Although user cooperation cannot improve the capacity of Gaussian two-way channels (GTWCs) with independent noises, it can improve communication reliability. In this work, we aim to enhance and balance the communication reliability in GTWCs by minimizing the sum of error probabilities via joint design of encoders and decoders at the users. We first formulate general encoding/decoding functions, where the user cooperation is captured by the coupling of user encoding processes. The coupling effect renders the encoder/decoder design non-trivial, requiring effective decoding to capture this effect, as well as efficient power management at the encoders within power constraints. To address these challenges, we propose two different two-way coding strategies: linear coding and learning-based coding. For linear coding, we propose optimal linear decoding and discuss new insights on encoding regarding user cooperation to balance reliability. We then propose an efficient algorithm for joint encoder/decoder design. For learning-based coding, we introduce a novel recurrent neural network (RNN)-based coding architecture, where we propose interactive RNNs and a power control layer for encoding, and we incorporate bi-directional RNNs with an attention mechanism for decoding. Through simulations, we show that our two-way coding methodologies outperform conventional channel coding schemes (that do not utilize user cooperation) significantly in sum-error performance. We also demonstrate that our linear coding excels at high signal-to-noise ratios (SNRs), while our RNN-based coding performs best at low SNRs. We further investigate our two-way coding strategies in terms of power distribution, two-way coding benefit, different coding rates, and block-length gain.
The Handwritten Mathematical Expression Recognition (HMER) task is a critical branch in the field of OCR. Recent studies have demonstrated that incorporating bidirectional context information significantly improves the performance of HMER models. However, existing methods fail to effectively utilize bidirectional context information during the inference stage. Furthermore, current bidirectional training methods are primarily designed for string decoders and cannot adequately generalize to tree decoders, which offer superior generalization capabilities and structural analysis capacity. In order to overcome these limitations, we propose the Mirror-Flipped Symbol Layout Tree (MF-SLT) and Bidirectional Asynchronous Training (BAT) structure. Our method extends the bidirectional training strategy to the tree decoder, allowing for more effective training by leveraging bidirectional information. Additionally, we analyze the impact of the visual and linguistic perception of the HMER model separately and introduce the Shared Language Modeling (SLM) mechanism. Through the SLM, we enhance the model's robustness and generalization when dealing with visual ambiguity, particularly in scenarios with abundant training data. Our approach has been validated through extensive experiments, demonstrating its ability to achieve new state-of-the-art results on the CROHME 2014, 2016, and 2019 datasets, as well as the HME100K dataset. The code used in our experiments will be publicly available.
In this paper, we propose a novel method for joint entity and relation extraction from unstructured text by framing it as a conditional sequence generation problem. In contrast to conventional generative information extraction models that are left-to-right token-level generators, our approach is \textit{span-based}. It generates a linearized graph where nodes represent text spans and edges represent relation triplets. Our method employs a transformer encoder-decoder architecture with pointing mechanism on a dynamic vocabulary of spans and relation types. Our model can capture the structural characteristics and boundaries of entities and relations through span representations while simultaneously grounding the generated output in the original text thanks to the pointing mechanism. Evaluation on benchmark datasets validates the effectiveness of our approach, demonstrating competitive results. Code is available at https://github.com/urchade/ATG.
In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the look-ahead and past contexts in the encoder, and (2) introducing an activation caching mechanism to enable the non-autoregressive encoder to operate autoregressively during inference. The proposed model is thoughtfully designed in a way to eliminate the accuracy disparity between the train and inference time which is common for many streaming models. Furthermore, our proposed encoder works with various decoder configurations including Connectionist Temporal Classification (CTC) and RNN-Transducer (RNNT) decoders. Additionally, we introduced a hybrid CTC/RNNT architecture which utilizes a shared encoder with both a CTC and RNNT decoder to boost the accuracy and save computation. We evaluate the proposed model on LibriSpeech dataset and a multi-domain large scale dataset and demonstrate that it can achieve better accuracy with lower latency and inference time compared to a conventional buffered streaming model baseline. We also showed that training a model with multiple latencies can achieve better accuracy than single latency models while it enables us to support multiple latencies with a single model. Our experiments also showed the hybrid architecture would not only speedup the convergence of the CTC decoder but also improves the accuracy of streaming models compared to single decoder models.
