Large vision Transformers (ViTs) driven by self-supervised pre-training mechanisms achieved unprecedented progress. Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms. Knowledge distillation defines a paradigm to transfer representations from large (teacher) models to small (student) ones. However, the conventional single-stage distillation easily gets stuck on task-specific transfer, failing to retain the task-agnostic knowledge crucial for model generalization. In this study, we propose generic-to-specific distillation (G2SD), to tap the potential of small ViT models under the supervision of large models pre-trained by masked autoencoders. In generic distillation, decoder of the small model is encouraged to align feature predictions with hidden representations of the large model, so that task-agnostic knowledge can be transferred. In specific distillation, predictions of the small model are constrained to be consistent with those of the large model, to transfer task-specific features which guarantee task performance. With G2SD, the vanilla ViT-Small model respectively achieves 98.7%, 98.1% and 99.3% the performance of its teacher (ViT-Base) for image classification, object detection, and semantic segmentation, setting a solid baseline for two-stage vision distillation. Code will be available at https://github.com/pengzhiliang/G2SD.
Talking face generation has been extensively investigated owing to its wide applicability. The two primary frameworks used for talking face generation comprise a text-driven framework, which generates synchronized speech and talking faces from text, and a speech-driven framework, which generates talking faces from speech. To integrate these frameworks, this paper proposes a unified facial landmark generator (UniFLG). The proposed system exploits end-to-end text-to-speech not only for synthesizing speech but also for extracting a series of latent representations that are common to text and speech, and feeds it to a landmark decoder to generate facial landmarks. We demonstrate that our system achieves higher naturalness in both speech synthesis and facial landmark generation compared to the state-of-the-art text-driven method. We further demonstrate that our system can generate facial landmarks from speech of speakers without facial video data or even speech data.
This paper explores the novel deep learning Transformers architectures for high-frequency Bitcoin-USDT log-return forecasting and compares them to the traditional Long Short-Term Memory models. A hybrid Transformer model, called \textbf{HFformer}, is then introduced for time series forecasting which incorporates a Transformer encoder, linear decoder, spiking activations, and quantile loss function, and does not use position encoding. Furthermore, possible high-frequency trading strategies for use with the HFformer model are discussed, including trade sizing, trading signal aggregation, and minimal trading threshold. Ultimately, the performance of the HFformer and Long Short-Term Memory models are assessed and results indicate that the HFformer achieves a higher cumulative PnL than the LSTM when trading with multiple signals during backtesting.
We propose to employ a saliency-driven hierarchical neural image compression network for a machine-to-machine communication scenario following the compress-then-analyze paradigm. By that, different areas of the image are coded at different qualities depending on whether salient objects are located in the corresponding area. Areas without saliency are transmitted in latent spaces of lower spatial resolution in order to reduce the bitrate. The saliency information is explicitly derived from the detections of an object detection network. Furthermore, we propose to add saliency information to the training process in order to further specialize the different latent spaces. All in all, our hierarchical model with all proposed optimizations achieves 77.1 % bitrate savings over the latest video coding standard VVC on the Cityscapes dataset and with Mask R-CNN as analysis network at the decoder side. Thereby, it also outperforms traditional, non-hierarchical compression networks.
With the demanding need for deploying dialogue systems in new domains with less cost, zero-shot dialogue state tracking (DST), which tracks user's requirements in task-oriented dialogues without training on desired domains, draws attention increasingly. Although prior works have leveraged question-answering (QA) data to reduce the need for in-domain training in DST, they fail to explicitly model knowledge transfer and fusion for tracking dialogue states. To address this issue, we propose CoFunDST, which is trained on domain-agnostic QA datasets and directly uses candidate choices of slot-values as knowledge for zero-shot dialogue-state generation, based on a T5 pre-trained language model. Specifically, CoFunDST selects highly-relevant choices to the reference context and fuses them to initialize the decoder to constrain the model outputs. Our experimental results show that our proposed model achieves outperformed joint goal accuracy compared to existing zero-shot DST approaches in most domains on the MultiWOZ 2.1. Extensive analyses demonstrate the effectiveness of our proposed approach for improving zero-shot DST learning from QA.
