Search

Large-scale self-supervised pre-training has paved the way for one foundation model to handle many different vision tasks. Most pre-training methodologies train a single model of a certain size at one time. Nevertheless, various computation or storage constraints in real-world scenarios require substantial efforts to develop a series of models with different sizes to deploy. Thus, in this study, we propose a novel tri-branch self-supervised training framework, termed as POA (Pre-training Once for All), to tackle this aforementioned issue. Our approach introduces an innovative elastic student branch into a modern self-distillation paradigm. At each pre-training step, we randomly sample a sub-network from the original student to form the elastic student and train all branches in a self-distilling fashion. Once pre-trained, POA allows the extraction of pre-trained models of diverse sizes for downstream tasks. Remarkably, the elastic student facilitates the simultaneous pre-training of multiple models with different sizes, which also acts as an additional ensemble of models of various sizes to enhance representation learning. Extensive experiments, including k-nearest neighbors, linear probing evaluation and assessments on multiple downstream tasks demonstrate the effectiveness and advantages of our POA. It achieves state-of-the-art performance using ViT, Swin Transformer and ResNet backbones, producing around a hundred models with different sizes through a single pre-training session. The code is available at: https://github.com/Qichuzyy/POA., Comment: Accepted by ECCV2024

This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various spacial scales. This architecture not only leverages global and local visual contexts effectively, but also facilitates the flexible extension of visual tokens through a compound token scaling strategy, allowing up to a 16x increase in the token count post pre-training. Consequently, Chain-of-Sight requires significantly fewer visual tokens in the pre-training phase compared to the fine-tuning phase. This intentional reduction of visual tokens during pre-training notably accelerates the pre-training process, cutting down the wall-clock training time by ~73%. Empirical results on a series of vision-language benchmarks reveal that the pre-train acceleration through Chain-of-Sight is achieved without sacrificing performance, matching or surpassing the standard pipeline of utilizing all visual tokens throughout the entire training process. Further scaling up the number of visual tokens for pre-training leads to stronger performances, competitive to existing approaches in a series of benchmarks.

The success of large pretrained models in natural language processing (NLP) and computer vision (CV) has opened new avenues for constructing foundation models for time series forecasting (TSF). Traditional TSF foundation models rely heavily on numerical data fitting. In contrast, the human brain is inherently skilled at processing visual information, prefer predicting future trends by observing visualized sequences. From a biomimetic perspective, utilizing models to directly process numerical sequences might not be the most effective route to achieving Artificial General Intelligence (AGI). This paper proposes ViTime, a novel Visual Intelligence-based foundation model for TSF. ViTime overcomes the limitations of numerical time series data fitting by utilizing visual data processing paradigms and employs a innovative data synthesis method during training, called Real Time Series (RealTS). Experiments on a diverse set of previously unseen forecasting datasets demonstrate that ViTime achieves state-of-the-art zero-shot performance, even surpassing the best individually trained supervised models in some situations. These findings suggest that visual intelligence can significantly enhance time series analysis and forecasting, paving the way for more advanced and versatile models in the field. The code for our framework is accessible at https://github.com/IkeYang/ViTime.

Remote Sensing Large Multi-Modal Models (RSLMMs) are developing rapidly and showcase significant capabilities in remote sensing imagery (RSI) comprehension. However, due to the limitations of existing datasets, RSLMMs have shortcomings in understanding the rich semantic relations among objects in complex remote sensing scenes. To unlock RSLMMs' complex comprehension ability, we propose a large-scale instruction tuning dataset FIT-RS, containing 1,800,851 instruction samples. FIT-RS covers common interpretation tasks and innovatively introduces several complex comprehension tasks of escalating difficulty, ranging from relation reasoning to image-level scene graph generation. Based on FIT-RS, we build the FIT-RSFG benchmark. Furthermore, we establish a new benchmark to evaluate the fine-grained relation comprehension capabilities of LMMs, named FIT-RSRC. Based on combined instruction data, we propose SkySenseGPT, which achieves outstanding performance on both public datasets and FIT-RSFG, surpassing existing RSLMMs. We hope the FIT-RS dataset can enhance the relation comprehension capability of RSLMMs and provide a large-scale fine-grained data source for the remote sensing community. The dataset will be available at https://github.com/Luo-Z13/SkySenseGPT, Comment: 30 pages, 5 figures, 19 tables, dataset and code see https://github.com/Luo-Z13/SkySenseGPT

