Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and finally hampering the model performance. To address this limitation, in this work, we introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout, enabling their unique characteristics to be exploited during the whole perception pipeline. To demonstrate the effectiveness of the proposed strategy, we design DeepInteraction++, a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Specifically, the encoder is implemented as a dual-stream Transformer with specialized attention operation for information exchange and integration between separate modality-specific representations. Our multi-modal representational learning incorporates both object-centric, precise sampling-based feature alignment and global dense information spreading, essential for the more challenging planning task. The decoder is designed to iteratively refine the predictions by alternately aggregating information from separate representations in a unified modality-agnostic manner, realizing multi-modal predictive interaction. Extensive experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks. Our code is available at https://github.com/fudan-zvg/DeepInteraction.
Surrogate models that combine dimensionality reduction and regression techniques are essential to reduce the need for costly high-fidelity computational fluid dynamics data. New approaches using $\beta$-Variational Autoencoder ($\beta$-VAE) architectures have shown promise in obtaining high-quality low-dimensional representations of high-dimensional flow data while enabling physical interpretation of their latent spaces. We propose a surrogate model based on latent space regression to predict pressure distributions on a transonic wing given the flight conditions: Mach number and angle of attack. The $\beta$-VAE model, enhanced with Principal Component Analysis (PCA), maps high-dimensional data to a low-dimensional latent space, showing a direct correlation with flight conditions. Regularization through $\beta$ requires careful tuning to improve overall performance, while PCA preprocessing helps to construct an effective latent space, improving autoencoder training and performance. Gaussian Process Regression is used to predict latent space variables from flight conditions, showing robust behavior independent of $\beta$, and the decoder reconstructs the high-dimensional pressure field data. This pipeline provides insight into unexplored flight conditions. Furthermore, a fine-tuning process of the decoder further refines the model, reducing the dependence on $\beta$ and enhancing accuracy. Structured latent space, robust regression performance, and significant improvements in fine-tuning collectively create a highly accurate and efficient surrogate model. Our methodology demonstrates the effectiveness of $\beta$-VAEs for aerodynamic surrogate modeling, offering a rapid, cost-effective, and reliable alternative for aerodynamic data prediction.
In automatic speech recognition, subsampling is essential for tackling diverse scenarios. However, the inadequacy of a single subsampling rate to address various real-world situations often necessitates training and deploying multiple models, consequently increasing associated costs. To address this issue, we propose HydraFormer, comprising HydraSub, a Conformer-based encoder, and a BiTransformer-based decoder. HydraSub encompasses multiple branches, each representing a distinct subsampling rate, allowing for the flexible selection of any branch during inference based on the specific use case. HydraFormer can efficiently manage different subsampling rates, significantly reducing training and deployment expenses. Experiments on AISHELL-1 and LibriSpeech datasets reveal that HydraFormer effectively adapts to various subsampling rates and languages while maintaining high recognition performance. Additionally, HydraFormer showcases exceptional stability, sustaining consistent performance under various initialization conditions, and exhibits robust transferability by learning from pretrained single subsampling rate automatic speech recognition models\footnote{Model code and scripts: https://github.com/HydraFormer/hydraformer}.
This research introduces the first multimodal approach for pavement condition assessment, providing both quantitative Pavement Condition Index (PCI) predictions and qualitative descriptions. We introduce PaveCap, a novel framework for automated pavement condition assessment. The framework consists of two main parts: a Single-Shot PCI Estimation Network and a Dense Captioning Network. The PCI Estimation Network uses YOLOv8 for object detection, the Segment Anything Model (SAM) for zero-shot segmentation, and a four-layer convolutional neural network to predict PCI. The Dense Captioning Network uses a YOLOv8 backbone, a Transformer encoder-decoder architecture, and a convolutional feed-forward module to generate detailed descriptions of pavement conditions. To train and evaluate these networks, we developed a pavement dataset with bounding box annotations, textual annotations, and PCI values. The results of our PCI Estimation Network showed a strong positive correlation (0.70) between predicted and actual PCIs, demonstrating its effectiveness in automating condition assessment. Also, the Dense Captioning Network produced accurate pavement condition descriptions, evidenced by high BLEU (0.7445), GLEU (0.5893), and METEOR (0.7252) scores. Additionally, the dense captioning model handled complex scenarios well, even correcting some errors in the ground truth data. The framework developed here can greatly improve infrastructure management and decision18 making in pavement maintenance.