Semantic communication is considered the future of mobile communication, which aims to transmit data beyond Shannon's theorem of communications by transmitting the semantic meaning of the data rather than the bit-by-bit reconstruction of the data at the receiver's end. The semantic communication paradigm aims to bridge the gap of limited bandwidth problems in modern high-volume multimedia application content transmission. Integrating AI technologies with the 6G communications networks paved the way to develop semantic communication-based end-to-end communication systems. In this study, we have implemented a semantic communication-based end-to-end image transmission system, and we discuss potential design considerations in developing semantic communication systems in conjunction with physical channel characteristics. A Pre-trained GAN network is used at the receiver as the transmission task to reconstruct the realistic image based on the Semantic segmented image at the receiver input. The semantic segmentation task at the transmitter (encoder) and the GAN network at the receiver (decoder) is trained on a common knowledge base, the COCO-Stuff dataset. The research shows that the resource gain in the form of bandwidth saving is immense when transmitting the semantic segmentation map through the physical channel instead of the ground truth image in contrast to conventional communication systems. Furthermore, the research studies the effect of physical channel distortions and quantization noise on semantic communication-based multimedia content transmission.
Image forgery localization aims to identify forged regions by capturing subtle traces from high-quality discriminative features. In this paper, we propose a Transformer-style network with two feature extraction branches for image forgery localization, and it is named as Two-Branch Transformer (TBFormer). Firstly, two feature extraction branches are elaborately designed, taking advantage of the discriminative stacked Transformer layers, for both RGB and noise domain features. Secondly, an Attention-aware Hierarchical-feature Fusion Module (AHFM) is proposed to effectively fuse hierarchical features from two different domains. Although the two feature extraction branches have the same architecture, their features have significant differences since they are extracted from different domains. We adopt position attention to embed them into a unified feature domain for hierarchical feature investigation. Finally, a Transformer decoder is constructed for feature reconstruction to generate the predicted mask. Extensive experiments on publicly available datasets demonstrate the effectiveness of the proposed model.
Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision. However, existing MAE-style methods can only learn from the data of a single modality, i.e., either images or point clouds, which neglect the implicit semantic and geometric correlation between 2D and 3D. In this paper, we explore how the 2D modality can benefit 3D masked autoencoding, and propose Joint-MAE, a 2D-3D joint MAE framework for self-supervised 3D point cloud pre-training. Joint-MAE randomly masks an input 3D point cloud and its projected 2D images, and then reconstructs the masked information of the two modalities. For better cross-modal interaction, we construct our JointMAE by two hierarchical 2D-3D embedding modules, a joint encoder, and a joint decoder with modal-shared and model-specific decoders. On top of this, we further introduce two cross-modal strategies to boost the 3D representation learning, which are local-aligned attention mechanisms for 2D-3D semantic cues, and a cross-reconstruction loss for 2D-3D geometric constraints. By our pre-training paradigm, Joint-MAE achieves superior performance on multiple downstream tasks, e.g., 92.4% accuracy for linear SVM on ModelNet40 and 86.07% accuracy on the hardest split of ScanObjectNN.
Trajectory prediction for autonomous driving must continuously reason the motion stochasticity of road agents and comply with scene constraints. Existing methods typically rely on one-stage trajectory prediction models, which condition future trajectories on observed trajectories combined with fused scene information. However, they often struggle with complex scene constraints, such as those encountered at intersections. To this end, we present a novel method, called LAformer. It uses a temporally dense lane-aware estimation module to select only the top highly potential lane segments in an HD map, which effectively and continuously aligns motion dynamics with scene information, reducing the representation requirements for the subsequent attention-based decoder by filtering out irrelevant lane segments. Additionally, unlike one-stage prediction models, LAformer utilizes predictions from the first stage as anchor trajectories and adds a second-stage motion refinement module to further explore temporal consistency across the complete time horizon. Extensive experiments on Argoverse 1 and nuScenes demonstrate that LAformer achieves excellent performance for multimodal trajectory prediction.
This paper introduces the Efficient Decoupled Masked Autoencoder (EDMAE), a novel self-supervised method for recognizing standard views in pediatric echocardiography. EDMAE introduces a new proxy task based on the encoder-decoder structure. The EDMAE encoder is composed of a teacher and a student encoder. The teacher encoder extracts the potential representation of the masked image blocks, while the student encoder extracts the potential representation of the visible image blocks. The loss is calculated between the feature maps output by the two encoders to ensure consistency in the latent representations they extract. EDMAE uses pure convolution operations instead of the ViT structure in the MAE encoder. This improves training efficiency and convergence speed. EDMAE is pre-trained on a large-scale private dataset of pediatric echocardiography using self-supervised learning, and then fine-tuned for standard view recognition. The proposed method achieves high classification accuracy in 27 standard views of pediatric echocardiography. To further verify the effectiveness of the proposed method, the authors perform another downstream task of cardiac ultrasound segmentation on the public dataset CAMUS. The experimental results demonstrate that the proposed method outperforms some popular supervised and recent self-supervised methods, and is more competitive on different downstream tasks.
