The prevalence of convolution neural networks (CNNs) and vision transformers (ViTs) has markedly revolutionized the area of single-image super-resolution (SISR). To further boost the SR performances, several techniques, such as residual learning and attention mechanism, are introduced, which can be largely attributed to a wider range of activated area, that is, the input pixels that strongly influence the SR results. However, the possibility of further improving SR performance through another versatile vision backbone remains an unresolved challenge. To address this issue, in this paper, we unleash the representation potential of the modern state space model, i.e., Vision Mamba (Vim), in the context of SISR. Specifically, we present three recipes for better utilization of Vim-based models: 1) Integration into a MetaFormer-style block; 2) Pre-training on a larger and broader dataset; 3) Employing complementary attention mechanism, upon which we introduce the MMA. The resulting network MMA is capable of finding the most relevant and representative input pixels to reconstruct the corresponding high-resolution images. Comprehensive experimental analysis reveals that MMA not only achieves competitive or even superior performance compared to state-of-the-art SISR methods but also maintains relatively low memory and computational overheads (e.g., +0.5 dB PSNR elevation on Manga109 dataset with 19.8 M parameters at the scale of 2). Furthermore, MMA proves its versatility in lightweight SR applications. Through this work, we aim to illuminate the potential applications of state space models in the broader realm of image processing rather than SISR, encouraging further exploration in this innovative direction.
Recently, the application of Contrastive Representation Learning (CRL) in learning with noisy labels (LNL) has shown promising advancements due to its remarkable ability to learn well-distributed representations for better distinguishing noisy labels. However, CRL is mainly used as a pre-training technique, leading to a complicated multi-stage training pipeline. We also observed that trivially combining CRL with supervised LNL methods decreases performance. Using different images from the same class as negative pairs in CRL creates optimization conflicts between CRL and the supervised loss. To address these two issues, we propose an end-to-end PLReMix framework that avoids the complicated pipeline by introducing a Pseudo-Label Relaxed (PLR) contrastive loss to alleviate the conflicts between losses. This PLR loss constructs a reliable negative set of each sample by filtering out its inappropriate negative pairs that overlap at the top k indices of prediction probabilities, leading to more compact semantic clusters than vanilla CRL. Furthermore, a two-dimensional Gaussian Mixture Model (GMM) is adopted to distinguish clean and noisy samples by leveraging semantic information and model outputs simultaneously, which is expanded on the previously widely used one-dimensional form. The PLR loss and a semi-supervised loss are simultaneously applied to train on the GMM divided clean and noisy samples. Experiments on multiple benchmark datasets demonstrate the effectiveness of the proposed method. Our proposed PLR loss is scalable, which can be easily integrated into other LNL methods and boost their performance. Codes will be available.
The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP typically require offline fine-tuning of the parameters on few-shot samples, resulting in longer inference time and the risk of over-fitting in certain domains. To tackle these challenges, we propose the Meta-Adapter, a lightweight residual-style adapter, to refine the CLIP features guided by the few-shot samples in an online manner. With a few training samples, our method can enable effective few-shot learning capabilities and generalize to unseen data or tasks without additional fine-tuning, achieving competitive performance and high efficiency. Without bells and whistles, our approach outperforms the state-of-the-art online few-shot learning method by an average of 3.6\% on eight image classification datasets with higher inference speed. Furthermore, our model is simple and flexible, serving as a plug-and-play module directly applicable to downstream tasks. Without further fine-tuning, Meta-Adapter obtains notable performance improvements in open-vocabulary object detection and segmentation tasks.
In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3.2 trillion tokens drawn from both English and Chinese texts. This bilingual foundation model is the most extensively trained and openly published LLMs of comparable size to date. We introduce a two-stage training methodology using a segmented corpus, targeting general purpose training and then domain-specific enhancement training, respectively. We show that our model not only excels on popular benchmarks, but also achieves \emph{state of the art} performance in Chinese language modeling on diverse domains. Furthermore, we propose a novel leakage detection method, demonstrating that test data contamination is a pressing issue warranting further investigation by the LLM community. To spur future research, we release Skywork-13B along with checkpoints obtained during intermediate stages of the training process. We are also releasing part of our SkyPile corpus, a collection of over 150 billion tokens of web text, which is the largest high quality open Chinese pre-training corpus to date. We hope Skywork-13B and our open corpus will serve as a valuable open-source resource to democratize access to high-quality LLMs.
