Yang Zhao

Bing Su, Dazhao Du, Zhao Yang et al.

Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality. Since the hierarchy of molecular knowledge is profound, even humans learn from different modalities including both intuitive diagrams and professional texts to assist their understanding. Inspired by this, we propose a molecular multimodal foundation model which is pretrained from molecular graphs and their semantically related textual data (crawled from published Scientific Citation Index papers) via contrastive learning. This AI model represents a critical attempt that directly bridges molecular graphs and natural language. Importantly, through capturing the specific and complementary information of the two modalities, our proposed model can better grasp molecular expertise. Experimental results show that our model not only exhibits promising performance in cross-modal tasks such as cross-modal retrieval and molecule caption, but also enhances molecular property prediction and possesses capability to generate meaningful molecular graphs from natural language descriptions. We believe that our model would have a broad impact on AI-empowered fields across disciplines such as biology, chemistry, materials, environment, and medicine, among others.

Bin Wang, Yan Song, Fanming Wang et al.

To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization. It provides a rough temporal location for an action but implicitly overstates the supervision from the annotated-frame during training, leading to the confusion between actions and backgrounds, i.e., action incompleteness and background false positives. To tackle the two challenges, in this work, we present the Snippet Classification model and the Dilation-Erosion module. In the Dilation-Erosion module, we expand the potential action segments with a loose criterion to alleviate the problem of action incompleteness and then remove the background from the potential action segments to alleviate the problem of action incompleteness. Relying on the single-frame annotation and the output of the snippet classification, the Dilation-Erosion module mines pseudo snippet-level ground-truth, hard backgrounds and evident backgrounds, which in turn further trains the Snippet Classification model. It forms a cyclic dependency. Furthermore, we propose a new embedding loss to aggregate the features of action instances with the same label and separate the features of actions from backgrounds. Experiments on THUMOS14 and ActivityNet 1.2 validate the effectiveness of the proposed method. Code has been made publicly available (https://github.com/LingJun123/single-frame-TAL).

Xuhui Jia, Yang Zhao, Kelvin C. K. Chan et al.

This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches, which often employ a per-object optimization paradigm. Our framework adopts an encoder to capture high-level identifiable semantics of objects, producing an object-specific embedding with only a single feed-forward pass. The acquired object embedding is then passed to a text-to-image synthesis model for subsequent generation. To effectively blend a object-aware embedding space into a well developed text-to-image model under the same generation context, we investigate different network designs and training strategies, and propose a simple yet effective regularized joint training scheme with an object identity preservation loss. Additionally, we propose a caption generation scheme that become a critical piece in fostering object specific embedding faithfully reflected into the generation process, while keeping control and editing abilities. Once trained, the network is able to produce diverse content and styles, conditioned on both texts and objects. We demonstrate through experiments that our proposed method is able to synthesize images with compelling output quality, appearance diversity, and object fidelity, without the need of test-time optimization. Systematic studies are also conducted to analyze our models, providing insights for future work.

Haoyuan Li, Hao Jiang, Tao Jin et al.

Product Retrieval (PR) and Grounding (PG), aiming to seek image and object-level products respectively according to a textual query, have attracted great interest recently for better shopping experience. Owing to the lack of relevant datasets, we collect two large-scale benchmark datasets from Taobao Mall and Live domains with about 474k and 101k image-query pairs for PR, and manually annotate the object bounding boxes in each image for PG. As annotating boxes is expensive and time-consuming, we attempt to transfer knowledge from annotated domain to unannotated for PG to achieve un-supervised Domain Adaptation (PG-DA). We propose a {\bf D}omain {\bf A}daptive Produc{\bf t} S{\bf e}eker ({\bf DATE}) framework, regarding PR and PG as Product Seeking problem at different levels, to assist the query {\bf date} the product. Concretely, we first design a semantics-aggregated feature extractor for each modality to obtain concentrated and comprehensive features for following efficient retrieval and fine-grained grounding tasks. Then, we present two cooperative seekers to simultaneously search the image for PR and localize the product for PG. Besides, we devise a domain aligner for PG-DA to alleviate uni-modal marginal and multi-modal conditional distribution shift between source and target domains, and design a pseudo box generator to dynamically select reliable instances and generate bounding boxes for further knowledge transfer. Extensive experiments show that our DATE achieves satisfactory performance in fully-supervised PR, PG and un-supervised PG-DA. Our desensitized datasets will be publicly available here\footnote{\url{https://github.com/Taobao-live/Product-Seeking}}.