Zero-Shot Object Counting (ZSOC) aims to count referred instances of arbitrary classes in a query image without human-annotated exemplars. To deal with ZSOC, preceding studies proposed a two-stage pipeline: discovering exemplars and counting. However, there remains a challenge of vulnerability to error propagation of the sequentially designed two-stage process. In this work, an one-stage baseline, Visual-Language Baseline (VLBase), exploring the implicit association of the semantic-patch embeddings of CLIP is proposed. Subsequently, the extension of VLBase to Visual-language Counter (VLCounter) is achieved by incorporating three modules devised to tailor VLBase for object counting. First, Semantic-conditioned Prompt Tuning (SPT) is introduced within the image encoder to acquire target-highlighted representations. Second, Learnable Affine Transformation (LAT) is employed to translate the semantic-patch similarity map to be appropriate for the counting task. Lastly, the layer-wisely encoded features are transferred to the decoder through Segment-aware Skip Connection (SaSC) to keep the generalization capability for unseen classes. Through extensive experiments on FSC147, CARPK, and PUCPR+, the benefits of the end-to-end framework, VLCounter, are demonstrated.
We address the challenges in estimating 3D human poses from multiple views under occlusion and with limited overlapping views. We approach multi-view, single-person 3D human pose reconstruction as a regression problem and propose a novel encoder-decoder Transformer architecture to estimate 3D poses from multi-view 2D pose sequences. The encoder refines 2D skeleton joints detected across different views and times, fusing multi-view and temporal information through global self-attention. We enhance the encoder by incorporating a geometry-biased attention mechanism, effectively leveraging geometric relationships between views. Additionally, we use detection scores provided by the 2D pose detector to further guide the encoder's attention based on the reliability of the 2D detections. The decoder subsequently regresses the 3D pose sequence from these refined tokens, using pre-defined queries for each joint. To enhance the generalization of our method to unseen scenes and improve resilience to missing joints, we implement strategies including scene centering, synthetic views, and token dropout. We conduct extensive experiments on three benchmark public datasets, Human3.6M, CMU Panoptic and Occlusion-Persons. Our results demonstrate the efficacy of our approach, particularly in occluded scenes and when few views are available, which are traditionally challenging scenarios for triangulation-based methods.
Multi-view compression technology, especially Stereo Image Compression (SIC), plays a crucial role in car-mounted cameras and 3D-related applications. Interestingly, the Distributed Source Coding (DSC) theory suggests that efficient data compression of correlated sources can be achieved through independent encoding and joint decoding. This motivates the rapidly developed deep-distributed SIC methods in recent years. However, these approaches neglect the unique characteristics of stereo-imaging tasks and incur high decoding latency. To address this limitation, we propose a Feature-based Fast Cascade Alignment network (FFCA-Net) to fully leverage the side information on the decoder. FFCA adopts a coarse-to-fine cascaded alignment approach. In the initial stage, FFCA utilizes a feature domain patch-matching module based on stereo priors. This module reduces redundancy in the search space of trivial matching methods and further mitigates the introduction of noise. In the subsequent stage, we utilize an hourglass-based sparse stereo refinement network to further align inter-image features with a reduced computational cost. Furthermore, we have devised a lightweight yet high-performance feature fusion network, called a Fast Feature Fusion network (FFF), to decode the aligned features. Experimental results on InStereo2K, KITTI, and Cityscapes datasets demonstrate the significant superiority of our approach over traditional and learning-based SIC methods. In particular, our approach achieves significant gains in terms of 3 to 10-fold faster decoding speed than other methods.
We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action. To unify different modalities, we tokenize inputs and outputs -- images, text, audio, action, bounding boxes, etc., into a shared semantic space and then process them with a single encoder-decoder transformer model. Since training with such diverse modalities is challenging, we propose various architectural improvements to stabilize model training. We train our model from scratch on a large multimodal pre-training corpus from diverse sources with a multimodal mixture of denoisers objective. To learn an expansive set of skills, such as following multimodal instructions, we construct and finetune on an ensemble of 120 datasets with prompts and augmentations. With a single unified model, Unified-IO 2 achieves state-of-the-art performance on the GRIT benchmark and strong results in more than 35 benchmarks, including image generation and understanding, natural language understanding, video and audio understanding, and robotic manipulation. We release all our models to the research community.
