Multi-Modal Relation Extraction (MMRE) aims at identifying the relation between two entities in texts that contain visual clues. Rich visual content is valuable for the MMRE task, but existing works cannot well model finer associations among different modalities, failing to capture the truly helpful visual information and thus limiting relation extraction performance. In this paper, we propose a novel MMRE framework to better capture the deeper correlations of text, entity pair, and image/objects, so as to mine more helpful information for the task, termed as DGF-PT. We first propose a prompt-based autoregressive encoder, which builds the associations of intra-modal and inter-modal features related to the task, respectively by entity-oriented and object-oriented prefixes. To better integrate helpful visual information, we design a dual-gated fusion module to distinguish the importance of image/objects and further enrich text representations. In addition, a generative decoder is introduced with entity type restriction on relations, better filtering out candidates. Extensive experiments conducted on the benchmark dataset show that our approach achieves excellent performance compared to strong competitors, even in the few-shot situation.
Open-domain long-term memory conversation can establish long-term intimacy with humans, and the key is the ability to understand and memorize long-term dialogue history information. Existing works integrate multiple models for modelling through a pipeline, which ignores the coupling between different stages. In this paper, we propose a Unified framework for Long-term Memory Conversations (UniMC), which increases the connection between different stages by learning relevance representation. Specifically, we decompose the main task into three subtasks based on probability graphs: 1) conversation summarization, 2) memory retrieval, 3) memory-augmented generation. Each subtask involves learning a representation for calculating the relevance between the query and memory, which is modelled by inserting a special token at the beginning of the decoder input. The relevance representation learning strengthens the connection across subtasks through parameter sharing and joint training. Extensive experimental results show that the proposed method consistently improves over strong baselines and yields better dialogue consistency and engagingness.
Predicting sea surface temperature (SST) within the El Ni\~no-Southern Oscillation (ENSO) region has been extensively studied due to its significant influence on global temperature and precipitation patterns. Statistical models such as linear inverse model (LIM), analog forecasting (AF), and recurrent neural network (RNN) have been widely used for ENSO prediction, offering flexibility and relatively low computational expense compared to large dynamic models. However, these models have limitations in capturing spatial patterns in SST variability or relying on linear dynamics. Here we present a modified Convolutional Gated Recurrent Unit (ConvGRU) network for the ENSO region spatio-temporal sequence prediction problem, along with the Ni\~no 3.4 index prediction as a down stream task. The proposed ConvGRU network, with an encoder-decoder sequence-to-sequence structure, takes historical SST maps of the Pacific region as input and generates future SST maps for subsequent months within the ENSO region. To evaluate the performance of the ConvGRU network, we trained and tested it using data from multiple large climate models. The results demonstrate that the ConvGRU network significantly improves the predictability of the Ni\~no 3.4 index compared to LIM, AF, and RNN. This improvement is evidenced by extended useful prediction range, higher Pearson correlation, and lower root-mean-square error. The proposed model holds promise for improving our understanding and predicting capabilities of the ENSO phenomenon and can be broadly applicable to other weather and climate prediction scenarios with spatial patterns and teleconnections.
We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning. In contrast to conventional methods, it is trained with oracle guidance, which is derived from the target sequence. Since the oracle guidance compactly represents the target-side context that can assist the sequence model in solving the task, the EM-Network achieves a better prediction compared to using only the source input. To allow the sequence model to inherit the promising capability of the EM-Network, we propose a new self-distillation strategy, where the original sequence model can benefit from the knowledge of the EM-Network in a one-stage manner. We conduct comprehensive experiments on two types of seq2seq models: connectionist temporal classification (CTC) for speech recognition and attention-based encoder-decoder (AED) for machine translation. Experimental results demonstrate that the EM-Network significantly advances the current state-of-the-art approaches, improving over the best prior work on speech recognition and establishing state-of-the-art performance on WMT'14 and IWSLT'14.
This work proposes a real-time anomaly detection scheme that leverages the multi-step ahead prediction capabilities of encoder-decoder (ED) deep learning models with recurrent units. Specifically, an encoder-decoder is used to model soft-failure evolution over a long future horizon (i.e., for several days ahead) by analyzing past quality-of-transmission (QoT) observations. This information is subsequently used for real-time anomaly detection (e.g., of attack incidents), as the knowledge of how the QoT is expected to evolve allows capturing unexpected network behavior. Specifically, for anomaly detection, a statistical hypothesis testing scheme is used, alleviating the limitations of supervised (SL) and unsupervised learning (UL) schemes, usually applied for this purpose. Indicatively, the proposed scheme eliminates the need for labeled anomalies, required when SL is applied, and the need for on-line analyzing entire datasets to identify abnormal instances (i.e., UL). Overall, it is shown that by utilizing QoT evolution information, the proposed approach can effectively detect abnormal deviations in real-time. Importantly, it is shown that the information concerning soft-failure evolution (i.e., QoT predictions) is essential to accurately detect anomalies.