The random sampling on graph signals is one of the fundamental topics in graph signal processing. In this letter, we consider the random sampling of k-bandlimited signals from the local measurements and show that no more than O(klogk) measurements with replacement are sufficient for the accurate and stable recovery of any k-bandlimited graph signals. We propose two random sampling strategies based on the minimum measurements, i.e., the optimal sampling and the estimated sampling. The geodesic distance between vertices is introduced to design the sampling probability distribution. Numerical experiments are included to show the effectiveness of the proposed methods.
This paper presents a novel transformer architecture for graph representation learning. The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks. Specifically, we propose a new attention mechanism called Graph Propagation Attention (GPA). It explicitly passes the information among nodes and edges in three ways, i.e. node-to-node, node-to-edge, and edge-to-node, which is essential for learning graph-structured data. On this basis, we design an effective transformer architecture named Graph Propagation Transformer (GPTrans) to further help learn graph data. We verify the performance of GPTrans in a wide range of graph learning experiments on several benchmark datasets. These results show that our method outperforms many state-of-the-art transformer-based graph models with better performance. The code will be released at https://github.com/czczup/GPTrans.
Graph Fourier transform (GFT) is one of the fundamental tools in graph signal processing to decompose graph signals into different frequency components and to represent graph signals with strong correlation by different modes of variation effectively. The GFT on undirected graphs has been well studied and several approaches have been proposed to define GFTs on directed graphs. In this paper, based on the singular value decompositions of some graph Laplacians, we propose two GFTs on the Cartesian product graph of two directed graphs. We show that the proposed GFTs could represent spatial-temporal data sets on directed networks with strong correlation efficiently, and in the undirected graph setting they are essentially the joint GFT in the literature. In this paper, we also consider the bandlimiting procedure in the spectral domain of the proposed GFTs, and demonstrate its performance to denoise the temperature data set in the region of Brest (France) on January 2014.
With COVID-19 now pervasive, identification of high-risk individuals is crucial. Using data from a major healthcare provider in Southwestern Pennsylvania, we develop survival models predicting severe COVID-19 progression. In this endeavor, we face a tradeoff between more accurate models relying on many features and less accurate models relying on a few features aligned with clinician intuition. Complicating matters, many EHR features tend to be under-coded, degrading the accuracy of smaller models. In this study, we develop two sets of high-performance risk scores: (i) an unconstrained model built from all available features; and (ii) a pipeline that learns a small set of clinical concepts before training a risk predictor. Learned concepts boost performance over the corresponding features (C-index 0.858 vs. 0.844) and demonstrate improvements over (i) when evaluated out-of-sample (subsequent time periods). Our models outperform previous works (C-index 0.844-0.872 vs. 0.598-0.810).
Graph Fourier transform (GFT) is a fundamental concept in graph signal processing. In this paper, based on singular value decomposition of Laplacian, we introduce a novel definition of GFT on directed graphs, and use singular values of Laplacian to carry the notion of graph frequencies. % of the proposed GFT. The proposed GFT is consistent with the conventional GFT in the undirected graph setting, and on directed circulant graphs, the proposed GFT is the classical discrete Fourier transform, up to some rotation, permutation and phase adjustment. We show that frequencies and frequency components of the proposed GFT can be evaluated by solving some constrained minimization problems with low computational cost. Numerical demonstrations indicate that the proposed GFT could represent graph signals with different modes of variation efficiently.
In this paper, we consider Wiener filters to reconstruct deterministic and (wide-band) stationary graph signals from their observations corrupted by random noises, and we propose distributed algorithms to implement Wiener filters and inverse filters on networks in which agents are equipped with a data processing subsystem for limited data storage and computation power, and with a one-hop communication subsystem for direct data exchange only with their adjacent agents. The proposed distributed polynomial approximation algorithm is an exponential convergent quasi-Newton method based on Jacobi polynomial approximation and Chebyshev interpolation polynomial approximation to analytic functions on a cube. Our numerical simulations show that Wiener filtering procedure performs better on denoising (wide-band) stationary signals than the Tikhonov regularization approach does, and that the proposed polynomial approximation algorithms converge faster than the Chebyshev polynomial approximation algorithm and gradient decent algorithm do in the implementation of an inverse filtering procedure associated with a polynomial filter of commutative graph shifts.