The resource efficiency of video analytics workloads is critical for large-scale deployments on edge nodes and cloud clusters. Recent advanced systems have benefited from techniques including video compression, frame filtering, and deep model acceleration. However, based on our year-long experience of operating a real-time video analytics system on more than 1000 cameras, we identified a previously overlooked bottleneck of end-to-end concurrency: video decoding. To support concurrent video inference at scale, in this work, we investigate a new task, named video packet gating, which selectively filters packets before running a decoder. We propose a novel multi-view embedding approach for video packets and present PacketGame that has both theoretical performance guarantee and practical system designs. Experiments on both public datasets and a real system show PacketGame saves 52.0--79.3% decoding costs and achieves 2.1--4.8× concurrency compared to original workloads. Comparisons with four state-of-the-art complementary methods show the superiority of PacketGame in end-to-end concurrency.
3D object detection in point clouds is important for autonomous driving systems. A primary challenge in 3D object detection stems from the sparse distribution of points within the 3D scene. Existing high-performance methods typically employ 3D sparse convolutional neural networks with small kernels to extract features. To reduce computational costs, these methods resort to submanifold sparse convolutions, which prevent the information exchange among spatially disconnected features. Some recent approaches have attempted to address this problem by introducing large-kernel convolutions or self-attention mechanisms, but they either achieve limited accuracy improvements or incur excessive computational costs. We propose HEDNet, a hierarchical encoder-decoder network for 3D object detection, which leverages encoder-decoder blocks to capture long-range dependencies among features in the spatial space, particularly for large and distant objects. We conducted extensive experiments on the Waymo Open and nuScenes datasets. HEDNet achieved superior detection accuracy on both datasets than previous state-of-the-art methods with competitive efficiency. The code is available at https://github.com/zhanggang001/HEDNet.
Recent work in zero-shot listwise reranking using LLMs has achieved state-of-the-art results. However, these methods are not without drawbacks. The proposed methods rely on large LLMs with billions of parameters and limited context sizes. This paper introduces LiT5-Distill and LiT5-Score, two methods for efficient zero-shot listwise reranking, leveraging T5 sequence-to-sequence encoder-decoder models. Our approaches demonstrate competitive reranking effectiveness compared to recent state-of-the-art LLM rerankers with substantially smaller models. Through LiT5-Score, we also explore the use of cross-attention to calculate relevance scores to perform reranking, eliminating the reliance on external passage relevance labels for training. We present a range of models from 220M parameters to 3B parameters, all with strong reranking results, challenging the necessity of large-scale models for effective zero-shot reranking and opening avenues for more efficient listwise reranking solutions. We provide code and scripts to reproduce our results at https://github.com/castorini/LiT5.
Sign language translation (SLT) aims to convert continuous sign language videos into textual sentences. As a typical multi-modal task, there exists an inherent modality gap between sign language videos and spoken language text, which makes the cross-modal alignment between visual and textual modalities crucial. However, previous studies tend to rely on an intermediate sign gloss representation to help alleviate the cross-modal problem thereby neglecting the alignment across modalities that may lead to compromised results. To address this issue, we propose a novel framework based on Conditional Variational autoencoder for SLT (CV-SLT) that facilitates direct and sufficient cross-modal alignment between sign language videos and spoken language text. Specifically, our CV-SLT consists of two paths with two Kullback-Leibler (KL) divergences to regularize the outputs of the encoder and decoder, respectively. In the prior path, the model solely relies on visual information to predict the target text; whereas in the posterior path, it simultaneously encodes visual information and textual knowledge to reconstruct the target text. The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs. We further enhance the integration of textual information to the posterior path by employing a shared Attention Residual Gaussian Distribution (ARGD), which considers the textual information in the posterior path as a residual component relative to the prior path. Extensive experiments conducted on public datasets (PHOENIX14T and CSL-daily) demonstrate the effectiveness of our framework, achieving new state-of-the-art results while significantly alleviating the cross-modal representation discrepancy.
