Wei Zhang

Xinchi Deng, Han Shi, Runhui Huang et al.

Cross-modal pre-training has shown impressive performance on a wide range of downstream tasks, benefiting from massive image-text pairs collected from the Internet. In practice, online data are growing constantly, highlighting the importance of the ability of pre-trained model to learn from data that is continuously growing. Existing works on cross-modal pre-training mainly focus on training a network with fixed architecture. However, it is impractical to limit the model capacity when considering the continuously growing nature of pre-training data in real-world applications. On the other hand, it is important to utilize the knowledge in the current model to obtain efficient training and better performance. To address the above issues, in this paper, we propose GrowCLIP, a data-driven automatic model growing algorithm for contrastive language-image pre-training with continuous image-text pairs as input. Specially, we adopt a dynamic growth space and seek out the optimal architecture at each growth step to adapt to online learning scenarios. And the shared encoder is proposed in our growth space to enhance the degree of cross-modal fusion. Besides, we explore the effect of growth in different dimensions, which could provide future references for the design of cross-modal model architecture. Finally, we employ parameter inheriting with momentum (PIM) to maintain the previous knowledge and address the issue of the local minimum dilemma. Compared with the existing methods, GrowCLIP improves 2.3% average top-1 accuracy on zero-shot image classification of 9 downstream tasks. As for zero-shot image retrieval, GrowCLIP can improve 1.2% for top-1 image-to-text recall on Flickr30K dataset.

Runhui Huang, Jianhua Han, Guansong Lu et al.

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for various downstream tasks by learning to align vision and language embeddings. In this paper, we explore the possibility of jointly modeling generation and discrimination. Specifically, we propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. DiffDis first formulates the image-text discriminative problem as a generative diffusion process of the text embedding from the text encoder conditioned on the image. Then, we propose a novel dual-stream network architecture, which fuses the noisy text embedding with the knowledge of latent images from different scales for image-text discriminative learning. Moreover, the generative and discriminative tasks can efficiently share the image-branch network structure in the multi-modality model. Benefiting from diffusion-based unified training, DiffDis achieves both better generation ability and cross-modal semantic alignment in one architecture. Experimental results show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks, e.g., 1.65% improvement on average accuracy of zero-shot classification over 12 datasets and 2.42 improvement on FID of zero-shot image synthesis.

Wei Zhang, Ping Zhang, Jian Dong et al.

The effectiveness of ad creatives is greatly influenced by their visual appearance. Advertising platforms can generate ad creatives with different appearances by combining creative elements provided by advertisers. However, with the increasing number of ad creative elements, it becomes challenging to select a suitable combination from the countless possibilities. The industry's mainstream approach is to select individual creative elements independently, which often overlooks the importance of interaction between creative elements during the modeling process. In response, this paper proposes a Cross-Element Combinatorial Selection framework for multiple creative elements, termed CECS. In the encoder process, a cross-element interaction is adopted to dynamically adjust the expression of a single creative element based on the current candidate creatives. In the decoder process, the creative combination problem is transformed into a cascade selection problem of multiple creative elements. A pointer mechanism with a cascade design is used to model the associations among candidates. Comprehensive experiments on real-world datasets show that CECS achieved the SOTA score on offline metrics. Moreover, the CECS algorithm has been deployed in our industrial application, resulting in a significant 6.02% CTR and 10.37% GMV lift, which is beneficial to the business.

Yan Zheng, Junpeng Wang, Chin-Chia Michael Yeh et al.

Embedding learning transforms discrete data entities into continuous numerical representations, encoding features/properties of the entities. Despite the outstanding performance reported from different embedding learning algorithms, few efforts were devoted to structurally interpreting how features are encoded in the learned embedding space. This work proposes EmbeddingTree, a hierarchical embedding exploration algorithm that relates the semantics of entity features with the less-interpretable embedding vectors. An interactive visualization tool is also developed based on EmbeddingTree to explore high-dimensional embeddings. The tool helps users discover nuance features of data entities, perform feature denoising/injecting in embedding training, and generate embeddings for unseen entities. We demonstrate the efficacy of EmbeddingTree and our visualization tool through embeddings generated for industry-scale merchant data and the public 30Music listening/playlists dataset.

Runhui Huang, Kaixin Cai, Jianhua Han et al.

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider real applications like professional graphic design and digital artistry, images are frequently created and manipulated in multiple layers to offer greater flexibility and control. Therefore in this paper, we propose a layer-collaborative diffusion model, named LayerDiff, specifically designed for text-guided, multi-layered, composable image synthesis. The composable image consists of a background layer, a set of foreground layers, and associated mask layers for each foreground element. To enable this, LayerDiff introduces a layer-based generation paradigm incorporating multiple layer-collaborative attention modules to capture inter-layer patterns. Specifically, an inter-layer attention module is designed to encourage information exchange and learning between layers, while a text-guided intra-layer attention module incorporates layer-specific prompts to direct the specific-content generation for each layer. A layer-specific prompt-enhanced module better captures detailed textual cues from the global prompt. Additionally, a self-mask guidance sampling strategy further unleashes the model's ability to generate multi-layered images. We also present a pipeline that integrates existing perceptual and generative models to produce a large dataset of high-quality, text-prompted, multi-layered images. Extensive experiments demonstrate that our LayerDiff model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. Moreover, LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.

Wei Zhang, Yunfeng Zhang, Ning Liu

Self-navigation, referred as the capability of automatically reaching the goal while avoiding collisions with obstacles, is a fundamental skill required for mobile robots. Recently, deep reinforcement learning (DRL) has shown great potential in the development of robot navigation algorithms. However, it is still difficult to train the robot to learn goal-reaching and obstacle-avoidance skills simultaneously. On the other hand, although many DRL-based obstacle-avoidance algorithms are proposed, few of them are reused for more complex navigation tasks. In this paper, a novel danger-aware adaptive composition (DAAC) framework is proposed to combine two individually DRL-trained agents, obstacle-avoidance and goal-reaching, to construct a navigation agent without any redesigning and retraining. The key to this adaptive composition approach is that the value function outputted by the obstacle-avoidance agent serves as an indicator for evaluating the risk level of the current situation, which in turn determines the contribution of these two agents for the next move. Simulation and real-world testing results show that the composed Navigation network can control the robot to accomplish difficult navigation tasks, e.g., reaching a series of successive goals in an unknown and complex environment safely and quickly.