Semantic segmentation has witnessed remarkable advancements with the adaptation of the Transformer architecture. Parallel to the strides made by the Transformer, CNN-based U-Net has seen significant progress, especially in high-resolution medical imaging and remote sensing. This dual success inspired us to merge the strengths of both, leading to the inception of a U-Net-based vision transformer decoder tailored for efficient contextual encoding. Here, we propose a novel transformer decoder, U-MixFormer, built upon the U-Net structure, designed for efficient semantic segmentation. Our approach distinguishes itself from the previous transformer methods by leveraging lateral connections between the encoder and decoder stages as feature queries for the attention modules, apart from the traditional reliance on skip connections. Moreover, we innovatively mix hierarchical feature maps from various encoder and decoder stages to form a unified representation for keys and values, giving rise to our unique mix-attention module. Our approach demonstrates state-of-the-art performance across various configurations. Extensive experiments show that U-MixFormer outperforms SegFormer, FeedFormer, and SegNeXt by a large margin. For example, U-MixFormer-B0 surpasses SegFormer-B0 and FeedFormer-B0 with 3.8% and 2.0% higher mIoU and 27.3% and 21.8% less computation and outperforms SegNext with 3.3% higher mIoU with MSCAN-T encoder on ADE20K. Code available at https://github.com/julian-klitzing/u-mixformer.
Modern Large Vision-Language Models (LVLMs) enjoy the same vision vocabulary -- CLIP, which can cover most common vision tasks. However, for some special vision task that needs dense and fine-grained vision perception, e.g., document-level OCR or chart understanding, especially in non-English scenarios, the CLIP-style vocabulary may encounter low efficiency in tokenizing the vision knowledge and even suffer out-of-vocabulary problem. Accordingly, we propose Vary, an efficient and effective method to scale up the vision vocabulary of LVLMs. The procedures of Vary are naturally divided into two folds: the generation and integration of a new vision vocabulary. In the first phase, we devise a vocabulary network along with a tiny decoder-only transformer to produce the desired vocabulary via autoregression. In the next, we scale up the vanilla vision vocabulary by merging the new one with the original one (CLIP), enabling the LVLMs can quickly garner new features. Compared to the popular BLIP-2, MiniGPT4, and LLaVA, Vary can maintain its vanilla capabilities while enjoying more excellent fine-grained perception and understanding ability. Specifically, Vary is competent in new document parsing features (OCR or markdown conversion) while achieving 78.2% ANLS in DocVQA and 36.2% in MMVet. Our code will be publicly available on the homepage.
We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles to achieving this goal. In this paper, we present DiffMatte, a solution designed to effectively overcome these challenges. First, DiffMatte decouples the decoder from the intricately coupled matting network design, involving only one lightweight decoder in the iterations of the diffusion process. With such a strategy, DiffMatte mitigates the growth of computational overhead as the number of samples increases. Second, we employ a self-aligned training strategy with uniform time intervals, ensuring a consistent noise sampling between training and inference across the entire time domain. Our DiffMatte is designed with flexibility in mind and can seamlessly integrate into various modern matting architectures. Extensive experimental results demonstrate that DiffMatte not only reaches the state-of-the-art level on the Composition-1k test set, surpassing the best methods in the past by 5% and 15% in the SAD metric and MSE metric respectively, but also show stronger generalization ability in other benchmarks.
In this paper, we propose a novel framework named DRL-CPG to learn disentangled latent representation for controllable person image generation, which can produce realistic person images with desired poses and human attributes (e.g., pose, head, upper clothes, and pants) provided by various source persons. Unlike the existing works leveraging the semantic masks to obtain the representation of each component, we propose to generate disentangled latent code via a novel attribute encoder with transformers trained in a manner of curriculum learning from a relatively easy step to a gradually hard one. A random component mask-agnostic strategy is introduced to randomly remove component masks from the person segmentation masks, which aims at increasing the difficulty of training and promoting the transformer encoder to recognize the underlying boundaries between each component. This enables the model to transfer both the shape and texture of the components. Furthermore, we propose a novel attribute decoder network to integrate multi-level attributes (e.g., the structure feature and the attribute representation) with well-designed Dual Adaptive Denormalization (DAD) residual blocks. Extensive experiments strongly demonstrate that the proposed approach is able to transfer both the texture and shape of different human parts and yield realistic results. To our knowledge, we are the first to learn disentangled latent representations with transformers for person image generation.
