Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism. Recent studies have shown that explicitly modeling the input graph structure can significantly improve the performance. However, the vanilla structural encoder cannot capture all specialized information in a single forward pass for all decoding steps, resulting in inaccurate semantic representations. Meanwhile, the input graph is flatted as an unordered sequence in the cross attention, ignoring the original graph structure. As a result, the obtained input graph context vector in the decoder may be flawed. To address these issues, we propose a Structure-Aware Cross-Attention (SACA) mechanism to re-encode the input graph representation conditioning on the newly generated context at each decoding step in a structure aware manner. We further adapt SACA and introduce its variant Dynamic Graph Pruning (DGP) mechanism to dynamically drop irrelevant nodes in the decoding process. We achieve new state-of-the-art results on two graph-to-text datasets, LDC2020T02 and ENT-DESC, with only minor increase on computational cost.
We present a neural network architecture for medical image segmentation of diabetic foot ulcers and colonoscopy polyps. Diabetic foot ulcers are caused by neuropathic and vascular complications of diabetes mellitus. In order to provide a proper diagnosis and treatment, wound care professionals need to extract accurate morphological features from the foot wounds. Using computer-aided systems is a promising approach to extract related morphological features and segment the lesions. We propose a convolution neural network called HarDNet-DFUS by enhancing the backbone and replacing the decoder of HarDNet-MSEG, which was SOTA for colonoscopy polyp segmentation in 2021. For the MICCAI 2022 Diabetic Foot Ulcer Segmentation Challenge (DFUC2022), we train HarDNet-DFUS using the DFUC2022 dataset and increase its robustness by means of five-fold cross validation, Test Time Augmentation, etc. In the validation phase of DFUC2022, HarDNet-DFUS achieved 0.7063 mean dice and was ranked third among all participants. In the final testing phase of DFUC2022, it achieved 0.7287 mean dice and was the first place winner. HarDNet-DFUS also deliver excellent performance for the colonoscopy polyp segmentation task. It achieves 0.924 mean Dice on the famous Kvasir dataset, an improvement of 1.2\% over the original HarDNet-MSEG. The codes are available on https://github.com/kytimmylai/DFUC2022 (for Diabetic Foot Ulcers Segmentation) and https://github.com/YuWenLo/HarDNet-DFUS (for Colonoscopy Polyp Segmentation).
High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution representations. This will lose spatial information, and errors introduced by the decoder will be more serious when multiple types of objects are considered or objects are far away from the camera. To address these issues, we revisit the design paradigm of CNN for robotic perception tasks. We demonstrate that using parallel branches as opposed to serial stacked convolutional layers will be a more powerful design for robotic visual grasping tasks. In particular, guidelines of neural network design are provided for robotic perception tasks, e.g., high-resolution representation and lightweight design, which respond to the challenges in different manipulation scenarios. We then develop a novel grasping visual architecture referred to as HRG-Net, a parallel-branch structure that always maintains a high-resolution representation and repeatedly exchanges information across resolutions. Extensive experiments validate that these two designs can effectively enhance the accuracy of visual-based grasping and accelerate network training. We show a series of comparative experiments in real physical environments at Youtube: https://youtu.be/Jhlsp-xzHFY.
Effective scaling and a flexible task interface enable large language models to excel at many tasks. We present PaLI (Pathways Language and Image model), a model that extends this approach to the joint modeling of language and vision. PaLI generates text based on visual and textual inputs, and with this interface performs many vision, language, and multimodal tasks, in many languages. To train PaLI, we make use of large pre-trained encoder-decoder language models and Vision Transformers (ViTs). This allows us to capitalize on their existing capabilities and leverage the substantial cost of training them. We find that joint scaling of the vision and language components is important. Since existing Transformers for language are much larger than their vision counterparts, we train a large, 4-billion parameter ViT (ViT-e) to quantify the benefits from even larger-capacity vision models. To train PaLI, we create a large multilingual mix of pretraining tasks, based on a new image-text training set containing 10B images and texts in over 100 languages. PaLI achieves state-of-the-art in multiple vision and language tasks (such as captioning, visual question-answering, scene-text understanding), while retaining a simple, modular, and scalable design.