Yang Zhao, Hao Zhang, Xiuyuan Hu · tsinghua

By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward propagation at each training iteration, which largely burdens the computation especially for scalable models. To this end, we propose a simple yet efficient training scheme, called Randomized Sharpness-Aware Training (RST). Optimizers in RST would perform a Bernoulli trial at each iteration to choose randomly from base algorithms (SGD) and sharpness-aware algorithms (SAM) with a probability arranged by a predefined scheduling function. Due to the mixture of base algorithms, the overall count of propagation pairs could be largely reduced. Also, we give theoretical analysis on the convergence of RST. Then, we empirically study the computation cost and effect of various types of scheduling functions, and give directions on setting appropriate scheduling functions. Further, we extend the RST to a general framework (G-RST), where we can adjust regularization degree on sharpness freely for any scheduling function. We show that G-RST can outperform SAM in most cases while saving 50\% extra computation cost.

Khoa D. Doan, Jianwen Xie, Yaxuan Zhu et al. · baidu

Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data. One effective solution to boost performance is to employ generative models, such as Generative Adversarial Networks (GANs), to generate synthetic data in an image hashing model. However, GAN-based methods are difficult to train, which prevents the hashing approaches from jointly training the generative models and the hash functions. This limitation results in sub-optimal retrieval performance. To overcome this limitation, we propose a novel framework, the generative cooperative hashing network, which is based on energy-based cooperative learning. This framework jointly learns a powerful generative representation of the data and a robust hash function via two components: a top-down contrastive pair generator that synthesizes contrastive images and a bottom-up multipurpose descriptor that simultaneously represents the images from multiple perspectives, including probability density, hash code, latent code, and category. The two components are jointly learned via a novel likelihood-based cooperative learning scheme. We conduct experiments on several real-world datasets and show that the proposed method outperforms the competing hashing supervised methods, achieving up to 10\% relative improvement over the current state-of-the-art supervised hashing methods, and exhibits a significantly better performance in out-of-distribution retrieval.

Zhonghao Wang, Wei Wei, Yang Zhao et al.

This paper explores advancements in high-fidelity personalized image generation through the utilization of pre-trained text-to-image diffusion models. While previous approaches have made significant strides in generating versatile scenes based on text descriptions and a few input images, challenges persist in maintaining the subject fidelity within the generated images. In this work, we introduce an innovative algorithm named HiFi Tuner to enhance the appearance preservation of objects during personalized image generation. Our proposed method employs a parameter-efficient fine-tuning framework, comprising a denoising process and a pivotal inversion process. Key enhancements include the utilization of mask guidance, a novel parameter regularization technique, and the incorporation of step-wise subject representations to elevate the sample fidelity. Additionally, we propose a reference-guided generation approach that leverages the pivotal inversion of a reference image to mitigate unwanted subject variations and artifacts. We further extend our method to a novel image editing task: substituting the subject in an image through textual manipulations. Experimental evaluations conducted on the DreamBooth dataset using the Stable Diffusion model showcase promising results. Fine-tuning solely on textual embeddings improves CLIP-T score by 3.6 points and improves DINO score by 9.6 points over Textual Inversion. When fine-tuning all parameters, HiFi Tuner improves CLIP-T score by 1.2 points and improves DINO score by 1.2 points over DreamBooth, establishing a new state of the art.

Yang Zhao, Junnan Zhu, Lu Xiang et al.

A common scenario of Multilingual Neural Machine Translation (MNMT) is that each translation task arrives in a sequential manner, and the training data of previous tasks is unavailable. In this scenario, the current methods suffer heavily from catastrophic forgetting (CF). To alleviate the CF, we investigate knowledge distillation based life-long learning methods. Specifically, in one-tomany scenario, we propose a multilingual distillation method to make the new model (student) jointly learn multilingual output from old model (teacher) and new task. In many-to one scenario, we find that direct distillation faces the extreme partial distillation problem, and we propose two different methods to address it: pseudo input distillation and reverse teacher distillation. The experimental results on twelve translation tasks show that the proposed methods can better consolidate the previous knowledge and sharply alleviate the CF.