Structure-based molecular ML (SBML) models can be highly sensitive to input geometries and give predictions with large variance. We present an approach to mitigate the challenge of selecting conformations for such models by generating conformers that explicitly minimize predictive uncertainty. To achieve this, we compute estimates of aleatoric and epistemic uncertainties that are differentiable w.r.t. latent posteriors. We then iteratively sample new latents in the direction of lower uncertainty by gradient descent. As we train our predictive models jointly with a conformer decoder, the new latent embeddings can be mapped to their corresponding inputs, which we call \textit{MoleCLUEs}, or (molecular) counterfactual latent uncertainty explanations \citep{antoran2020getting}. We assess our algorithm for the task of predicting drug properties from 3D structure with maximum confidence. We additionally analyze the structure trajectories obtained from conformer optimizations, which provide insight into the sources of uncertainty in SBML.
Semantic segmentation in surgical videos has applications in intra-operative guidance, post-operative analytics and surgical education. Segmentation models need to provide accurate and consistent predictions since temporally inconsistent identification of anatomical structures can impair usability and hinder patient safety. Video information can alleviate these challenges leading to reliable models suitable for clinical use. We propose a novel architecture for modelling temporal relationships in videos. The proposed model includes a spatio-temporal decoder to enable video semantic segmentation by improving temporal consistency across frames. The encoder processes individual frames whilst the decoder processes a temporal batch of adjacent frames. The proposed decoder can be used on top of any segmentation encoder to improve temporal consistency. Model performance was evaluated on the CholecSeg8k dataset and a private dataset of robotic Partial Nephrectomy procedures. Segmentation performance was improved when the temporal decoder was applied across both datasets. The proposed model also displayed improvements in temporal consistency.
We introduce RedMotion, a transformer model for motion prediction in self-driving vehicles that learns environment representations via redundancy reduction. Our first type of redundancy reduction is induced by an internal transformer decoder and reduces a variable-sized set of local road environment tokens, representing road graphs and agent data, to a fixed-sized global embedding. The second type of redundancy reduction is obtained by self-supervised learning and applies the redundancy reduction principle to embeddings generated from augmented views of road environments. Our experiments reveal that our representation learning approach outperforms PreTraM, Traj-MAE, and GraphDINO in a semi-supervised setting. Moreover, RedMotion achieves competitive results compared to HPTR or MTR++ in the Waymo Motion Prediction Challenge. Our open-source implementation is available at: https://github.com/kit-mrt/future-motion
Accurate segmentation of colonoscopic polyps is considered a fundamental step in medical image analysis and surgical interventions. Many recent studies have made improvements based on the encoder-decoder framework, which can effectively segment diverse polyps. Such improvements mainly aim to enhance local features by using global features and applying attention methods. However, relying only on the global information of the final encoder block can result in losing local regional features in the intermediate layer. In addition, determining the edges between benign regions and polyps could be a challenging task. To address the aforementioned issues, we propose a novel separated edge-guidance transformer (SegT) network that aims to build an effective polyp segmentation model. A transformer encoder that learns a more robust representation than existing CNN-based approaches was specifically applied. To determine the precise segmentation of polyps, we utilize a separated edge-guidance module consisting of separator and edge-guidance blocks. The separator block is a two-stream operator to highlight edges between the background and foreground, whereas the edge-guidance block lies behind both streams to strengthen the understanding of the edge. Lastly, an innovative cascade fusion module was used and fused the refined multi-level features. To evaluate the effectiveness of SegT, we conducted experiments with five challenging public datasets, and the proposed model achieved state-of-the-art performance.
Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by machine vision algorithms. Intuitively, it is more efficient to enhance/analyze the coded representations directly without decoding them into pixels. Therefore, we propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis, thereby being versatile for both human and machine vision. Our VNVC framework has a feature-based compression loop. In the loop, one frame is encoded into compact representations and decoded to an intermediate feature that is obtained before performing reconstruction. The intermediate feature can be used as reference in motion compensation and motion estimation through feature-based temporal context mining and cross-domain motion encoder-decoder to compress the following frames. The intermediate feature is directly fed into video reconstruction, video enhancement, and video analysis networks to evaluate its effectiveness. The evaluation shows that our framework with the intermediate feature achieves high compression efficiency for video reconstruction and satisfactory task performances with lower complexities.
