As climate change intensifies, the global imperative to shift towards sustainable energy sources becomes more pronounced. Photovoltaic (PV) energy is a favored choice due to its reliability and ease of installation. Accurate mapping of PV installations is crucial for understanding their adoption and informing energy policy. To meet this need, we introduce the SolarFormer, designed to segment solar panels from aerial imagery, offering insights into their location and size. However, solar panel identification in Computer Vision is intricate due to various factors like weather conditions, roof conditions, and Ground Sampling Distance (GSD) variations. To tackle these complexities, we present the SolarFormer, featuring a multi-scale Transformer encoder and a masked-attention Transformer decoder. Our model leverages low-level features and incorporates an instance query mechanism to enhance the localization of solar PV installations. We rigorously evaluated our SolarFormer using diverse datasets, including GGE (France), IGN (France), and USGS (California, USA), across different GSDs. Our extensive experiments consistently demonstrate that our model either matches or surpasses state-of-the-art models, promising enhanced solar panel segmentation for global sustainable energy initiatives.
One of the common and promising deep learning approaches used for medical image segmentation is transformers, as they can capture long-range dependencies among the pixels by utilizing self-attention. Despite being successful in medical image segmentation, transformers face limitations in capturing local contexts of pixels in multimodal dimensions. We propose a Medical Image Segmentation Transformer (MIST) incorporating a novel Convolutional Attention Mixing (CAM) decoder to address this issue. MIST has two parts: a pre-trained multi-axis vision transformer (MaxViT) is used as an encoder, and the encoded feature representation is passed through the CAM decoder for segmenting the images. In the CAM decoder, an attention-mixer combining multi-head self-attention, spatial attention, and squeeze and excitation attention modules is introduced to capture long-range dependencies in all spatial dimensions. Moreover, to enhance spatial information gain, deep and shallow convolutions are used for feature extraction and receptive field expansion, respectively. The integration of low-level and high-level features from different network stages is enabled by skip connections, allowing MIST to suppress unnecessary information. The experiments show that our MIST transformer with CAM decoder outperforms the state-of-the-art models specifically designed for medical image segmentation on the ACDC and Synapse datasets. Our results also demonstrate that adding the CAM decoder with a hierarchical transformer improves segmentation performance significantly. Our model with data and code is publicly available on GitHub.
In medical image segmentation, domain generalization poses a significant challenge due to domain shifts caused by variations in data acquisition devices and other factors. These shifts are particularly pronounced in the most common scenario, which involves only single-source domain data due to privacy concerns. To address this, we draw inspiration from the self-supervised learning paradigm that effectively discourages overfitting to the source domain. We propose the Denoising Y-Net (DeY-Net), a novel approach incorporating an auxiliary denoising decoder into the basic U-Net architecture. The auxiliary decoder aims to perform denoising training, augmenting the domain-invariant representation that facilitates domain generalization. Furthermore, this paradigm provides the potential to utilize unlabeled data. Building upon denoising training, we propose Denoising Test Time Adaptation (DeTTA) that further: (i) adapts the model to the target domain in a sample-wise manner, and (ii) adapts to the noise-corrupted input. Extensive experiments conducted on widely-adopted liver segmentation benchmarks demonstrate significant domain generalization improvements over our baseline and state-of-the-art results compared to other methods. Code is available at https://github.com/WenRuxue/DeTTA.
Among applications of deep learning (DL) involving low cost sensors, remote image classification involves a physical channel that separates edge sensors and cloud classifiers. Traditional DL models must be divided between an encoder for the sensor and the decoder + classifier at the edge server. An important challenge is to effectively train such distributed models when the connecting channels have limited rate/capacity. Our goal is to optimize DL models such that the encoder latent requires low channel bandwidth while still delivers feature information for high classification accuracy. This work proposes a three-step joint learning strategy to guide encoders to extract features that are compact, discriminative, and amenable to common augmentations/transformations. We optimize latent dimension through an initial screening phase before end-to-end (E2E) training. To obtain an adjustable bit rate via a single pre-deployed encoder, we apply entropy-based quantization and/or manual truncation on the latent representations. Tests show that our proposed method achieves accuracy improvement of up to 1.5% on CIFAR-10 and 3% on CIFAR-100 over conventional E2E cross-entropy training.