Knee Osteoarthritis (KOA) is a common musculoskeletal condition that significantly affects mobility and quality of life, particularly in elderly populations. However, training deep learning models for early KOA classification is often hampered by the limited availability of annotated medical datasets, owing to the high costs and labour-intensive nature of data labelling. Traditional data augmentation techniques, while useful, rely on simple transformations and fail to introduce sufficient diversity into the dataset. To address these challenges, we propose the Key-Exchange Convolutional Auto-Encoder (KECAE) as an innovative Artificial Intelligence (AI)-based data augmentation strategy for early KOA classification. Our model employs a convolutional autoencoder with a novel key-exchange mechanism that generates synthetic images by selectively exchanging key pathological features between X-ray images, which not only diversifies the dataset but also ensures the clinical validity of the augmented data. A hybrid loss function is introduced to supervise feature learning and reconstruction, integrating multiple components, including reconstruction, supervision, and feature separation losses. Experimental results demonstrate that the KECAE-generated data significantly improve the performance of KOA classification models, with accuracy gains of up to 1.98% across various standard and state-of-the-art architectures. Furthermore, a clinical validation study involving expert radiologists confirms the anatomical plausibility and diagnostic realism of the synthetic outputs. These findings highlight the potential of KECAE as a robust tool for augmenting medical datasets in early KOA detection.
The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection criteria of these methods are varied for different domains, making them hard to generalize; 2) the selection performance of these approaches drops significantly when processing high-dimensional feature space coupled with small sample size. In light of these challenges, we pose the question: can selected feature subsets be more robust, accurate, and input dimensionality agnostic? In this paper, we reformulate the feature selection problem as a deep differentiable optimization task and propose a new research perspective: conceptualizing discrete feature subsetting as continuous embedding space optimization. We introduce a novel and principled framework that encompasses a sequential encoder, an accuracy evaluator, a sequential decoder, and a gradient ascent optimizer. This comprehensive framework includes four important steps: preparation of features-accuracy training data, deep feature subset embedding, gradient-optimized search, and feature subset reconstruction. Specifically, we utilize reinforcement feature selection learning to generate diverse and high-quality training data and enhance generalization. By optimizing reconstruction and accuracy losses, we embed feature selection knowledge into a continuous space using an encoder-evaluator-decoder model structure. We employ a gradient ascent search algorithm to find better embeddings in the learned embedding space. Furthermore, we reconstruct feature selection solutions using these embeddings and select the feature subset with the highest performance for downstream tasks as the optimal subset.
In todays era huge volume of information exists everywhere. Therefore, it is very crucial to evaluate that information and extract useful, and often summarized, information out of it so that it may be used for relevant purposes. This extraction can be achieved through a crucial technique of artificial intelligence, namely, machine learning. Indeed automatic text summarization has emerged as an important application of machine learning in text processing. In this paper, an english text summarizer has been built with GRU-based encoder and decoder. Bahdanau attention mechanism has been added to overcome the problem of handling long sequences in the input text. A news-summary dataset has been used to train the model. The output is observed to outperform competitive models in the literature. The generated summary can be used as a newspaper headline.
Visual Question Answering (VQA) becomes one of the most active research problems in the medical imaging domain. A well-known VQA challenge is the intrinsic diversity between the image and text modalities, and in the medical VQA task, there is another critical problem relying on the limited size of labelled image-question-answer data. In this study we propose an encoder-decoder framework that leverages the image-text joint representation learned from large-scaled medical image-caption data and adapted to the small-sized medical VQA task. The encoder embeds across the image-text dual modalities with self-attention mechanism and is independently pre-trained on the large-scaled medical image-caption dataset by multiple self-supervised learning tasks. Then the decoder is connected to the top of the encoder and fine-tuned using the small-sized medical VQA dataset. The experiment results present that our proposed method achieves better performance comparing with the baseline and SOTA methods.
Past work in natural language processing interpretability focused mainly on popular classification tasks while largely overlooking generation settings, partly due to a lack of dedicated tools. In this work, we introduce Inseq, a Python library to democratize access to interpretability analyses of sequence generation models. Inseq enables intuitive and optimized extraction of models' internal information and feature importance scores for popular decoder-only and encoder-decoder Transformers architectures. We showcase its potential by adopting it to highlight gender biases in machine translation models and locate factual knowledge inside GPT-2. Thanks to its extensible interface supporting cutting-edge techniques such as contrastive feature attribution, Inseq can drive future advances in explainable natural language generation, centralizing good practices and enabling fair and reproducible model evaluations.