In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from multiple viewpoints, there is a higher degree of difficulty due to the difference in background, occlusion, and visibility of the captured action from different camera angles. To tackle the various problems introduced in multi-view action recognition, we propose a novel configuration of learnable transformer decoder queries, in conjunction with two supervised contrastive losses, to enforce the learning of action features that are robust to shifts in viewpoints. Our disentangled feature learning occurs in two stages: the transformer decoder uses separate queries to separately learn action and view information, which are then further disentangled using our two contrastive losses. We show that our model and method of training significantly outperforms all other uni-modal models on four multi-view action recognition datasets: NTU RGB+D, NTU RGB+D 120, PKU-MMD, and N-UCLA. Compared to previous RGB works, we see maximal improvements of 1.5\%, 4.8\%, 2.2\%, and 4.8\% on each dataset, respectively.
This paper presents EdgeSAM, an accelerated variant of the Segment Anything Model (SAM), optimized for efficient execution on edge devices with minimal compromise in performance. Our approach involves distilling the original ViT-based SAM image encoder into a purely CNN-based architecture, better suited for edge devices. We carefully benchmark various distillation strategies and demonstrate that taskagnostic encoder distillation fails to capture the full knowledge embodied in SAM. To overcome this bottleneck, we include both the prompt encoder and mask decoder in the distillation process, with box and point prompts in the loop, so that the distilled model can accurately capture the intricate dynamics between user input and mask generation. To mitigate dataset bias issues stemming from point prompt distillation, we incorporate a lightweight module within the encoder. As a result, EdgeSAM achieves a 37-fold speed increase compared to the original SAM, and it also outperforms MobileSAM/EfficientSAM, being over 7 times as fast when deployed on edge devices while enhancing the mIoUs on COCO and LVIS by 2.3/1.5 and 3.1/1.6, respectively. It is also the first SAM variant that can run at over 30 FPS on an iPhone 14. Code and demo are available at https://www.mmlab-ntu.com/project/edgesam.
Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.
With the development of Internet of Things (IoT) systems, precise long-term forecasting method is requisite for decision makers to evaluate current statuses and formulate future policies. Currently, Transformer and MLP are two paradigms for deep time-series forecasting and the former one is more prevailing in virtue of its exquisite attention mechanism and encoder-decoder architecture. However, data scientists seem to be more willing to dive into the research of encoder, leaving decoder unconcerned. Some researchers even adopt linear projections in lieu of the decoder to reduce the complexity. We argue that both extracting the features of input sequence and seeking the relations of input and prediction sequence, which are respective functions of encoder and decoder, are of paramount significance. Motivated from the success of FPN in CV field, we propose FPPformer to utilize bottom-up and top-down architectures respectively in encoder and decoder to build the full and rational hierarchy. The cutting-edge patch-wise attention is exploited and further developed with the combination, whose format is also different in encoder and decoder, of revamped element-wise attention in this work. Extensive experiments with six state-of-the-art baselines on twelve benchmarks verify the promising performances of FPPformer and the importance of elaborately devising decoder in time-series forecasting Transformer. The source code is released in https://github.com/OrigamiSL/FPPformer.