This paper presents a method of decoupled pronunciation and prosody modeling to improve the performance of meta-learning-based multilingual speech synthesis. The baseline meta-learning synthesis method adopts a single text encoder with a parameter generator conditioned on language embeddings and a single decoder to predict mel-spectrograms for all languages. In contrast, our proposed method designs a two-stream model structure that contains two encoders and two decoders for pronunciation and prosody modeling, respectively, considering that the pronunciation knowledge and the prosody knowledge should be shared in different ways among languages. In our experiments, our proposed method effectively improved the intelligibility and naturalness of multilingual speech synthesis comparing with the baseline meta-learning synthesis method.
Structure-based drug design is drawing growing attentions in computer-aided drug discovery. Compared with the virtual screening approach where a pre-defined library of compounds are computationally screened, de novo drug design based on the structure of a target protein can provide novel drug candidates. In this paper, we present a generative solution named TamGent (Target-aware molecule generator with Transformer) that can directly generate candidate drugs from scratch for a given target, overcoming the limits imposed by existing compound libraries. Following the Transformer framework (a state-of-the-art framework in deep learning), we design a variant of Transformer encoder to process 3D geometric information of targets and pre-train the Transformer decoder on 10 million compounds from PubChem for candidate drug generation. Systematical evaluation on candidate compounds generated for targets from DrugBank shows that both binding affinity and drugability are largely improved. TamGent outperforms previous baselines in terms of both effectiveness and efficiency. The method is further verified by generating candidate compounds for the SARS-CoV-2 main protease and the oncogenic mutant KRAS G12C. The results show that our method not only re-discovers previously verified drug molecules , but also generates novel molecules with better docking scores, expanding the compound pool and potentially leading to the discovery of novel drugs.
Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to explicitly complete missing annotations in partially annotated dense scene datasets. This reduces the need to annotate every object instance in the scene thereby reducing annotation cost. ComplETR augments object queries in DETR decoder with patch information of objects in the image. Combined with a matching loss, it can effectively find objects that are similar to the input patch and complete the missing annotations. We show that our framework outperforms the state-of-the-art methods such as Soft Sampling and Unbiased Teacher by itself, while at the same time can be used in conjunction with these methods to further improve their performance. Our framework is also agnostic to the choice of the downstream object detectors; we show performance improvement for several popular detectors such as Faster R-CNN, Cascade R-CNN, CenterNet2, and Deformable DETR on multiple dense scene datasets.
The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training objective. In this paper, we propose PreSTU, a novel pre-training recipe dedicated to scene-text understanding (STU). PreSTU introduces OCR-aware pre-training objectives that encourage the model to recognize text from an image and connect it to the rest of the image content. We implement PreSTU using a simple transformer-based encoder-decoder architecture, combined with large-scale image-text datasets with scene text obtained from an off-the-shelf OCR system. We empirically demonstrate the effectiveness of this pre-training approach on eight visual question answering and four image captioning benchmarks.
In this paper, we propose a novel pipeline that leverages language foundation models for temporal sequential pattern mining, such as for human mobility forecasting tasks. For example, in the task of predicting Place-of-Interest (POI) customer flows, typically the number of visits is extracted from historical logs, and only the numerical data are used to predict visitor flows. In this research, we perform the forecasting task directly on the natural language input that includes all kinds of information such as numerical values and contextual semantic information. Specific prompts are introduced to transform numerical temporal sequences into sentences so that existing language models can be directly applied. We design an AuxMobLCast pipeline for predicting the number of visitors in each POI, integrating an auxiliary POI category classification task with the encoder-decoder architecture. This research provides empirical evidence of the effectiveness of the proposed AuxMobLCast pipeline to discover sequential patterns in mobility forecasting tasks. The results, evaluated on three real-world datasets, demonstrate that pre-trained language foundation models also have good performance in forecasting temporal sequences. This study could provide visionary insights and lead to new research directions for predicting human mobility.