Estimating the joint distribution of on-road agents' future trajectories is essential for autonomous driving. In this technical report, we propose a next-generation framework for joint multi-agent trajectory prediction called QCNeXt. First, we adopt the query-centric encoding paradigm for the task of joint multi-agent trajectory prediction. Powered by this encoding scheme, our scene encoder is equipped with permutation equivariance on the set elements, roto-translation invariance in the space dimension, and translation invariance in the time dimension. These invariance properties not only enable accurate multi-agent forecasting fundamentally but also empower the encoder with the capability of streaming processing. Second, we propose a multi-agent DETR-like decoder, which facilitates joint multi-agent trajectory prediction by modeling agents' interactions at future time steps. For the first time, we show that a joint prediction model can outperform marginal prediction models even on the marginal metrics, which opens up new research opportunities in trajectory prediction. Our approach ranks 1st on the Argoverse 2 multi-agent motion forecasting benchmark, winning the championship of the Argoverse Challenge at the CVPR 2023 Workshop on Autonomous Driving.
This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction. By delving into the vectorization pipeline, we elaborate an effective architecture, termed as MachMap, which formulates the task of HD-map construction as the point detection paradigm in the bird-eye-view space with an end-to-end manner. Firstly, we introduce a novel map-compaction scheme into our framework, leading to reducing the number of vectorized points by 93% without any expression performance degradation. Build upon the above process, we then follow the general query-based paradigm and propose a strong baseline with integrating a powerful CNN-based backbone like InternImage, a temporal-based instance decoder and a well-designed point-mask coupling head. Additionally, an extra optional ensemble stage is utilized to refine model predictions for better performance. Our MachMap-tiny with IN-1K initialization achieves a mAP of 79.1 on the Argoverse2 benchmark and the further improved MachMap-huge reaches the best mAP of 83.5, outperforming all the other online HD-map construction approaches on the final leaderboard with a distinct performance margin (> 9.8 mAP at least).
The human brain possesses remarkable abilities in visual processing, including image recognition and scene summarization. Efforts have been made to understand the cognitive capacities of the visual brain, but a comprehensive understanding of the underlying mechanisms still needs to be discovered. Advancements in brain decoding techniques have led to sophisticated approaches like fMRI-to-Image reconstruction, which has implications for cognitive neuroscience and medical imaging. However, challenges persist in fMRI-to-image reconstruction, such as incorporating global context and contextual information. In this article, we propose fMRI captioning, where captions are generated based on fMRI data to gain insight into the neural correlates of visual perception. This research presents DreamCatcher, a novel framework for fMRI captioning. DreamCatcher consists of the Representation Space Encoder (RSE) and the RevEmbedding Decoder, which transform fMRI vectors into a latent space and generate captions, respectively. We evaluated the framework through visualization, dataset training, and testing on subjects, demonstrating strong performance. fMRI-based captioning has diverse applications, including understanding neural mechanisms, Human-Computer Interaction, and enhancing learning and training processes.
Image inpainting for completing complicated semantic environments and diverse hole patterns of corrupted images is challenging even for state-of-the-art learning-based inpainting methods trained on large-scale data. A reference image capturing the same scene of a corrupted image offers informative guidance for completing the corrupted image as it shares similar texture and structure priors to that of the holes of the corrupted image. In this work, we propose a transformer-based encoder-decoder network, named TransRef, for reference-guided image inpainting. Specifically, the guidance is conducted progressively through a reference embedding procedure, in which the referencing features are subsequently aligned and fused with the features of the corrupted image. For precise utilization of the reference features for guidance, a reference-patch alignment (Ref-PA) module is proposed to align the patch features of the reference and corrupted images and harmonize their style differences, while a reference-patch transformer (Ref-PT) module is proposed to refine the embedded reference feature. Moreover, to facilitate the research of reference-guided image restoration tasks, we construct a publicly accessible benchmark dataset containing 50K pairs of input and reference images. Both quantitative and qualitative evaluations demonstrate the efficacy of the reference information and the proposed method over the state-of-the-art methods in completing complex holes. Code and dataset can be accessed at https://github.com/Cameltr/TransRef.
Radiology report generation aims to automatically generate a clinically accurate and coherent paragraph from the X-ray image, which could relieve radiologists from the heavy burden of report writing. Although various image caption methods have shown remarkable performance in the natural image field, generating accurate reports for medical images requires knowledge of multiple modalities, including vision, language, and medical terminology. We propose a Knowledge-injected U-Transformer (KiUT) to learn multi-level visual representation and adaptively distill the information with contextual and clinical knowledge for word prediction. In detail, a U-connection schema between the encoder and decoder is designed to model interactions between different modalities. And a symptom graph and an injected knowledge distiller are developed to assist the report generation. Experimentally, we outperform state-of-the-art methods on two widely used benchmark datasets: IU-Xray and MIMIC-CXR. Further experimental results prove the advantages of our architecture and the complementary benefits of the injected knowledge.
