Most existing vision-language pre-training (VLP) approaches adopt cross-modal masked language modeling (CMLM) to learn vision-language associations. However, we find that CMLM is insufficient for this purpose according to our observations: (1) Modality bias: a considerable amount of masked tokens in CMLM can be recovered with only the language information, ignoring the visual inputs. (2) Under-utilization of the unmasked tokens: CMLM primarily focuses on the masked token but it cannot simultaneously leverage other tokens to learn vision-language associations. To handle those limitations, we propose EPIC (lEveraging Per Image-Token Consistency for vision-language pre-training). In EPIC, for each image-sentence pair, we mask tokens that are salient to the image (i.e., Saliency-based Masking Strategy) and replace them with alternatives sampled from a language model (i.e., Inconsistent Token Generation Procedure), and then the model is required to determine for each token in the sentence whether it is consistent with the image (i.e., Image-Token Consistency Task). The proposed EPIC method is easily combined with pre-training methods. Extensive experiments show that the combination of the EPIC method and state-of-the-art pre-training approaches, including ViLT, ALBEF, METER, and X-VLM, leads to significant improvements on downstream tasks. The code is released at https://github.com/gyhdog99/epic.
We propose a novel Transformer-based image-to-text generation model termed as \textbf{ACF} that adaptively clusters vision patches into object regions and language words into phrases to implicitly learn object-phrase alignments for better visual-text coherence. To achieve this, we design a novel self-attention layer that applies self-attention over the elements in a local cluster window instead of the whole sequence. The window size is softly decided by a clustering matrix that is calculated by the current input data and thus this process is adaptive. By stacking these revised self-attention layers to construct ACF, the small clusters in the lower layers can be grouped into a bigger cluster, \eg vision/language. ACF clusters small objects/phrases into bigger ones. In this gradual clustering process, a parsing tree is generated which embeds the hierarchical knowledge of the input sequence. As a result, by using ACF to build the vision encoder and language decoder, the hierarchical object-phrase alignments are embedded and then transferred from vision to language domains in two popular image-to-text tasks: Image captioning and Visual Question Answering. The experiment results demonstrate the effectiveness of ACF, which outperforms most SOTA captioning and VQA models and achieves comparable scores compared with some large-scale pre-trained models. Our code is available \href{https://github.com/ZihuaEvan/ACFModel/}{[here]}.
In a video, an object usually appears as the trajectory, i.e., it spans over a few spatial but longer temporal patches, that contains abundant spatiotemporal contexts. However, modern Video-Language BERTs (VDL-BERTs) neglect this trajectory characteristic that they usually follow image-language BERTs (IL-BERTs) to deploy the patch-to-word (P2W) attention that may over-exploit trivial spatial contexts and neglect significant temporal contexts. To amend this, we propose a novel TW-BERT to learn Trajectory-Word alignment by a newly designed trajectory-to-word (T2W) attention for solving video-language tasks. Moreover, previous VDL-BERTs usually uniformly sample a few frames into the model while different trajectories have diverse graininess, i.e., some trajectories span longer frames and some span shorter, and using a few frames will lose certain useful temporal contexts. However, simply sampling more frames will also make pre-training infeasible due to the largely increased training burdens. To alleviate the problem, during the fine-tuning stage, we insert a novel Hierarchical Frame-Selector (HFS) module into the video encoder. HFS gradually selects the suitable frames conditioned on the text context for the later cross-modal encoder to learn better trajectory-word alignments. By the proposed T2W attention and HFS, our TW-BERT achieves SOTA performances on text-to-video retrieval tasks, and comparable performances on video question-answering tasks with some VDL-BERTs trained on much more data. The code will be available in the supplementary material.
Identifying and utilising various biomarkers for tracking Alzheimer's disease (AD) progression have received many recent attentions and enable helping clinicians make the prompt decisions. Traditional progression models focus on extracting morphological biomarkers in regions of interest (ROIs) from MRI/PET images, such as regional average cortical thickness and regional volume. They are effective but ignore the relationships between brain ROIs over time, which would lead to synergistic deterioration. For exploring the synergistic deteriorating relationship between these biomarkers, in this paper, we propose a novel spatio-temporal similarity measure based multi-task learning approach for effectively predicting AD progression and sensitively capturing the critical relationships between biomarkers. Specifically, we firstly define a temporal measure for estimating the magnitude and velocity of biomarker change over time, which indicate a changing trend(temporal). Converting this trend into the vector, we then compare this variability between biomarkers in a unified vector space(spatial). The experimental results show that compared with directly ROI based learning, our proposed method is more effective in predicting disease progression. Our method also enables performing longitudinal stability selection to identify the changing relationships between biomarkers, which play a key role in disease progression. We prove that the synergistic deteriorating biomarkers between cortical volumes or surface areas have a significant effect on the cognitive prediction.