We present SeRP, a framework for Self-Supervised Learning of 3D point clouds. SeRP consists of encoder-decoder architecture that takes perturbed or corrupted point clouds as inputs and aims to reconstruct the original point cloud without corruption. The encoder learns the high-level latent representations of the points clouds in a low-dimensional subspace and recovers the original structure. In this work, we have used Transformers and PointNet-based Autoencoders. The proposed framework also addresses some of the limitations of Transformers-based Masked Autoencoders which are prone to leakage of location information and uneven information density. We trained our models on the complete ShapeNet dataset and evaluated them on ModelNet40 as a downstream classification task. We have shown that the pretrained models achieved 0.5-1% higher classification accuracies than the networks trained from scratch. Furthermore, we also proposed VASP: Vector-Quantized Autoencoder for Self-supervised Representation Learning for Point Clouds that employs Vector-Quantization for discrete representation learning for Transformer-based autoencoders.
Transformers combined with convolutional encoders have been recently used for hand gesture recognition (HGR) using micro-Doppler signatures. We propose a vision-transformer-based architecture for HGR with multi-antenna continuous-wave Doppler radar receivers. The proposed architecture consists of three modules: a convolutional encoderdecoder, an attention module with three transformer layers, and a multi-layer perceptron. The novel convolutional decoder helps to feed patches with larger sizes to the attention module for improved feature extraction. Experimental results obtained with a dataset corresponding to a two-antenna continuous-wave Doppler radar receiver operating at 24 GHz (published by Skaria et al.) confirm that the proposed architecture achieves an accuracy of 98.3% which substantially surpasses the state-of-the-art on the used dataset.
Decoders built on Gaussian processes (GPs) are enticing due to the marginalisation over the non-linear function space. Such models (also known as GP-LVMs) are often expensive and notoriously difficult to train in practice, but can be scaled using variational inference and inducing points. In this paper, we revisit active set approximations. We develop a new stochastic estimate of the log-marginal likelihood based on recently discovered links to cross-validation, and propose a computationally efficient approximation thereof. We demonstrate that the resulting stochastic active sets (SAS) approximation significantly improves the robustness of GP decoder training while reducing computational cost. The SAS-GP obtains more structure in the latent space, scales to many datapoints and learns better representations than variational autoencoders, which is rarely the case for GP decoders.
The handwritten text recognition problem is widely studied by the researchers of computer vision community due to its scope of improvement and applicability to daily lives, It is a sub-domain of pattern recognition. Due to advancement of computational power of computers since last few decades neural networks based systems heavily contributed towards providing the state-of-the-art handwritten text recognizers. In the same direction, we have taken two state-of-the art neural networks systems and merged the attention mechanism with it. The attention technique has been widely used in the domain of neural machine translations and automatic speech recognition and now is being implemented in text recognition domain. In this study, we are able to achieve 4.15% character error rate and 9.72% word error rate on IAM dataset, 7.07% character error rate and 16.14% word error rate on GW dataset after merging the attention and word beam search decoder with existing Flor et al. architecture. To analyse further, we have also used system similar to Shi et al. neural network system with greedy decoder and observed 23.27% improvement in character error rate from the base model.
Multi-Document Scientific Summarization (MDSS) aims to produce coherent and concise summaries for clusters of topic-relevant scientific papers. This task requires precise understanding of paper content and accurate modeling of cross-paper relationships. Knowledge graphs convey compact and interpretable structured information for documents, which makes them ideal for content modeling and relationship modeling. In this paper, we present KGSum, an MDSS model centred on knowledge graphs during both the encoding and decoding process. Specifically, in the encoding process, two graph-based modules are proposed to incorporate knowledge graph information into paper encoding, while in the decoding process, we propose a two-stage decoder by first generating knowledge graph information of summary in the form of descriptive sentences, followed by generating the final summary. Empirical results show that the proposed architecture brings substantial improvements over baselines on the Multi-Xscience dataset.
Sparse representations of images are useful in many computer vision applications. Sparse coding with an $l_1$ penalty and a learned linear dictionary requires regularization of the dictionary to prevent a collapse in the $l_1$ norms of the codes. Typically, this regularization entails bounding the Euclidean norms of the dictionary's elements. In this work, we propose a novel sparse coding protocol which prevents a collapse in the codes without the need to regularize the decoder. Our method regularizes the codes directly so that each latent code component has variance greater than a fixed threshold over a set of sparse representations for a given set of inputs. Furthermore, we explore ways to effectively train sparse coding systems with multi-layer decoders since they can model more complex relationships than linear dictionaries. In our experiments with MNIST and natural image patches, we show that decoders learned with our approach have interpretable features both in the linear and multi-layer case. Moreover, we show that sparse autoencoders with multi-layer decoders trained using our variance regularization method produce higher quality reconstructions with sparser representations when compared to autoencoders with linear dictionaries. Additionally, sparse representations obtained with our variance regularization approach are useful in the downstream tasks of denoising and classification in the low-data regime.