Remotely captured images possess an immense scale and object appearance variability due to the complex scene. It becomes challenging to capture the underlying attributes in the global and local context for their segmentation. Existing networks struggle to capture the inherent features due to the cluttered background. To address these issues, we propose a remote sensing image segmentation network, RemoteNet, for semantic segmentation of remote sensing images. We capture the global and local features by leveraging the benefits of the transformer and convolution mechanisms. RemoteNet is an encoder-decoder design that uses multi-scale features. We construct an attention map module to generate channel-wise attention scores for fusing these features. We construct a global-local transformer block (GLTB) in the decoder network to support learning robust representations during a decoding phase. Further, we designed a feature refinement module to refine the fused output of the shallow stage encoder feature and the deepest GLTB feature of the decoder. Experimental findings on the two public datasets show the effectiveness of the proposed RemoteNet.
Distinguishing among different marine benthic habitat characteristics is of key importance in a wide set of seabed operations ranging from installations of oil rigs to laying networks of cables and monitoring the impact of humans on marine ecosystems. The Side-Scan Sonar (SSS) is a widely used imaging sensor in this regard. It produces high-resolution seafloor maps by logging the intensities of sound waves reflected back from the seafloor. In this work, we leverage these acoustic intensity maps to produce pixel-wise categorization of different seafloor types. We propose a novel architecture adapted from the Vision Transformer (ViT) in an encoder-decoder framework. Further, in doing so, the applicability of ViTs is evaluated on smaller datasets. To overcome the lack of CNN-like inductive biases, thereby making ViTs more conducive to applications in low data regimes, we propose a novel feature extraction module to replace the Multi-layer Perceptron (MLP) block within transformer layers and a novel module to extract multiscale patch embeddings. A lightweight decoder is also proposed to complement this design in order to further boost multiscale feature extraction. With the modified architecture, we achieve state-of-the-art results and also meet real-time computational requirements. We make our code available at ~\url{https://github.com/hayatrajani/s3seg-vit
Previous pitch-controllable text-to-speech (TTS) models rely on directly modeling fundamental frequency, leading to low variance in synthesized speech. To address this issue, we propose PITS, an end-to-end pitch-controllable TTS model that utilizes variational inference to model pitch. Based on VITS, PITS incorporates the Yingram encoder, the Yingram decoder, and adversarial training of pitch-shifted synthesis to achieve pitch-controllability. Experiments demonstrate that PITS generates high-quality speech that is indistinguishable from ground truth speech and has high pitch-controllability without quality degradation. Code, audio samples, and demo are available at https://github.com/anonymous-pits/pits.
Fine-grained temporal action segmentation in long, untrimmed RGB videos is a key topic in visual human- machine interaction. Recent temporal convolution based approaches either use encoder-decoder(ED) architecture or dilations with doubling factor in consecutive convolution layers to segment actions in videos. However ED networks operate on low temporal resolution and the dilations in suc- cessive layers cause gridding artifacts problem. We propose depthwise separable temporal convolution network (DS- TCN) that operates on full temporal resolution and with re- duced gridding effects. The basic component of DS-TCN is residual depthwise dilated block (RDDB). We explore the trade-off between large kernels and small dilation rates us- ing RDDB. We show that our DS-TCN is capable of captur- ing long-term dependencies as well as local temporal cues efficiently. Our evaluation on three benchmark datasets, GTEA, 50Salads, and Breakfast demonstrates that DS-TCN outperforms the existing ED-TCN and dilation based TCN baselines even with comparatively fewer parameters.
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e.g., emotion status) and cognitive factors (e.g., cause of the emotion). Besides concerning emotion status in early work, the latest approaches study emotion causes in empathetic dialogue. These approaches focus on understanding and duplicating emotion causes in the context to show empathy for the speaker. However, instead of only repeating the contextual causes, the real empathic response often demonstrate a logical and emotion-centered transition from the causes in the context to those in the responses. In this work, we propose an emotion cause transition graph to explicitly model the natural transition of emotion causes between two adjacent turns in empathetic dialogue. With this graph, the concept words of the emotion causes in the next turn can be predicted and used by a specifically designed concept-aware decoder to generate the empathic response. Automatic and human experimental results on the benchmark dataset demonstrate that our method produces more empathetic, coherent, informative, and specific responses than existing models.