In this project, we train a vision encoder-decoder model to generate LaTeX code from images of mathematical formulas and text. Utilizing a diverse collection of image-to-LaTeX data, we build two models: a base model with a Swin Transformer encoder and a GPT-2 decoder, trained on machine-generated images, and a fine-tuned version enhanced with Low-Rank Adaptation (LoRA) trained on handwritten formulas. We then compare the BLEU performance of our specialized model on a handwritten test set with other similar models, such as Pix2Text, TexTeller, and Sumen. Through this project, we contribute open-source models for converting images to LaTeX and provide from-scratch code for building these models with distributed training and GPU optimizations.
Knowledge graphs (KGs) enhance the performance of large language models (LLMs) and search engines by providing structured, interconnected data that improves reasoning and context-awareness. However, KGs only focus on text data, thereby neglecting other modalities such as speech. In this work, we introduce wav2graph, the first framework for supervised learning knowledge graph from speech data. Our pipeline are straightforward: (1) constructing a KG based on transcribed spoken utterances and a named entity database, (2) converting KG into embedding vectors, and (3) training graph neural networks (GNNs) for node classification and link prediction tasks. Through extensive experiments conducted in inductive and transductive learning contexts using state-of-the-art GNN models, we provide baseline results and error analysis for node classification and link prediction tasks on human transcripts and automatic speech recognition (ASR) transcripts, including evaluations using both encoder-based and decoder-based node embeddings, as well as monolingual and multilingual acoustic pre-trained models. All related code, data, and models are published online.
The semantic segmentation task in pathology plays an indispensable role in assisting physicians in determining the condition of tissue lesions. With the proposal of Segment Anything Model (SAM), more and more foundation models have seen rapid development in the field of image segmentation. Recently, SAM2 has garnered widespread attention in both natural image and medical image segmentation. Compared to SAM, it has significantly improved in terms of segmentation accuracy and generalization performance. We compared the foundational models based on SAM and found that their performance in semantic segmentation of pathological images was hardly satisfactory. In this paper, we propose Path-SAM2, which for the first time adapts the SAM2 model to cater to the task of pathological semantic segmentation. We integrate the largest pretrained vision encoder for histopathology (UNI) with the original SAM2 encoder, adding more pathology-based prior knowledge. Additionally, we introduce a learnable Kolmogorov-Arnold Networks (KAN) classification module to replace the manual prompt process. In three adenoma pathological datasets, Path-SAM2 has achieved state-of-the-art performance.This study demonstrates the great potential of adapting SAM2 to pathology image segmentation tasks. We plan to release the code and model weights for this paper at: https://github.com/simzhangbest/SAM2PATH
Cinematic audio source separation (CASS), as a standalone problem of extracting individual stems from their mixture, is a fairly new subtask of audio source separation. A typical setup of CASS is a three-stem problem, with the aim of separating the mixture into the dialogue (DX), music (MX), and effects (FX) stems. Given the creative nature of cinematic sound production, however, several edge cases exist; some sound sources do not fit neatly in any of these three stems, necessitating the use of additional auxiliary stems in production. One very common edge case is the singing voice in film audio, which may belong in either the DX or MX or neither, depending heavily on the cinematic context. In this work, we demonstrate a very straightforward extension of the dedicated-decoder Bandit and query-based single-decoder Banquet models to a four-stem problem, treating non-musical dialogue, instrumental music, singing voice, and effects as separate stems. Interestingly, the query-based Banquet model outperformed the dedicated-decoder Bandit model. We hypothesized that this is due to a better feature alignment at the bottleneck as enforced by the band-agnostic FiLM layer. Dataset and model implementation will be made available at https://github.com/kwatcharasupat/source-separation-landing.