Blind-audio-source-separation (BASS) techniques, particularly those with low latency, play an important role in a wide range of real-time systems, e.g., hearing aids, in-car hand-free voice communication, real-time human-machine interaction, etc. Most existing BASS algorithms are deduced to run on batch mode, and therefore large latency is unavoidable. Recently, some online algorithms were developed, which achieve separation on a frame-by-frame basis in the short-time-Fourier-transform (STFT) domain and the latency is significantly reduced as compared to those batch methods. However, the latency with these algorithms may still be too long for many real-time systems to bear. To further reduce latency while achieving good separation performance, we propose in this work to integrate a weighted prediction error (WPE) module into a non-causal sample-truncating-based independent vector analysis (NST-IVA). The resulting algorithm can maintain the algorithmic delay as NST-IVA if the delay with WPE is appropriately controlled while achieving significantly better performance, which is validated by simulations., Comment: 4 pages, 4 figures. Accepted by EUSIPCO 2024

The design of the query is crucial for the performance of DETR and its variants. Each query consists of two components: a content part and a positional one. Traditionally, the content query is initialized with a zero or learnable embedding, lacking essential content information and resulting in sub-optimal performance. In this paper, we introduce a novel plug-and-play module, Self-Adaptive Content Query (SACQ), to address this limitation. The SACQ module utilizes features from the transformer encoder to generate content queries via self-attention pooling. This allows candidate queries to adapt to the input image, resulting in a more comprehensive content prior and better focus on target objects. However, this improved concentration poses a challenge for the training process that utilizes the Hungarian matching, which selects only a single candidate and suppresses other similar ones. To overcome this, we propose a query aggregation strategy to cooperate with SACQ. It merges similar predicted candidates from different queries, easing the optimization. Our extensive experiments on the COCO dataset demonstrate the effectiveness of our proposed approaches across six different DETR's variants with multiple configurations, achieving an average improvement of over 1.0 AP., Comment: 11 pages, 7 figures

Recent works in implicit representations, such as Neural Radiance Fields (NeRF), have advanced the generation of realistic and animatable head avatars from video sequences. These implicit methods are still confronted by visual artifacts and jitters, since the lack of explicit geometric constraints poses a fundamental challenge in accurately modeling complex facial deformations. In this paper, we introduce Dynamic Tetrahedra (DynTet), a novel hybrid representation that encodes explicit dynamic meshes by neural networks to ensure geometric consistency across various motions and viewpoints. DynTet is parameterized by the coordinate-based networks which learn signed distance, deformation, and material texture, anchoring the training data into a predefined tetrahedra grid. Leveraging Marching Tetrahedra, DynTet efficiently decodes textured meshes with a consistent topology, enabling fast rendering through a differentiable rasterizer and supervision via a pixel loss. To enhance training efficiency, we incorporate classical 3D Morphable Models to facilitate geometry learning and define a canonical space for simplifying texture learning. These advantages are readily achievable owing to the effective geometric representation employed in DynTet. Compared with prior works, DynTet demonstrates significant improvements in fidelity, lip synchronization, and real-time performance according to various metrics. Beyond producing stable and visually appealing synthesis videos, our method also outputs the dynamic meshes which is promising to enable many emerging applications., Comment: CVPR 2024

Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of large-scale pretraining datasets. Toward this end, we introduce a comprehensive bilingual (Chinese-English) dataset BM-6B with over 6 billion image-text pairs, aimed at enhancing multimodal foundation models to well understand images in both languages. To handle such a scale of dataset, we propose a novel grouped aggregation approach for image-text contrastive loss computation, which reduces the communication overhead and GPU memory demands significantly, facilitating a 60% increase in training speed. We pretrain a series of bilingual image-text foundation models with an enhanced fine-grained understanding ability on BM-6B, the resulting models, dubbed as $M^2$-Encoders (pronounced "M-Square"), set new benchmarks in both languages for multimodal retrieval and classification tasks. Notably, Our largest $M^2$-Encoder-10B model has achieved top-1 accuracies of 88.5% on ImageNet and 80.7% on ImageNet-CN under a zero-shot classification setting, surpassing previously reported SoTA methods by 2.2% and 21.1%, respectively. The $M^2$-Encoder series represents one of the most comprehensive bilingual image-text foundation models to date, so we are making it available to the research community for further exploration and development.

The so-called independent low-rank matrix analysis (ILRMA) has demonstrated a great potential for dealing with the problem of determined blind source separation (BSS) for audio and speech signals. This method assumes that the spectra from different frequency bands are independent and the spectral coefficients in any frequency band are Gaussian distributed. The Itakura-Saito divergence is then employed to estimate the source model related parameters. In reality, however, the spectral coefficients from different frequency bands may be dependent, which is not considered in the existing ILRMA algorithm. This paper presents an improved version of ILRMA, which considers the dependency between the spectral coefficients from different frequency bands. The Sinkhorn divergence is then exploited to optimize the source model parameters. As a result of using the cross-band information, the BSS performance is improved. But the number of parameters to be estimated also increases significantly, and so is the computational complexity. To reduce the algorithm complexity, we apply the Kronecker product to decompose the modeling matrix into the product of a number of matrices of much smaller dimensionality. An efficient algorithm is then developed to implement the Sinkhorn divergence based BSS algorithm and the complexity is reduced by an order of magnitude.