Cong Ma, Yaping Zhang, Mei Tu et al.

End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of end-to-end text image translation. Multi-task learning is a non-trivial way to alleviate this problem via exploring knowledge from complementary related tasks. In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus. Extensive experimental results show our proposed method outperforms existing end-to-end methods, and the joint multi-task learning with both text translation and recognition tasks achieves better results, proving translation and recognition auxiliary tasks are complementary.

Zehan Wang, Ziang Zhang, Luping Liu et al.

Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high dependence on large-scale, high-quality paired data and the expensive training costs limit their further development. Inspired by recent C-MCR, this paper proposes Extending Multimodal Contrastive Representation (Ex-MCR), a training-efficient and paired-data-free method to flexibly learn unified contrastive representation space for more than three modalities by integrating the knowledge of existing MCR spaces. Specifically, Ex-MCR aligns multiple existing MCRs into the same based MCR, which can effectively preserve the original semantic alignment of the based MCR. Besides, we comprehensively enhance the entire learning pipeline for aligning MCR spaces from the perspectives of training data, architecture, and learning objectives. With the preserved original modality alignment and the enhanced space alignment, Ex-MCR shows superior representation learning performance and excellent modality extensibility. To demonstrate the effectiveness of Ex-MCR, we align the MCR spaces of CLAP (audio-text) and ULIP (3D-vision) into the CLIP (vision-text), leveraging the overlapping text and image modality, respectively. Remarkably, without using any paired data, Ex-MCR learns a 3D-image-text-audio unified contrastive representation, and it achieves state-of-the-art performance on audio-visual, 3D-image, audio-text, visual-text retrieval, and 3D object classification tasks. More importantly, extensive qualitative results further demonstrate the emergent semantic alignment between the extended modalities (e.g., audio and 3D), which highlights the great potential of modality extensibility.

Yang Zhao, Yan Song

Temporal action segmentation in videos has drawn much attention recently. Timestamp supervision is a cost-effective way for this task. To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels iteratively based on the output of a segmentation model and the timestamp annotations. However, this practice may introduce noise and oscillation during the training, and lead to performance degeneration. To address this problem, we propose a new framework for timestamp supervised temporal action segmentation by introducing a teacher model parallel to the segmentation model to help stabilize the process of model optimization. The teacher model can be seen as an ensemble of the segmentation model, which helps to suppress the noise and to improve the stability of pseudo labels. We further introduce a segmentally smoothing loss, which is more focused and cohesive, to enforce the smooth transition of the predicted probabilities within action instances. The experiments on three datasets show that our method outperforms the state-of-the-art method and performs comparably against the fully-supervised methods at a much lower annotation cost.

Thomas Morrish, Theodore Papamarkou, Anastasia Papavasiliou et al.

Motivated by the need to develop a general framework for performing statistical inference for discretely observed random rough differential equations, our aim is to construct a geometric $p$-rough path ${\bf X}$ whose response $Y$, when driving a rough differential equation, matches the observed trajectory $y$. We call this the \textit{continuous inverse problem} and start by rigorously defining its solution. We then develop a framework where the solution can be constructed as a limit of solutions to appropriately designed \textit{discrete inverse problems}, so that convergence holds in $p$-variation. Our approach is based on calibrating the bounded variation paths whose limit defines the rough path `lift' of path $X$ to rough path ${\bf X}$ to the observed trajectory $y$. Moreover, we develop a general numerical algorithm for constructing the solution to the discrete inverse problem. The core idea of the algorithm is to use the signature representation of the path, iterating between the response and the control, each time correcting according to the required properties. We apply our framework to the case where the geometric $p$-rough path ${\bf X}$ is defined as the limit of piecewise linear paths in the $p$-variation topology. We express the discrete inverse problem for a fixed observation rate as a solution to a system of equations driven by piecewise linear paths and prove convergence to the solution of the continuous inverse problem for observation time $δ\to 0$. Finally, we show that, in this context, the numerical algorithm for solving the discrete inverse problem simplifies to an iterative simultaneous update of the local gradients and we prove that it converges in $p$-variation uniformly with respect to $δ$.