This paper introduces {HINER}, a novel neural representation for compressing HSI and ensuring high-quality downstream tasks on compressed HSI. HINER fully exploits inter-spectral correlations by explicitly encoding of spectral wavelengths and achieves a compact representation of the input HSI sample through joint optimization with a learnable decoder. By additionally incorporating the Content Angle Mapper with the L1 loss, we can supervise the global and local information within each spectral band, thereby enhancing the overall reconstruction quality. For downstream classification on compressed HSI, we theoretically demonstrate the task accuracy is not only related to the classification loss but also to the reconstruction fidelity through a first-order expansion of the accuracy degradation, and accordingly adapt the reconstruction by introducing Adaptive Spectral Weighting. Owing to the monotonic mapping of HINER between wavelengths and spectral bands, we propose Implicit Spectral Interpolation for data augmentation by adding random variables to input wavelengths during classification model training. Experimental results on various HSI datasets demonstrate the superior compression performance of our HINER compared to the existing learned methods and also the traditional codecs. Our model is lightweight and computationally efficient, which maintains high accuracy for downstream classification task even on decoded HSIs at high compression ratios. Our materials will be released at https://github.com/Eric-qi/HINER.
The action anticipation task refers to predicting what action will happen based on observed videos, which requires the model to have a strong ability to summarize the present and then reason about the future. Experience and common sense suggest that there is a significant correlation between different actions, which provides valuable prior knowledge for the action anticipation task. However, previous methods have not effectively modeled this underlying statistical relationship. To address this issue, we propose a novel end-to-end video modeling architecture that utilizes attention mechanisms, named Anticipation via Recognition and Reasoning (ARR). ARR decomposes the action anticipation task into action recognition and sequence reasoning tasks, and effectively learns the statistical relationship between actions by next action prediction (NAP). In comparison to existing temporal aggregation strategies, ARR is able to extract more effective features from observable videos to make more reasonable predictions. In addition, to address the challenge of relationship modeling that requires extensive training data, we propose an innovative approach for the unsupervised pre-training of the decoder, which leverages the inherent temporal dynamics of video to enhance the reasoning capabilities of the network. Extensive experiments on the Epic-kitchen-100, EGTEA Gaze+, and 50salads datasets demonstrate the efficacy of the proposed methods. The code is available at https://github.com/linuxsino/ARR.
We present Lumina-mGPT, a family of multimodal autoregressive models capable of various vision and language tasks, particularly excelling in generating flexible photorealistic images from text descriptions. By initializing from multimodal Generative PreTraining (mGPT), we demonstrate that decoder-only Autoregressive (AR) model can achieve image generation performance comparable to modern diffusion models with high efficiency through Flexible Progressive Supervised Fine-tuning (FP-SFT). Equipped with our proposed Unambiguous image Representation (UniRep), Lumina-mGPT can flexibly generate high-quality images of varying aspect ratios. Building on the strong image generation capabilities, we further explore Ominiponent Supervised Fine-tuning (Omni-SFT), an initial attempt to elevate Lumina-mGPT into a unified multi-modal generalist. The resulting model demonstrates versatile multimodal capabilities, including visual generation tasks like text-to-image/multiview generation and controllable generation, visual recognition tasks like segmentation and depth estimation, and vision-language tasks like multi-turn visual question answering, showing the rosy potential of the technical direction. Codes and checkpoints are available at https://github.com/Alpha-VLLM/Lumina-mGPT.