In recent years, there has been an increase in using deep learning for climate and weather modeling. Though results have been impressive, explainability and interpretability of deep learning models are still a challenge. A third wave of Artificial Intelligence (AI), which includes logic and reasoning, has been described as a way to address these issues. Neuro-symbolic AI is a key component of this integration of logic and reasoning with deep learning. In this work we propose a neuro-symbolic approach called Neuro-Symbolic Question-Answer Program Translator, or NS-QAPT, to address explainability and interpretability for deep learning climate simulation, applied to climate tipping point discovery. The NS-QAPT method includes a bidirectional encoder-decoder architecture that translates between domain-specific questions and executable programs used to direct the climate simulation, acting as a bridge between climate scientists and deep learning models. We show early compelling results of this translation method and introduce a domain-specific language and associated executable programs for a commonly known tipping point, the collapse of the Atlantic Meridional Overturning Circulation (AMOC).
Video anomaly detection aims to identify anomalous segments in a video. It is typically trained with weakly supervised video-level labels. This paper focuses on two crucial factors affecting the performance of video anomaly detection models. First, we explore how to capture the local and global temporal dependencies more effectively. Previous architectures are effective at capturing either local and global information, but not both. We propose to employ a U-Net like structure to model both types of dependencies in a unified structure where the encoder learns global dependencies hierarchically on top of local ones; then the decoder propagates this global information back to the segment level for classification. Second, overfitting is a non-trivial issue for video anomaly detection due to limited training data. We propose weakly supervised contrastive regularization which adopts a feature-based approach to regularize the network. Contrastive regularization learns more generalizable features by enforcing inter-class separability and intra-class compactness. Extensive experiments on the UCF-Crime dataset shows that our approach outperforms several state-of-the-art methods.
Deep learning models, especially U-Net and its derivate models, have been widely used in medical image segmentation. These approaches have achieved promising results in many medical image segmentation tasks with a limited number of training samples. We aim on enhancing medical image segmentation by using spatial continuity information in a proposed Multi-Encoder Parse-Decoder Network (MEPDNet) based on the fact that most of the medical images are sampled continuously. Sequential images are input into parameter-shared encoders for getting feature maps, which are then fused by a fusion block. A $\textbf{V}\mathbf{\Lambda}$-block is structured to parse the fused feature map to extract the hidden continuity information. The reconstructed feature map is fed into a decoder for generating segmentation masks. Experiments on three datasets show MEPDNet outperforms other state-of-the-art segmentation models while using the least parameters.
Superresolution (SR) of remote sensing images aims to restore high-quality information from low-resolution images. Recently, it has witnessed great strides with the rapid development of deep learning (DL) techniques. Despite their good performance, these DL-based models are often ineffective in balancing global and local feature extraction. Moreover, they are usually hindered by the poor image reconstruction capability of the decoder inside their SR models. To cope with this problem, this work proposes a novel global context-driven residual dense network (GCRDN) for satellite image SR based on the encoder and decoder architecture. In particular, the proposed encoder is endowed with nonlocal sparse attention modules incorporated into the residual dense network to learn robust representations from global features. Furthermore, a decoder equipped with back-sampling blocks is devised to fully exploit the feature maps extracted from the encoder. Extensive experimental comparisons based on two multisensor satellite remote sensing datasets confirm that the proposed GCRDN achieves impressive performance in terms of perceptual quality and fidelity.
Although temporal patterns inherent in visual and audio signals are crucial for affective video content analysis, they have not been thoroughly explored yet. In this paper, we propose a novel Temporal-Aware Multimodal (TAM) method to fully capture the temporal information. Specifically, we design a cross-temporal multimodal fusion module that applies attention-based fusion to different modalities within and across video segments. As a result, it fully captures the temporal relations between different modalities. Furthermore, a single emotion label lacks supervision for learning representation of each segment, making temporal pattern mining difficult. We leverage time-synchronized comments (TSCs) as auxiliary supervision, since these comments are easily accessible and contain rich emotional cues. Two TSC-based self-supervised tasks are designed: the first aims to predict the emotional words in a TSC from video representation and TSC contextual semantics, and the second predicts the segment in which the TSC appears by calculating the correlation between video representation and TSC embedding. These self-supervised tasks are used to pre-train the cross-temporal multimodal fusion module on a large-scale video-TSC dataset, which is crawled from the web without labeling costs. These self-supervised pre-training tasks prompt the fusion module to perform representation learning on segments including TSC, thus capturing more temporal affective patterns. Experimental results on three benchmark datasets show that the proposed fusion module achieves state-of-the-art results in affective video content analysis. Ablation studies verify that after TSC-based pre-training, the fusion module learns more segments' affective patterns and achieves better performance.