Multi-horizon time series forecasting, crucial across diverse domains, demands high accuracy and speed. While AutoRegressive (AR) models excel in short-term predictions, they suffer speed and error issues as the horizon extends. Non-AutoRegressive (NAR) models suit long-term predictions but struggle with interdependence, yielding unrealistic results. We introduce AMLNet, an innovative NAR model that achieves realistic forecasts through an online Knowledge Distillation (KD) approach. AMLNet harnesses the strengths of both AR and NAR models by training a deep AR decoder and a deep NAR decoder in a collaborative manner, serving as ensemble teachers that impart knowledge to a shallower NAR decoder. This knowledge transfer is facilitated through two key mechanisms: 1) outcome-driven KD, which dynamically weights the contribution of KD losses from the teacher models, enabling the shallow NAR decoder to incorporate the ensemble's diversity; and 2) hint-driven KD, which employs adversarial training to extract valuable insights from the model's hidden states for distillation. Extensive experimentation showcases AMLNet's superiority over conventional AR and NAR models, thereby presenting a promising avenue for multi-horizon time series forecasting that enhances accuracy and expedites computation.
Vision-language pretraining has been shown to produce high-quality visual encoders which transfer efficiently to downstream computer vision tasks. Contrastive learning approaches have increasingly been adopted for medical vision language pretraining (MVLP), yet recent developments in generative AI offer new modeling alternatives. This paper introduces RadTex, a CNN-encoder transformer-decoder architecture optimized for radiology. We explore bidirectional captioning as an alternative MVLP strategy and demonstrate that RadTex's captioning pretraining is competitive with established contrastive methods, achieving a CheXpert macro-AUC of 89.4%. Additionally, RadTex's lightweight text decoder not only generates clinically relevant radiology reports (macro-F1 score of 0.349), but also provides targeted, interactive responses, highlighting the utility of bidirectional captioning in advancing medical image analysis.
Incorporating human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture) and how to efficiently incorporate always-limited human perceptual data into training strategies of models. In this paper, we introduce MENTOR (huMan pErceptioN-guided preTraining fOr increased geneRalization), which addresses this question through two unique rounds of training the CNNs tasked with open-set anomaly detection. First, we train an autoencoder to learn human saliency maps given an input image, without class labels. The autoencoder is thus tasked with discovering domain-specific salient features which mimic human perception. Second, we remove the decoder part, add a classification layer on top of the encoder, and fine-tune this new model conventionally. We show that MENTOR's benefits are twofold: (a) significant accuracy boost in anomaly detection tasks (in this paper demonstrated for detection of unknown iris presentation attacks, synthetically-generated faces, and anomalies in chest X-ray images), compared to models utilizing conventional transfer learning (e.g., sourcing the weights from ImageNet-pretrained models) as well as to models trained with the state-of-the-art approach incorporating human perception guidance into loss functions, and (b) an increase in the efficiency of model training, requiring fewer epochs to converge compared to state-of-the-art training methods.
Visual object tracking is a fundamental component of transportation systems, especially for intelligent driving. Despite achieving state-of-the-art performance in visual tracking, recent single-branch trackers tend to overlook the weak prior assumptions associated with the Vision Transformer (ViT) encoder and inference pipeline in visual tracking. Moreover, the effectiveness of discriminative trackers remains constrained due to the adoption of the dual-branch pipeline. To tackle the inferior effectiveness of vanilla ViT, we propose an Adaptive ViT Model Prediction tracker (AViTMP) to design a customised tracking method. This method bridges the single-branch network with discriminative models for the first time. Specifically, in the proposed encoder AViT encoder, we introduce a tracking-tailored Adaptor module for vanilla ViT and a joint target state embedding to enrich the target-prior embedding paradigm. Then, we combine the AViT encoder with a discriminative transformer-specific model predictor to predict the accurate location. Furthermore, to mitigate the limitations of conventional inference practice, we present a novel inference pipeline called CycleTrack, which bolsters the tracking robustness in the presence of distractors via bidirectional cycle tracking verification. In the experiments, we evaluated AViTMP on eight tracking benchmarks for a comprehensive assessment, including LaSOT, LaSOTExtSub, AVisT, etc. The experimental results unequivocally establish that, under fair comparison, AViTMP achieves state-of-the-art performance, especially in terms of long-term tracking and robustness. The source code will be released at https://github.com/Tchuanm/AViTMP.