Dewang Hou, Yuanyuan Du, Kai Zhao et al.

With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems. First, the fusion of multimodal information requires more network modules to process different modalities. But the application scenarios of sparse ToF measurements usually demand lightweight structure and low computational cost. Second, fusing sparse and noisy depth data with dense pixel-wise RGB data may introduce artifacts. In this paper, a light but efficient depth completion network is proposed, which consists of a two-branch global and local depth prediction module and a funnel convolutional spatial propagation network. The two-branch structure extracts and fuses cross-modal features with lightweight backbones. The improved spatial propagation module can refine the completed depth map gradually. Furthermore, corrected gradient loss is presented for the depth completion problem. Experimental results demonstrate the proposed method can outperform some state-of-the-art methods with a lightweight architecture. The proposed method also wins the championship in the MIPI2022 RGB+TOF depth completion challenge.

Zhao Yang, Fengyang Deng, Linxi Han

The behavior of malware threats is gradually increasing, heightened the need for malware detection. However, existing malware detection methods only target at the existing malicious samples, the detection of fresh malicious code and variants of malicious code is limited. In this paper, we propose a novel scheme that detects malware and its variants efficiently. Based on the idea of the generative adversarial networks (GANs), we obtain the `true' sample distribution that satisfies the characteristics of the real malware, use them to deceive the discriminator, thus achieve the defense against malicious code attacks and improve malware detection. Firstly, a new Android malware APK to image texture feature extraction segmentation method is proposed, which is called segment self-growing texture segmentation algorithm. Secondly, tensor singular value decomposition (tSVD) based on the low-tubal rank transforms malicious features with different sizes into a fixed third-order tensor uniformly, which is entered into the neural network for training and learning. Finally, a flexible Android malware detection model based on GANs with code tensor (MTFD-GANs) is proposed. Experiments show that the proposed model can generally surpass the traditional malware detection model, with a maximum improvement efficiency of 41.6\%. At the same time, the newly generated samples of the GANs generator greatly enrich the sample diversity. And retraining malware detector can effectively improve the detection efficiency and robustness of traditional models.

Ming Gao, YanWu Xu, Yang Zhao et al.

In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler). We aim at stylizing any 3D scene with an arbitrary style from a text description, and synthesizing the novel stylized view, which is more flexible than the image-conditioned style transfer. Compared with the previous 2D method CLIPStyler, we are able to stylize a 3D scene and generalize to novel scenes without re-train our model. A straightforward solution is to combine previous image-conditioned 3D style transfer and text-conditioned 2D style transfer \bigskip methods. However, such a solution cannot achieve our goal due to two main challenges. First, there is no multi-modal model matching point clouds and language at different feature scales (low-level, high-level). Second, we observe a style mixing issue when we stylize the content with different style conditions from text prompts. To address the first issue, we propose a 3D stylization framework to match the point cloud features with text features in local and global views. For the second issue, we propose an improved directional divergence loss to make arbitrary text styles more distinguishable as a complement to our framework. We conduct extensive experiments to show the effectiveness of our model on text-guided 3D scene style transfer.

Zehan Wang, Yang Zhao, Xize Cheng et al.

Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically aligned shared space. This paradigm shows remarkable generalization ability on numerous downstream tasks across various modalities. However, the reliance on massive high-quality data pairs limits its further development on more modalities. This paper proposes a novel training-efficient method for learning MCR without paired data called Connecting Multi-modal Contrastive Representations (C-MCR). Specifically, given two existing MCRs pre-trained on (A, B) and (B, C) modality pairs, we project them to a new space and use the data from the overlapping modality B to aligning the two MCRs in the new space. Meanwhile, since the modality pairs (A, B) and (B, C) are already aligned within each MCR, the connection learned by overlapping modality can also be transferred to non-overlapping modality pair (A, C). To unleash the potential of C-MCR, we further introduce a semantic-enhanced inter- and intra-MCR connection method. We first enhance the semantic consistency and completion of embeddings across different modalities for more robust alignment. Then we utilize the inter-MCR alignment to establish the connection, and employ the intra-MCR alignment to better maintain the connection for inputs from non-overlapping modalities. To demonstrate the effectiveness of C-MCR, we connect CLIP and CLAP via texts to derive audio-visual representations, and integrate CLIP and ULIP via images for 3D-language representations. Remarkably, without using any paired data, C-MCR for audio-visual achieves state-of-the-art performance on audio-image retrieval, audio-visual source localization, and counterfactual audio-image recognition tasks. Furthermore, C-MCR for 3D-language also attains advanced zero-shot 3D point cloud classification accuracy on ModelNet40.