With the rise of social media, the spread of fake news has become a significant concern, potentially misleading public perceptions and impacting social stability. Although deep learning methods like CNNs, RNNs, and Transformer-based models like BERT have enhanced fake news detection, they primarily focus on content, overlooking social context during news propagation. Graph-based techniques have incorporated this social context but are limited by the need for large labeled datasets. Addressing these challenges, this paper introduces GAMC, an unsupervised fake news detection technique using the Graph Autoencoder with Masking and Contrastive learning. By leveraging both the context and content of news propagation as self-supervised signals, our method negates the requirement for labeled datasets. We augment the original news propagation graph, encode these with a graph encoder, and employ a graph decoder for reconstruction. A unique composite loss function, including reconstruction error and contrast loss, is designed. The method's contributions are: introducing self-supervised learning to fake news detection, proposing a graph autoencoder integrating two distinct losses, and validating our approach's efficacy through real-world dataset experiments.
In recent years, transformer-based models have dominated panoptic segmentation, thanks to their strong modeling capabilities and their unified representation for both semantic and instance classes as global binary masks. In this paper, we revisit pure convolution model and propose a novel panoptic architecture named MaskConver. MaskConver proposes to fully unify things and stuff representation by predicting their centers. To that extent, it creates a lightweight class embedding module that can break the ties when multiple centers co-exist in the same location. Furthermore, our study shows that the decoder design is critical in ensuring that the model has sufficient context for accurate detection and segmentation. We introduce a powerful ConvNeXt-UNet decoder that closes the performance gap between convolution- and transformerbased models. With ResNet50 backbone, our MaskConver achieves 53.6% PQ on the COCO panoptic val set, outperforming the modern convolution-based model, Panoptic FCN, by 9.3% as well as transformer-based models such as Mask2Former (+1.7% PQ) and kMaX-DeepLab (+0.6% PQ). Additionally, MaskConver with a MobileNet backbone reaches 37.2% PQ, improving over Panoptic-DeepLab by +6.4% under the same FLOPs/latency constraints. A further optimized version of MaskConver achieves 29.7% PQ, while running in real-time on mobile devices. The code and model weights will be publicly available
The advent of deep learning (DL)-based models has significantly advanced Channel State Information (CSI) feedback mechanisms in wireless communication systems. However, traditional approaches often suffer from high communication overhead and potential privacy risks due to the centralized nature of CSI data processing. To address these challenges, we design a CSI feedback training framework called Dig-CSI, in which the dataset for training the CSI feedback model is produced by the distributed generators uploaded by each user equipment (UE), but not through local data upload. Each UE trains an autoencoder, where the decoder is considered as the distributed generator, with local data to gain reconstruction accuracy and the ability to generate. Experimental results show that Dig-CSI can train a global CSI feedback model with comparable performance to the model trained with classical centralized learning with a much lighter communication overhead.
The computer-aided diagnosis (CAD) of skin diseases relies heavily on automated skin lesion segmentation, albeit presenting considerable challenges due to lesion diversity in shape, size, color, and texture, as well as potential blurry boundaries with surrounding tissues. Traditional Convolutional Neural Networks (CNN) typically underperform in this domain, given their inherent constraints in global context information capture. In the present study, we present a new U-shaped network, Dual-Encoder U-Net (DEU-Net), which is based on an encoder-decoder architecture. DEU-Net integrates a dual-encoder branch comprising a convolutional encoder and a transformer encoder, thereby facilitating the concurrent extraction of local features and global contextual information. Additionally, in order to enhance the performance of DEU-Net, we employ an integrated test-time augmentation technique. To ascertain the efficiency and superiority of our proposed methodology, we performed comprehensive experiments across four widely accessible skin lesion datasets, namely ISIC 2016, ISIC 2017, ISIC 2018, and PH2. The Dice coefficients achieved on these datasets were 92.90%, 87.16%, 90.81%, and 95.65%, respectively. These results demonstrate superior performance compared to most current state-of-the-art methods. The source code is released at https://github.com/alikm6/DEU-Net .
Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in computer vision. In this paper, we take a step in this direction and propose a multimodal training scheme called 4M. It consists of training a single unified Transformer encoder-decoder using a masked modeling objective across a wide range of input/output modalities - including text, images, geometric, and semantic modalities, as well as neural network feature maps. 4M achieves scalability by unifying the representation space of all modalities through mapping them into discrete tokens and performing multimodal masked modeling on a small randomized subset of tokens. 4M leads to models that exhibit several key capabilities: (1) they can perform a diverse set of vision tasks out of the box, (2) they excel when fine-tuned for unseen downstream tasks or new input modalities, and (3) they can function as a generative model that can be conditioned on arbitrary modalities, enabling a wide variety of expressive multimodal editing capabilities with remarkable flexibility. Through experimental analyses, we demonstrate the potential of 4M for training versatile and scalable foundation models for vision tasks, setting the stage for further exploration in multimodal learning for vision and other domains.
Improving neural machine translation (NMT) systems with prompting has achieved significant progress in recent years. In this work, we focus on how to integrate multi-knowledge, multiple types of knowledge, into NMT models to enhance the performance with prompting. We propose a unified framework, which can integrate effectively multiple types of knowledge including sentences, terminologies/phrases and translation templates into NMT models. We utilize multiple types of knowledge as prefix-prompts of input for the encoder and decoder of NMT models to guide the translation process. The approach requires no changes to the model architecture and effectively adapts to domain-specific translation without retraining. The experiments on English-Chinese and English-German translation demonstrate that our approach significantly outperform strong baselines, achieving high translation quality and terminology match accuracy.
Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as DALL-E and diffusion models, with minimal effort and cost. In this paper, we present DatasetDM, a generic dataset generation model that can produce diverse synthetic images and the corresponding high-quality perception annotations (e.g., segmentation masks, and depth). Our method builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation. We show that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module. Training the decoder only needs less than 1% (around 100 images) manually labeled images, enabling the generation of an infinitely large annotated dataset. Then these synthetic data can be used for training various perception models for downstream tasks. To showcase the power of the proposed approach, we generate datasets with rich dense pixel-wise labels for a wide range of downstream tasks, including semantic segmentation, instance segmentation, and depth estimation. Notably, it achieves 1) state-of-the-art results on semantic segmentation and instance segmentation; 2) significantly more robust on domain generalization than using the real data alone; and state-of-the-art results in zero-shot segmentation setting; and 3) flexibility for efficient application and novel task composition (e.g., image editing). The project website and code can be found at https://weijiawu.github.io/DatasetDM_page/ and https://github.com/showlab/DatasetDM, respectively
Learning object-centric representations from complex natural environments enables both humans and machines with reasoning abilities from low-level perceptual features. To capture compositional entities of the scene, we proposed cyclic walks between perceptual features extracted from vision transformers and object entities. First, a slot-attention module interfaces with these perceptual features and produces a finite set of slot representations. These slots can bind to any object entities in the scene via inter-slot competitions for attention. Next, we establish entity-feature correspondence with cyclic walks along high transition probability based on the pairwise similarity between perceptual features (aka "parts") and slot-binded object representations (aka "whole"). The whole is greater than its parts and the parts constitute the whole. The part-whole interactions form cycle consistencies, as supervisory signals, to train the slot-attention module. Our rigorous experiments on \textit{seven} image datasets in \textit{three} \textit{unsupervised} tasks demonstrate that the networks trained with our cyclic walks can disentangle foregrounds and backgrounds, discover objects, and segment semantic objects in complex scenes. In contrast to object-centric models attached with a decoder for the pixel-level or feature-level reconstructions, our cyclic walks provide strong learning signals, avoiding computation overheads and enhancing memory efficiency. Our source code and data are available at: \href{https://github.com/ZhangLab-DeepNeuroCogLab/Parts-Whole-Object-Centric-Learning/}{link}.