Individuals, despite having varied life experiences and learning processes, can communicate effectively through languages. This study aims to explore the efficiency of language as a communication medium. We put forth two specific hypotheses: First, discrete messages are more effective than continuous ones when agents have diverse personal experiences. Second, communications using multiple discrete tokens are more advantageous than those using a single token. To valdate these hypotheses, we designed multi-agent machine learning experiments to assess communication efficiency using various information transmission methods between speakers and listeners. Our empirical findings indicate that, in scenarios where agents are exposed to different data, communicating through sentences composed of discrete tokens offers the best inter-agent communication efficiency. The limitations of our finding include lack of systematic advantages over other more sophisticated encoder-decoder model such as variational autoencoder and lack of evluation on non-image dataset, which we will leave for future studies.
While it is important to make implantable brain-machine interfaces (iBMI) wireless to increase patient comfort and safety, the trend of increased channel count in recent neural probes poses a challenge due to the concomitant increase in the data rate. Extracting information from raw data at the source by using edge computing is a promising solution to this problem, with integrated intention decoders providing the best compression ratio. Recent benchmarking efforts have shown recurrent neural networks to be the best solution. Spiking Neural Networks (SNN) emerge as a promising solution for resource efficient neural decoding while Long Short Term Memory (LSTM) networks achieve the best accuracy. In this work, we show that combining traditional signal processing techniques, namely signal filtering, with SNNs improve their decoding performance significantly for regression tasks, closing the gap with LSTMs, at little added cost. Results with different filters are shown with Bessel filters providing best performance. Two block-bidirectional Bessel filters have been used--one for low latency and another for high accuracy. Adding the high accuracy variant of the Bessel filters to the output of ANN, SNN and variants provided statistically significant benefits with maximum gains of $\approx 5\%$ and $8\%$ in $R^2$ for two SNN topologies (SNN\_Streaming and SNN\_3D). Our work presents state of the art results for this dataset and paves the way for decoder-integrated-implants of the future.
Generalization and sample efficiency have been long-standing issues concerning reinforcement learning, and thus the field of Offline Meta-Reinforcement Learning~(OMRL) has gained increasing attention due to its potential of solving a wide range of problems with static and limited offline data. Existing OMRL methods often assume sufficient training tasks and data coverage to apply contrastive learning to extract task representations. However, such assumptions are not applicable in several real-world applications and thus undermine the generalization ability of the representations. In this paper, we consider OMRL with two types of data limitations: limited training tasks and limited behavior diversity and propose a novel algorithm called GENTLE for learning generalizable task representations in the face of data limitations. GENTLE employs Task Auto-Encoder~(TAE), which is an encoder-decoder architecture to extract the characteristics of the tasks. Unlike existing methods, TAE is optimized solely by reconstruction of the state transition and reward, which captures the generative structure of the task models and produces generalizable representations when training tasks are limited. To alleviate the effect of limited behavior diversity, we consistently construct pseudo-transitions to align the data distribution used to train TAE with the data distribution encountered during testing. Empirically, GENTLE significantly outperforms existing OMRL methods on both in-distribution tasks and out-of-distribution tasks across both the given-context protocol and the one-shot protocol.
In the domain of medical imaging, many supervised learning based methods for segmentation face several challenges such as high variability in annotations from multiple experts, paucity of labelled data and class imbalanced datasets. These issues may result in segmentations that lack the requisite precision for clinical analysis and can be misleadingly overconfident without associated uncertainty quantification. This work proposes the PULASki method as a computationally efficient generative tool for biomedical image segmentation that accurately captures variability in expert annotations, even in small datasets. This approach makes use of an improved loss function based on statistical distances in a conditional variational autoencoder structure (Probabilistic UNet), which improves learning of the conditional decoder compared to the standard cross-entropy particularly in class imbalanced problems. The proposed method was analysed for two structurally different segmentation tasks (intracranial vessel and multiple sclerosis (MS) lesion) and compare our results to four well-established baselines in terms of quantitative metrics and qualitative output. These experiments involve class-imbalanced datasets characterised by challenging features, including suboptimal signal-to-noise ratios and high ambiguity. Empirical results demonstrate the PULASKi method outperforms all baselines at the 5\% significance level. Our experiments are also of the first to present a comparative study of the computationally feasible segmentation of complex geometries using 3D patches and the traditional use of 2D slices. The generated segmentations are shown to be much more anatomically plausible than in the 2D case, particularly for the vessel task.