This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP (Team 237) in the second Chinese Continuous Visual Speech Recognition Challenge (CNVSRC 2024), engaging in all four tracks, including the fixed and open tracks of Single-Speaker VSR Task and Multi-Speaker VSR Task. In terms of data processing, we leverage the lip motion extractor from the baseline1 to produce multiscale video data. Besides, various augmentation techniques are applied during training, encompassing speed perturbation, random rotation, horizontal flipping, and color transformation. The VSR model adopts an end-to-end architecture with joint CTC/attention loss, introducing Enhanced ResNet3D visual frontend, E-Branchformer encoder, and Bi-directional Transformer decoder. Our approach yields a 30.47% CER for the Single-Speaker Task and 34.30% CER for the Multi-Speaker Task, securing second place in the open track of the Single-Speaker Task and first place in the other three tracks.
Adapter based fine-tuning has been studied for improving the performance of SAM on downstream tasks. However, there is still a significant performance gap between fine-tuned SAMs and domain-specific models. To reduce the gap, we propose Two-Stream SAM (TS-SAM). On the one hand, inspired by the side network in Parameter-Efficient Fine-Tuning (PEFT), we designed a lightweight Convolutional Side Adapter (CSA), which integrates the powerful features from SAM into side network training for comprehensive feature fusion. On the other hand, in line with the characteristics of segmentation tasks, we designed Multi-scale Refinement Module (MRM) and Feature Fusion Decoder (FFD) to keep both the detailed and semantic features. Extensive experiments on ten public datasets from three tasks demonstrate that TS-SAM not only significantly outperforms the recently proposed SAM-Adapter and SSOM, but achieves competitive performance with the SOTA domain-specific models. Our code is available at: https://github.com/maoyangou147/TS-SAM.
Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the network, we identify two key obstacles in AVS models: 1) attention dissipation, corresponding to the over-concentrated attention weights by Softmax within restricted frames, and 2) inefficient, burdensome transformer decoder, caused by narrow focus patterns in early stages. In this paper, we introduce AVESFormer, the first real-time Audio-Visual Efficient Segmentation transformer that achieves fast, efficient and light-weight simultaneously. Our model leverages an efficient prompt query generator to correct the behaviour of cross-attention. Additionally, we propose ELF decoder to bring greater efficiency by facilitating convolutions suitable for local features to reduce computational burdens. Extensive experiments demonstrate that our AVESFormer significantly enhances model performance, achieving 79.9% on S4, 57.9% on MS3 and 31.2% on AVSS, outperforming previous state-of-the-art and achieving an excellent trade-off between performance and speed. Code can be found at https://github.com/MarkXCloud/AVESFormer.git.
Autonomous parking is a crucial task in the intelligent driving field. Traditional parking algorithms are usually implemented using rule-based schemes. However, these methods are less effective in complex parking scenarios due to the intricate design of the algorithms. In contrast, neural-network-based methods tend to be more intuitive and versatile than the rule-based methods. By collecting a large number of expert parking trajectory data and emulating human strategy via learning-based methods, the parking task can be effectively addressed. In this paper, we employ imitation learning to perform end-to-end planning from RGB images to path planning by imitating human driving trajectories. The proposed end-to-end approach utilizes a target query encoder to fuse images and target features, and a transformer-based decoder to autoregressively predict future waypoints. We conducted extensive experiments in real-world scenarios, and the results demonstrate that the proposed method achieved an average parking success rate of 87.8% across four different real-world garages. Real-vehicle experiments further validate the feasibility and effectiveness of the method proposed in this paper.
Radar-based contactless cardiac monitoring has become a popular research direction recently, but the fine-grained electrocardiogram (ECG) signal is still hard to reconstruct from millimeter-wave radar signal. The key obstacle is to decouple the cardiac activities in the electrical domain (i.e., ECG) from that in the mechanical domain (i.e., heartbeat), and most existing research only uses pure data-driven methods to map such domain transformation as a black box. Therefore, this work first proposes a signal model for domain transformation, and then a novel deep learning framework called radarODE is designed to fuse the temporal and morphological features extracted from radar signals and generate ECG. In addition, ordinary differential equations are embedded in radarODE as a decoder to provide morphological prior, helping the convergence of the model training and improving the robustness under body movements. After being validated on the dataset, the proposed radarODE achieves better performance compared with the benchmark in terms of missed detection rate, root mean square error, Pearson correlation coefficient with the improvement of 9%, 16% and 19%, respectively. The validation results imply that radarODE is capable of recovering ECG signals from radar signals with high fidelity and can be potentially implemented in real-life scenarios.