Cong Ma, Yaping Zhang, Mei Tu et al.

Text image machine translation (TIMT) has been widely used in various real-world applications, which translates source language texts in images into another target language sentence. Existing methods on TIMT are mainly divided into two categories: the recognition-then-translation pipeline model and the end-to-end model. However, how to transfer knowledge from the pipeline model into the end-to-end model remains an unsolved problem. In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) method to effectively distillate knowledge into the end-to-end TIMT model from the pipeline model. Specifically, three teachers are utilized to improve the performance of the end-to-end TIMT model. The image encoder in the end-to-end TIMT model is optimized with the knowledge distillation guidance from the recognition teacher encoder, while the sequential encoder and decoder are improved by transferring knowledge from the translation sequential and decoder teacher models. Furthermore, both token and sentence-level knowledge distillations are incorporated to better boost the translation performance. Extensive experimental results show that our proposed MTKD effectively improves the text image translation performance and outperforms existing end-to-end and pipeline models with fewer parameters and less decoding time, illustrating that MTKD can take advantage of both pipeline and end-to-end models.

Cong Ma, Yaping Zhang, Mei Tu et al.

Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and one-stage end-to-end architectures, suffer from different issues. The cascade models can benefit from the large-scale optical character recognition (OCR) and MT datasets but the two-stage architecture is redundant. The end-to-end models are efficient but suffer from training data deficiency. To this end, in our paper, we propose an end-to-end TIMT model fully making use of the knowledge from existing OCR and MT datasets to pursue both an effective and efficient framework. More specifically, we build a novel modal adapter effectively bridging the OCR encoder and MT decoder. End-to-end TIMT loss and cross-modal contrastive loss are utilized jointly to align the feature distribution of the OCR and MT tasks. Extensive experiments show that the proposed method outperforms the existing two-stage cascade models and one-stage end-to-end models with a lighter and faster architecture. Furthermore, the ablation studies verify the generalization of our method, where the proposed modal adapter is effective to bridge various OCR and MT models.

Zhao Yang, Jiaqi Wang, Yansong Tang et al.

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A paradigm for tackling this problem is to leverage a powerful vision-language ("cross-modal") decoder to fuse features independently extracted from a vision encoder and a language encoder. Recent methods have made remarkable advancements in this paradigm by exploiting Transformers as cross-modal decoders, concurrent to the Transformer's overwhelming success in many other vision-language tasks. Adopting a different approach in this work, we show that significantly better cross-modal alignments can be achieved through the early fusion of linguistic and visual features in intermediate layers of a vision Transformer encoder network. By conducting cross-modal feature fusion in the visual feature encoding stage, we can leverage the well-proven correlation modeling power of a Transformer encoder for excavating helpful multi-modal context. This way, accurate segmentation results are readily harvested with a light-weight mask predictor. Without bells and whistles, our method surpasses the previous state-of-the-art methods on RefCOCO, RefCOCO+, and G-Ref by large margins.

Yang Zhao, Hao Zhang

Generalization is the key capability for deep neural networks (DNNs). However, it is challenging to give a reliable measure of the generalization ability of a DNN via only its nature. In this paper, we propose a novel method for estimating the generalization gap based on network sparsity. In our method, two key quantities are proposed first. They have close relationship with the generalization ability and can be calculated directly from the training results alone. Then a simple linear model involving two key quantities are constructed to give accurate estimation of the generalization gap. By training DNNs with a wide range of generalization gap on popular datasets, we show that our key quantities and linear model could be efficient tools for estimating the generalization gap of DNNs.