Recent advances in image inpainting increasingly use generative models to handle large irregular masks. However, these models can create unrealistic inpainted images due to two main issues: (1) Unwanted object insertion: Even with unmasked areas as context, generative models may still generate arbitrary objects in the masked region that don't align with the rest of the image. (2) Color inconsistency: Inpainted regions often have color shifts that causes a smeared appearance, reducing image quality. Retraining the generative model could help solve these issues, but it's costly since state-of-the-art latent-based diffusion and rectified flow models require a three-stage training process: training a VAE, training a generative U-Net or transformer, and fine-tuning for inpainting. Instead, this paper proposes a post-processing approach, dubbed as ASUKA (Aligned Stable inpainting with UnKnown Areas prior), to improve inpainting models. To address unwanted object insertion, we leverage a Masked Auto-Encoder (MAE) for reconstruction-based priors. This mitigates object hallucination while maintaining the model's generation capabilities. To address color inconsistency, we propose a specialized VAE decoder that treats latent-to-image decoding as a local harmonization task, significantly reducing color shifts for color-consistent inpainting. We validate ASUKA on SD 1.5 and FLUX inpainting variants with Places2 and MISATO, our proposed diverse collection of datasets. Results show that ASUKA mitigates object hallucination and improves color consistency over standard diffusion and rectified flow models and other inpainting methods.
Text-to-image (T2I) diffusion models, notably the unCLIP models (e.g., DALL-E-2), achieve state-of-the-art (SOTA) performance on various compositional T2I benchmarks, at the cost of significant computational resources. The unCLIP stack comprises T2I prior and diffusion image decoder. The T2I prior model alone adds a billion parameters compared to the Latent Diffusion Models, which increases the computational and high-quality data requirements. We introduce ECLIPSE, a novel contrastive learning method that is both parameter and data-efficient. ECLIPSE leverages pre-trained vision-language models (e.g., CLIP) to distill the knowledge into the prior model. We demonstrate that the ECLIPSE trained prior, with only 3.3% of the parameters and trained on a mere 2.8% of the data, surpasses the baseline T2I priors with an average of 71.6% preference score under resource-limited setting. It also attains performance on par with SOTA big models, achieving an average of 63.36% preference score in terms of the ability to follow the text compositions. Extensive experiments on two unCLIP diffusion image decoders, Karlo and Kandinsky, affirm that ECLIPSE priors consistently deliver high performance while significantly reducing resource dependency.
Degenerative spinal pathologies are highly prevalent among the elderly population. Timely diagnosis of osteoporotic fractures and other degenerative deformities facilitates proactive measures to mitigate the risk of severe back pain and disability. In this study, we specifically explore the use of shape auto-encoders for vertebrae, taking advantage of advancements in automated multi-label segmentation and the availability of large datasets for unsupervised learning. Our shape auto-encoders are trained on a large set of vertebrae surface patches, leveraging the vast amount of available data for vertebra segmentation. This addresses the label scarcity problem faced when learning shape information of vertebrae from image intensities. Based on the learned shape features we train an MLP to detect vertebral body fractures. Using segmentation masks that were automatically generated using the TotalSegmentator, our proposed method achieves an AUC of 0.901 on the VerSe19 testset. This outperforms image-based and surface-based end-to-end trained models. Additionally, our results demonstrate that pre-training the models in an unsupervised manner enhances geometric methods like PointNet and DGCNN. Our findings emphasise the advantages of explicitly learning shape features for diagnosing osteoporotic vertebrae fractures. This approach improves the reliability of classification results and reduces the need for annotated labels. This study provides novel insights into the effectiveness of various encoder-decoder models for shape analysis of vertebrae and proposes a new decoder architecture: the point-based shape decoder.
Recent advances in deep learning, and especially the invention of encoder-decoder architectures, has significantly improved the performance of abstractive summarization systems. The majority of research has focused on written documents, however, neglecting the problem of multi-party dialogue summarization. In this paper, we present a dataset of French political debates for the purpose of enhancing resources for multi-lingual dialogue summarization. Our dataset consists of manually transcribed and annotated political debates, covering a range of topics and perspectives. We highlight the importance of high quality transcription and annotations for training accurate and effective dialogue summarization models, and emphasize the need for multilingual resources to support dialogue summarization in non-English languages. We also provide baseline experiments using state-of-the-art methods, and encourage further research in this area to advance the field of dialogue summarization. Our dataset will be made publicly available for use by the research community.