Named Entity Recognition (NER) remains challenging due to the complex entities, like nested, overlapping, and discontinuous entities. Existing approaches, such as sequence-to-sequence (Seq2Seq) generation and span-based classification, have shown impressive performance on various NER subtasks, but they are difficult to scale to datasets with longer input text because of either exposure bias issue or inefficient computation. In this paper, we propose a novel Sequence-to-Forest generation paradigm, S2F-NER, which can directly extract entities in sentence via a Forest decoder that decode multiple entities in parallel rather than sequentially. Specifically, our model generate each path of each tree in forest autoregressively, where the maximum depth of each tree is three (which is the shortest feasible length for complex NER and is far smaller than the decoding length of Seq2Seq). Based on this novel paradigm, our model can elegantly mitigates the exposure bias problem and keep the simplicity of Seq2Seq. Experimental results show that our model significantly outperforms the baselines on three discontinuous NER datasets and on two nested NER datasets, especially for discontinuous entity recognition.
Text-to-SQL aims to generate an executable SQL program given the user utterance and the corresponding database schema. To ensure the well-formedness of output SQLs, one prominent approach adopts a grammar-based recurrent decoder to produce the equivalent SQL abstract syntax tree (AST). However, previous methods mainly utilize an RNN-series decoder, which 1) is time-consuming and inefficient and 2) introduces very few structure priors. In this work, we propose an AST structure-aware Transformer decoder (ASTormer) to replace traditional RNN cells. The structural knowledge, such as node types and positions in the tree, is seamlessly incorporated into the decoder via both absolute and relative position embeddings. Besides, the proposed framework is compatible with different traversing orders even considering adaptive node selection. Extensive experiments on five text-to-SQL benchmarks demonstrate the effectiveness and efficiency of our structured decoder compared to competitive baselines.
In recent years, the task of text-to-SQL translation, which converts natural language questions into executable SQL queries, has gained significant attention for its potential to democratize data access. Despite its promise, challenges such as adapting to unseen databases and aligning natural language with SQL syntax have hindered widespread adoption. To overcome these issues, we introduce SQLformer, a novel Transformer architecture specifically crafted to perform text-to-SQL translation tasks. Our model predicts SQL queries as abstract syntax trees (ASTs) in an autoregressive way, incorporating structural inductive bias in the encoder and decoder layers. This bias, guided by database table and column selection, aids the decoder in generating SQL query ASTs represented as graphs in a Breadth-First Search canonical order. Our experiments demonstrate that SQLformer achieves state-of-the-art performance across six prominent text-to-SQL benchmarks.
Previous research in $2D$ object detection focuses on various tasks, including detecting objects in generic and camouflaged images. These works are regarded as passive works for object detection as they take the input image as is. However, convergence to global minima is not guaranteed to be optimal in neural networks; therefore, we argue that the trained weights in the object detector are not optimal. To rectify this problem, we propose a wrapper based on proactive schemes, PrObeD, which enhances the performance of these object detectors by learning a signal. PrObeD consists of an encoder-decoder architecture, where the encoder network generates an image-dependent signal termed templates to encrypt the input images, and the decoder recovers this template from the encrypted images. We propose that learning the optimum template results in an object detector with an improved detection performance. The template acts as a mask to the input images to highlight semantics useful for the object detector. Finetuning the object detector with these encrypted images enhances the detection performance for both generic and camouflaged. Our experiments on MS-COCO, CAMO, COD$10$K, and NC$4$K datasets show improvement over different detectors after applying PrObeD. Our models/codes are available at https://github.com/vishal3477/Proactive-Object-Detection.
Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a decoder, which encourages the network to capture and learn structural information about objects and scenes. The intermediate feature representations obtained from MIM are suitable for fine-tuning on downstream tasks. In this paper, we propose an Image Modeling framework based on random orthogonal projection instead of binary masking as in MIM. Our proposed Random Orthogonal Projection Image Modeling (ROPIM) reduces spatially-wise token information under guaranteed bound on the noise variance and can be considered as masking entire spatial image area under locally varying masking degrees. Since ROPIM uses a random subspace for the projection that realizes the masking step, the readily available complement of the subspace can be used during unmasking to promote recovery of removed information. In this paper, we show that using random orthogonal projection leads to superior performance compared to crop-based masking. We demonstrate state-of-the-art results on several popular benchmarks.
In this paper, we present a Diffusion GAN based approach (Prosodic Diff-TTS) to generate the corresponding high-fidelity speech based on the style description and content text as an input to generate speech samples within only 4 denoising steps. It leverages the novel conditional prosodic layer normalization to incorporate the style embeddings into the multi head attention based phoneme encoder and mel spectrogram decoder based generator architecture to generate the speech. The style embedding is generated by fine tuning the pretrained BERT model on auxiliary tasks such as pitch, speaking speed, emotion,gender classifications. We demonstrate the efficacy of our proposed architecture on multi-speaker LibriTTS and PromptSpeech datasets, using multiple quantitative metrics that measure generated accuracy and MOS.
The rapid advancement of large language models (LLMs) has sparked interest in data synthesis techniques, aiming to generate diverse and high-quality synthetic datasets. However, these synthetic datasets often suffer from a lack of diversity and added noise. In this paper, we present TarGEN, a multi-step prompting strategy for generating high-quality synthetic datasets utilizing a LLM. An advantage of TarGEN is its seedless nature; it does not require specific task instances, broadening its applicability beyond task replication. We augment TarGEN with a method known as self-correction empowering LLMs to rectify inaccurately labeled instances during dataset creation, ensuring reliable labels. To assess our technique's effectiveness, we emulate 8 tasks from the SuperGLUE benchmark and finetune various language models, including encoder-only, encoder-decoder, and decoder-only models on both synthetic and original training sets. Evaluation on the original test set reveals that models trained on datasets generated by TarGEN perform approximately 1-2% points better than those trained on original datasets (82.84% via syn. vs. 81.12% on og. using Flan-T5). When incorporating instruction tuning, the performance increases to 84.54% on synthetic data vs. 81.49% on original data by Flan-T5. A comprehensive analysis of the synthetic dataset compared to the original dataset reveals that the synthetic dataset demonstrates similar or higher levels of dataset complexity and diversity. Furthermore, the synthetic dataset displays a bias level that aligns closely with the original dataset. Finally, when pre-finetuned on our synthetic SuperGLUE dataset, T5-3B yields impressive results on the OpenLLM leaderboard, surpassing the model trained on the Self-Instruct dataset by 4.14% points. We hope that TarGEN can be helpful for quality data generation and reducing the human efforts to create complex benchmarks.
In recent years, continuous latent space (CLS) and discrete latent space (DLS) deep learning models have been proposed for medical image analysis for improved performance. However, these models encounter distinct challenges. CLS models capture intricate details but often lack interpretability in terms of structural representation and robustness due to their emphasis on low-level features. Conversely, DLS models offer interpretability, robustness, and the ability to capture coarse-grained information thanks to their structured latent space. However, DLS models have limited efficacy in capturing fine-grained details. To address the limitations of both DLS and CLS models, we propose SynergyNet, a novel bottleneck architecture designed to enhance existing encoder-decoder segmentation frameworks. SynergyNet seamlessly integrates discrete and continuous representations to harness complementary information and successfully preserves both fine and coarse-grained details in the learned representations. Our extensive experiment on multi-organ segmentation and cardiac datasets demonstrates that SynergyNet outperforms other state of the art methods, including TransUNet: dice scores improving by 2.16%, and Hausdorff scores improving by 11.13%, respectively. When evaluating skin lesion and brain tumor segmentation datasets, we observe a remarkable improvement of 1.71% in Intersection-over Union scores for skin lesion segmentation and of 8.58% for brain tumor segmentation. Our innovative approach paves the way for enhancing the overall performance and capabilities of deep learning models in the critical domain of medical image analysis.