Remote Sensing Visual Question Answering (RSVQA) has gained significant research interest. However, current RSVQA methods are limited by the imaging mechanisms of optical sensors, particularly under challenging conditions such as cloud-covered and low-light scenarios. Given the all-time and all-weather imaging capabilities of Synthetic Aperture Radar (SAR), it is crucial to investigate the integration of optical-SAR images to improve RSVQA performance. In this work, we propose a Text-guided Coarse-to-Fine Fusion Network (TGFNet), which leverages the semantic relationships between question text and multi-source images to guide the network toward complementary fusion at the feature level. Specifically, we develop a Text-guided Coarse-to-Fine Attention Refinement (CFAR) module to focus on key areas related to the question in complex remote sensing images. This module progressively directs attention from broad areas to finer details through key region routing, enhancing the model's ability to focus on relevant regions. Furthermore, we propose an Adaptive Multi-Expert Fusion (AMEF) module that dynamically integrates different experts, enabling the adaptive fusion of optical and SAR features. In addition, we create the first large-scale benchmark dataset for evaluating optical-SAR RSVQA methods, comprising 6,008 well-aligned optical-SAR image pairs and 1,036,694 well-labeled question-answer pairs across 16 diverse question types, including complex relational reasoning questions. Extensive experiments on the proposed dataset demonstrate that our TGFNet effectively integrates complementary information between optical and SAR images, significantly improving the model's performance in challenging scenarios. The dataset is available at: https://github.com/mmic-lcl/. Index Terms: Remote Sensing Visual Question Answering, Multi-source Data Fusion, Multimodal, Remote Sensing, OPT-SAR.
We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We disentangle the motion and appearance of a virtual human with explicit mesh geometry and implicit appearance modeling with Gaussian Splatting. The Gaussians are defined by barycentric coordinates and displacement on a triangle mesh as Phong surfaces. We extend lifted optimization to simultaneously optimize the parameters of the Gaussians while walking on the triangle mesh. SplattingAvatar is a hybrid representation of virtual humans where the mesh represents low-frequency motion and surface deformation, while the Gaussians take over the high-frequency geometry and detailed appearance. Unlike existing deformation methods that rely on an MLP-based linear blend skinning (LBS) field for motion, we control the rotation and translation of the Gaussians directly by mesh, which empowers its compatibility with various animation techniques, e.g., skeletal animation, blend shapes, and mesh editing. Trainable from monocular videos for both full-body and head avatars, SplattingAvatar shows state-of-the-art rendering quality across multiple datasets.
Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused multi-scale class-aware attention maps. Our observation is that attention maps of different scales contain rich complementary information, especially for large and small objects. Therefore, we collect information from attention maps of different scales and obtain multi-scale attention maps. We then apply denoising and reactivation strategies to enhance the potential regions and reduce noisy areas. Finally, we use the refined attention maps to retrain the network. Experiments showthat our method enables the model to extract rich semantic information from multi-scale images and achieves 72.4% mIou scores on both the PASCAL VOC 2012 validation and test sets. The code is available at https://bupt-ai-cz.github.io/SMAF.
Motivation: Retrosynthesis planning poses a formidable challenge in the organic chemical industry. Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science. Various deep learning-based methods have been proposed for this task in recent years, incorporating diverse levels of additional chemical knowledge dependency. Results: This paper introduces UAlign, a template-free graph-to-sequence pipeline for retrosynthesis prediction. By combining graph neural networks and Transformers, our method can more effectively leverage the inherent graph structure of molecules. Based on the fact that the majority of molecule structures remain unchanged during a chemical reaction, we propose a simple yet effective SMILES alignment technique to facilitate the reuse of unchanged structures for reactant generation. Extensive experiments show that our method substantially outperforms state-of-the-art template-free and semi-template-based approaches. Importantly, our template-free method achieves effectiveness comparable to, or even surpasses, established powerful template-based methods. Scientific contribution: We present a novel graph-to-sequence template-free retrosynthesis prediction pipeline that overcomes the limitations of Transformer-based methods in molecular representation learning and insufficient utilization of chemical information. We propose an unsupervised learning mechanism for establishing product-atom correspondence with reactant SMILES tokens, achieving even better results than supervised SMILES alignment methods. Extensive experiments demonstrate that UAlign significantly outperforms state-of-the-art template-free methods and rivals or surpasses template-based approaches, with up to 5\% (top-5) and 5.4\% (top-10) increased accuracy over the strongest baseline.