Most state-of-the-art methods for medical image segmentation adopt the encoder-decoder architecture. However, this U-shaped framework still has limitations in capturing the non-local multi-scale information with a simple skip connection. To solve the problem, we firstly explore the potential weakness of skip connections in U-Net on multiple segmentation tasks, and find that i) not all skip connections are useful, each skip connection has different contribution; ii) the optimal combinations of skip connections are different, relying on the specific datasets. Based on our findings, we propose a new segmentation framework, named UDTransNet, to solve three semantic gaps in U-Net. Specifically, we propose a Dual Attention Transformer (DAT) module for capturing the channel- and spatial-wise relationships to better fuse the encoder features, and a Decoder-guided Recalibration Attention (DRA) module for effectively connecting the DAT tokens and the decoder features to eliminate the inconsistency. Hence, both modules establish a learnable connection to solve the semantic gaps between the encoder and the decoder, which leads to a high-performance segmentation model for medical images. Comprehensive experimental results indicate that our UDTransNet produces higher evaluation scores and finer segmentation results with relatively fewer parameters over the state-of-the-art segmentation methods on different public datasets. Code: https://github.com/McGregorWwww/UDTransNet.
Pulmonary embolism (PE) is a prevalent lung disease that can lead to right ventricular hypertrophy and failure in severe cases, ranking second in severity only to myocardial infarction and sudden death. Pulmonary artery CT angiography (CTPA) is a widely used diagnostic method for PE. However, PE detection presents challenges in clinical practice due to limitations in imaging technology. CTPA can produce noises similar to PE, making confirmation of its presence time-consuming and prone to overdiagnosis. Nevertheless, the traditional segmentation method of PE can not fully consider the hierarchical structure of features, local and global spatial features of PE CT images. In this paper, we propose an automatic PE segmentation method called SCUNet++ (Swin Conv UNet++). This method incorporates multiple fusion dense skip connections between the encoder and decoder, utilizing the Swin Transformer as the encoder. And fuses features of different scales in the decoder subnetwork to compensate for spatial information loss caused by the inevitable downsampling in Swin-UNet or other state-of-the-art methods, effectively solving the above problem. We provide a theoretical analysis of this method in detail and validate it on publicly available PE CT image datasets FUMPE and CAD-PE. The experimental results indicate that our proposed method achieved a Dice similarity coefficient (DSC) of 83.47% and a Hausdorff distance 95th percentile (HD95) of 3.83 on the FUMPE dataset, as well as a DSC of 83.42% and an HD95 of 5.10 on the CAD-PE dataset. These findings demonstrate that our method exhibits strong performance in PE segmentation tasks, potentially enhancing the accuracy of automatic segmentation of PE and providing a powerful diagnostic tool for clinical physicians. Our source code and new FUMPE dataset are available at https://github.com/JustlfC03/SCUNet-plusplus.
X-ray free-electron lasers (XFELs) offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate XFELs enable single particle imaging (X-ray SPI) where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray SPI reconstruction algorithms, which estimate the unknown orientation of a particle in each captured image as well as its shared 3D structure, are inadequate in handling the massive datasets generated by these emerging XFELs. Here, we introduce X-RAI, an online reconstruction framework that estimates the structure of a 3D macromolecule from large X-ray SPI datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray SPI towards real-time capture and reconstruction.
Multi-task dense prediction aims at handling multiple pixel-wise prediction tasks within a unified network simultaneously for visual scene understanding. However, cross-task feature interactions of current methods are still suffering from incomplete levels of representations, less discriminative semantics in feature participants, and inefficient pair-wise task interaction processes. To tackle these under-explored issues, we propose a novel BridgeNet framework, which extracts comprehensive and discriminative intermediate Bridge Features, and conducts interactions based on them. Specifically, a Task Pattern Propagation (TPP) module is firstly applied to ensure highly semantic task-specific feature participants are prepared for subsequent interactions, and a Bridge Feature Extractor (BFE) is specially designed to selectively integrate both high-level and low-level representations to generate the comprehensive bridge features. Then, instead of conducting heavy pair-wise cross-task interactions, a Task-Feature Refiner (TFR) is developed to efficiently take guidance from bridge features and form final task predictions. To the best of our knowledge, this is the first work considering the completeness and quality of feature participants in cross-task interactions. Extensive experiments are conducted on NYUD-v2, Cityscapes and PASCAL Context benchmarks, and the superior performance shows the proposed architecture is effective and powerful in promoting different dense prediction tasks simultaneously.