Robotic arms are widely used in automatic industries. However, with wide applications of deep learning in robotic arms, there are new challenges such as the allocation of grasping computing power and the growing demand for security. In this work, we propose a robotic arm grasping approach based on deep learning and edge-cloud collaboration. This approach realizes the arbitrary grasp planning of the robot arm and considers the grasp efficiency and information security. In addition, the encoder and decoder trained by GAN enable the images to be encrypted while compressing, which ensures the security of privacy. The model achieves 92% accuracy on the OCID dataset, the image compression ratio reaches 0.03%, and the structural difference value is higher than 0.91.
We propose a two-stage approach for training a single NMT model to translate unseen languages both to and from English. For the first stage, we initialize an encoder-decoder model to pretrained XLM-R and RoBERTa weights, then perform multilingual fine-tuning on parallel data in 40 languages to English. We find this model can generalize to zero-shot translations on unseen languages. For the second stage, we leverage this generalization ability to generate synthetic parallel data from monolingual datasets, then bidirectionally train with successive rounds of back-translation. Our approach, which we EcXTra (English-centric Crosslingual (X) Transfer), is conceptually simple, only using a standard cross-entropy objective throughout. It is also data-driven, sequentially leveraging auxiliary parallel data and monolingual data. We evaluate unsupervised NMT results for 7 low-resource languages, and find that each round of back-translation training further refines bidirectional performance. Our final single EcXTra-trained model achieves competitive translation performance in all translation directions, notably establishing a new state-of-the-art for English-to-Kazakh (22.9 > 10.4 BLEU). Our code is available at https://github.com/manestay/EcXTra .
Extracting depth information from a single RGB image is a fundamental and challenging task in computer vision with wide-ranging applications. This task cannot be solved using traditional methods like multi-view geometry but only by deep learning. Existing methods using convolutional neural nets produce inconsistent and blurry results due to the lack of long-range dependencies. With the recent success of Transformer networks in computer vision, which can process information locally and globally, we leverage this idea to propose a novel architecture named Focal-WNet in this paper. This architecture consists of two separate encoders and a single decoder. The main aim of this network is to learn most monocular depth cues like relative scale, contrast differences, texture gradient, etc. We incorporate focal self-attention instead of vanilla self-attention to reduce the computational complexity of the network. Along with the focal transformer layers, we leverage a convolutional architecture to learn depth cues that cannot be learned by a transformer alone as some cues like occlusion require a local receptive field and are easier for a conv-net to learn. Extensive experiments show that the proposed Focal-WNet achieves competitive results on two challenging datasets.
Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely used to improve PET image quality. Though successful and efficient in local feature extraction, CNN cannot capture long-range dependencies well due to its limited receptive field. Global multi-head self-attention (MSA) is a popular approach to capture long-range information. However, the calculation of global MSA for 3D images has high computational costs. In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs. Experiments based on datasets of different PET tracers, i.e., $^{18}$F-FDG, $^{18}$F-ACBC, $^{18}$F-DCFPyL, and $^{68}$Ga-DOTATATE, were conducted to evaluate the proposed framework. Quantitative results show that the proposed Spach Transformer framework outperforms state-of-the-art deep learning architectures. Our codes are available at https://github.com/sijang/SpachTransformer
Octree-based point cloud representation and compression have been adopted by the MPEG G-PCC standard. However, it only uses handcrafted methods to predict the probability that a leaf node is non-empty, which is then used for entropy coding. We propose a novel approach for predicting such probabilities for geometry coding, which applies a denoising neural network to a "noisy" context cube that includes both neighboring decoded voxels as well as uncoded voxels. We further propose a convolution-based model to upsample the decoded point cloud at a coarse resolution on the decoder side. Integration of the two approaches significantly improves the rate-distortion performance for geometry coding compared to the original G-PCC standard and other baseline methods for dense point clouds. The proposed octree-based entropy coding approach is naturally scalable, which is desirable for dynamic rate adaptation in point cloud streaming systems.