Language-based environment manipulation requires agents to manipulate the environment following natural language instructions, which is challenging due to the huge space of the environments. To address this challenge, various approaches have been proposed in recent work. Although these approaches work well for their intended environments, they are difficult to generalize across environments. In this work, we propose LEMON, a general framework for language-based environment manipulation tasks. Specifically, we first specify a task-agnostic approach for language-based environment manipulation tasks, which can deal with various environments using the same generative language model. Then we propose an execution-guided pre-training strategy to inject prior knowledge of environments to the language model with a pure synthetic pre-training corpus. Experimental results on tasks including Alchemy, Scene, Tangrams, ProPara and Recipes demonstrate the effectiveness of LEMON: it achieves new state-of-the-art results on four of the tasks, and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.
Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-style latent representation in which the category information is disentangled from image style and can be directly used as the cluster assignment. To achieve this goal, mutual information maximization is applied to embed relevant information in the latent representation. Moreover, augmentation-invariant loss is employed to disentangle the representation into category part and style part. Last but not least, a prior distribution is imposed on the latent representation to ensure the elements of the category vector can be used as the probabilities over clusters. Comprehensive experiments demonstrate that the proposed approach outperforms state-of-the-art methods significantly on five public datasets.
Robot awareness of human actions is an essential research problem in robotics with many important real-world applications, including human-robot collaboration and teaming. Over the past few years, depth sensors have become a standard device widely used by intelligent robots for 3D perception, which can also offer human skeletal data in 3D space. Several methods based on skeletal data were designed to enable robot awareness of human actions with satisfactory accuracy. However, previous methods treated all body parts and features equally important, without the capability to identify discriminative body parts and features. In this paper, we propose a novel simultaneous Feature And Body-part Learning (FABL) approach that simultaneously identifies discriminative body parts and features, and efficiently integrates all available information together to enable real-time robot awareness of human behaviors. We formulate FABL as a regression-like optimization problem with structured sparsity-inducing norms to model interrelationships of body parts and features. We also develop an optimization algorithm to solve the formulated problem, which possesses a theoretical guarantee to find the optimal solution. To evaluate FABL, three experiments were performed using public benchmark datasets, including the MSR Action3D and CAD-60 datasets, as well as a Baxter robot in practical assistive living applications. Experimental results show that our FABL approach obtains a high recognition accuracy with a processing speed of the order-of-magnitude of 10e4 Hz, which makes FABL a promising method to enable real-time robot awareness of human behaviors in practical robotics applications.
Convolutional neural networks (CNNs) have shown great performance as general feature representations for object recognition applications. However, for multi-label images that contain multiple objects from different categories, scales and locations, global CNN features are not optimal. In this paper, we incorporate local information to enhance the feature discriminative power. In particular, we first extract object proposals from each image. With each image treated as a bag and object proposals extracted from it treated as instances, we transform the multi-label recognition problem into a multi-class multi-instance learning problem. Then, in addition to extracting the typical CNN feature representation from each proposal, we propose to make use of ground-truth bounding box annotations (strong labels) to add another level of local information by using nearest-neighbor relationships of local regions to form a multi-view pipeline. The proposed multi-view multi-instance framework utilizes both weak and strong labels effectively, and more importantly it has the generalization ability to even boost the performance of unseen categories by partial strong labels from other categories. Our framework is extensively compared with state-of-the-art hand-crafted feature based methods and CNN based methods on two multi-label benchmark datasets. The experimental results validate the discriminative power and the generalization ability of the proposed framework. With strong labels, our framework is able to achieve state-of-the-art results in both datasets.
In this paper, we categorize fine-grained images without using any object / part annotation neither in the training nor in the testing stage, a step towards making it suitable for deployments. Fine-grained image categorization aims to classify objects with subtle distinctions. Most existing works heavily rely on object / part detectors to build the correspondence between object parts by using object or object part annotations inside training images. The need for expensive object annotations prevents the wide usage of these methods. Instead, we propose to select useful parts from multi-scale part proposals in objects, and use them to compute a global image representation for categorization. This is specially designed for the annotation-free fine-grained categorization task, because useful parts have shown to play an important role in existing annotation-dependent works but accurate part detectors can be hardly acquired. With the proposed image representation, we can further detect and visualize the key (most discriminative) parts in objects of different classes. In the experiment, the proposed annotation-free method achieves better accuracy than that of state-of-the-art annotation-free and most existing annotation-dependent methods on two challenging datasets, which shows that it is not always necessary to use accurate object / part annotations in fine-grained image categorization.