With the significant advances in AI-generated content (AIGC) and the proliferation of mobile devices, providing high-quality AIGC services via wireless networks is becoming the future direction. However, the primary challenges of AIGC services provisioning in wireless networks lie in unstable channels, limited bandwidth resources, and unevenly distributed computational resources. To this end, this paper proposes a semantic communication (SemCom)-empowered AIGC (SemAIGC) generation and transmission framework, where only semantic information of the content rather than all the binary bits should be generated and transmitted by using SemCom. Specifically, SemAIGC integrates diffusion models within the semantic encoder and decoder to design a workload-adjustable transceiver thereby allowing adjustment of computational resource utilization in edge and local. In addition, a Resource-aware wOrklOad Trade-off (ROOT) scheme is devised to intelligently make workload adaptation decisions for the transceiver, thus efficiently generating, transmitting, and fine-tuning content as per dynamic wireless channel conditions and service requirements. Simulations verify the superiority of our proposed SemAIGC framework in terms of latency and content quality compared to conventional approaches.
In this paper, we discuss one aspect of the latest MPEG standard edition on energy-efficient media consumption, also known as Green Metadata (ISO/IEC 232001-11), which is the interactive signaling for remote decoder-power reduction for peer-to-peer video conferencing. In this scenario, the receiver of a video, e.g., a battery-driven portable device, can send a dedicated request to the sender which asks for a video bitstream representation that is less complex to decode and process. Consequently, the receiver saves energy and extends operating times. We provide an overview on latest studies from the literature dealing with energy-saving aspects, which motivate the extension of the legacy Green Metadata standard. Furthermore, we explain the newly introduced syntax elements and verify their effectiveness by performing dedicated experiments. We show that the integration of these syntax elements can lead to dynamic energy savings of up to 90% for software video decoding and 80% for hardware video decoding, respectively.
Auscultation for neonates is a simple and non-invasive method of providing diagnosis for cardiovascular and respiratory disease. Such diagnosis often requires high-quality heart and lung sounds to be captured during auscultation. However, in most cases, obtaining such high-quality sounds is non-trivial due to the chest sounds containing a mixture of heart, lung, and noise sounds. As such, additional preprocessing is needed to separate the chest sounds into heart and lung sounds. This paper proposes a novel deep-learning approach to separate such chest sounds into heart and lung sounds. Inspired by the Conv-TasNet model, the proposed model has an encoder, decoder, and mask generator. The encoder consists of a 1D convolution model and the decoder consists of a transposed 1D convolution. The mask generator is constructed using stacked 1D convolutions and transformers. The proposed model outperforms previous methods in terms of objective distortion measures by 2.01 dB to 5.06 dB in the artificial dataset, as well as computation time, with at least a 17-time improvement. Therefore, our proposed model could be a suitable preprocessing step for any phonocardiogram-based health monitoring system.
Decoder-only models, such as GPT, have demonstrated superior performance in many areas compared to traditional encoder-decoder structure transformer models. Over the years, end-to-end models based on the traditional transformer structure, like MOTR, have achieved remarkable performance in multi-object tracking. However, the significant computational resource consumption of these models leads to less friendly inference speeds and training times. To address these issues, this paper attempts to construct a lightweight Decoder-only model: DecoderTracker for end-to-end multi-object tracking. Specifically, drawing on some real-time detection models, we have developed an image feature extraction network which can efficiently extract features from images to replace the encoder structure. In addition to minor innovations in the network, we analyze the potential reasons for the slow training of MOTR-like models and propose an effective training strategy to mitigate the issue of prolonged training times. On the DanceTrack dataset, without any bells and whistles, DecoderTracker's tracking performance slightly surpasses that of MOTR, with approximately twice the inference speed. Furthermore, DecoderTracker requires significantly less training time compared to MOTR.