives. First, it introduces historical contrastive instance discrimination (HCID) that learns from target samples by contrasting their embeddings which are generated by the currently adapted model and the historical models. With the historical models, HCID encourages UMA to learn instance-discriminative target representations while preserving the source hypothesis. Second, it introduces historical contrastive category discrimination (HCCD) that pseudo-labels target samples to learn category-discriminative target representations. Specifically, HCCD re-weights pseudo labels according to their prediction consistency across the current and historical models. Extensive experiments show that HCL outperforms and state-of-the-art methods consistently across a variety of visual tasks and setups.

GenCo: Generative Co-training on Data-Limited Image Generation

Training effective Generative Adversarial Networks (GANs) requires large amounts of training data, without which the trained models are usually sub-optimal with discriminator over-fitting. Several prior studies address this issue by expanding the distribution of the limited training data via massive and hand-crafted data augmentation. We handle data-limited image generation from a very different perspective. Specifically, we design GenCo, a Generative Co-training network that mitigates the discriminator over-fitting issue by introducing multiple complementary discriminators that provide diverse supervision from multiple distinctive views in training. We instantiate the idea of GenCo in two ways. The first way is Weight-Discrepancy Co-training (WeCo) which co-trains multiple distinctive discriminators by diversifying their parameters. The second way is Data-Discrepancy Co-training (DaCo) which achieves co-training by feeding discriminators with different views of the input images (e.g., different frequency components of the input images). Extensive experiments over multiple benchmarks show that GenCo achieves superior generation with limited training data. In addition, GenCo also complements the augmentation approach with consistent and clear performance gains when combined.