The many-to-many multilingual neural machine translation can be regarded as the process of integrating semantic features from the source sentences and linguistic features from the target sentences. To enhance zero-shot translation, models need to share knowledge across languages, which can be achieved through auxiliary tasks for learning a universal representation or cross-lingual mapping. To this end, we propose to exploit both semantic and linguistic features between multiple languages to enhance multilingual translation. On the encoder side, we introduce a disentangling learning task that aligns encoder representations by disentangling semantic and linguistic features, thus facilitating knowledge transfer while preserving complete information. On the decoder side, we leverage a linguistic encoder to integrate low-level linguistic features to assist in the target language generation. Experimental results on multilingual datasets demonstrate significant improvement in zero-shot translation compared to the baseline system, while maintaining performance in supervised translation. Further analysis validates the effectiveness of our method in leveraging both semantic and linguistic features. The code is available at https://github.com/ictnlp/SemLing-MNMT.
This paper describes IAI group's participation for automated check-worthiness estimation for claims, within the framework of the 2024 CheckThat! Lab "Task 1: Check-Worthiness Estimation". The task involves the automated detection of check-worthy claims in English, Dutch, and Arabic political debates and Twitter data. We utilized various pre-trained generative decoder and encoder transformer models, employing methods such as few-shot chain-of-thought reasoning, fine-tuning, data augmentation, and transfer learning from one language to another. Despite variable success in terms of performance, our models achieved notable placements on the organizer's leaderboard: ninth-best in English, third-best in Dutch, and the top placement in Arabic, utilizing multilingual datasets for enhancing the generalizability of check-worthiness detection. Despite a significant drop in performance on the unlabeled test dataset compared to the development test dataset, our findings contribute to the ongoing efforts in claim detection research, highlighting the challenges and potential of language-specific adaptations in claim verification systems.
We introduce a project that revives a piece of 15th-century Korean court music, Chihwapyeong and Chwipunghyeong, composed upon the poem Songs of the Dragon Flying to Heaven. One of the earliest examples of Jeongganbo, a Korean musical notation system, the remaining version only consists of a rudimentary melody. Our research team, commissioned by the National Gugak (Korean Traditional Music) Center, aimed to transform this old melody into a performable arrangement for a six-part ensemble. Using Jeongganbo data acquired through bespoke optical music recognition, we trained a BERT-like masked language model and an encoder-decoder transformer model. We also propose an encoding scheme that strictly follows the structure of Jeongganbo and denotes note durations as positions. The resulting machine-transformed version of Chihwapyeong and Chwipunghyeong were evaluated by experts and performed by the Court Music Orchestra of National Gugak Center. Our work demonstrates that generative models can successfully be applied to traditional music with limited training data if combined with careful design.
Representing symbolic music with compound tokens, where each token consists of several different sub-tokens representing a distinct musical feature or attribute, offers the advantage of reducing sequence length. While previous research has validated the efficacy of compound tokens in music sequence modeling, predicting all sub-tokens simultaneously can lead to suboptimal results as it may not fully capture the interdependencies between them. We introduce the Nested Music Transformer (NMT), an architecture tailored for decoding compound tokens autoregressively, similar to processing flattened tokens, but with low memory usage. The NMT consists of two transformers: the main decoder that models a sequence of compound tokens and the sub-decoder for modeling sub-tokens of each compound token. The experiment results showed that applying the NMT to compound tokens can enhance the performance in terms of better perplexity in processing various symbolic music datasets and discrete audio tokens from the MAESTRO dataset.