In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred many researchers. To further reduce the complexity of attention models, numerous efforts have been made to design more efficient methods. Among them, the State Space Model (SSM), as a possible replacement for the self-attention based Transformer model, has drawn more and more attention in recent years. In this paper, we give the first comprehensive review of these works and also provide experimental comparisons and analysis to better demonstrate the features and advantages of SSM. Specifically, we first give a detailed description of principles to help the readers quickly capture the key ideas of SSM. After that, we dive into the reviews of existing SSMs and their various applications, including natural language processing, computer vision, graph, multi-modal and multi-media, point cloud/event stream, time series data, and other domains. In addition, we give statistical comparisons and analysis of these models and hope it helps the readers to understand the effectiveness of different structures on various tasks. Then, we propose possible research points in this direction to better promote the development of the theoretical model and application of SSM. More related works will be continuously updated on the following GitHub: https://github.com/Event-AHU/Mamba_State_Space_Model_Paper_List.
Ultrasound video-based breast lesion segmentation provides a valuable assistance in early breast lesion detection and treatment. However, existing works mainly focus on lesion segmentation based on ultrasound breast images which usually can not be adapted well to obtain desirable results on ultrasound videos. The main challenge for ultrasound video-based breast lesion segmentation is how to exploit the lesion cues of both intra-frame and inter-frame simultaneously. To address this problem, we propose a novel Spatial-Temporal Progressive Fusion Network (STPFNet) for video based breast lesion segmentation problem. The main aspects of the proposed STPFNet are threefold. First, we propose to adopt a unified network architecture to capture both spatial dependences within each ultrasound frame and temporal correlations between different frames together for ultrasound data representation. Second, we propose a new fusion module, termed Multi-Scale Feature Fusion (MSFF), to fuse spatial and temporal cues together for lesion detection. MSFF can help to determine the boundary contour of lesion region to overcome the issue of lesion boundary blurring. Third, we propose to exploit the segmentation result of previous frame as the prior knowledge to suppress the noisy background and learn more robust representation. In particular, we introduce a new publicly available ultrasound video breast lesion segmentation dataset, termed UVBLS200, which is specifically dedicated to breast lesion segmentation. It contains 200 videos, including 80 videos of benign lesions and 120 videos of malignant lesions. Experiments on the proposed dataset demonstrate that the proposed STPFNet achieves better breast lesion detection performance than state-of-the-art methods.
Differential Privacy (DP) mechanisms usually {force} reduction in data utility by producing ``out-of-bound'' noisy results for a tight privacy budget. We introduce the Budget Recycling Differential Privacy (BR-DP) framework, designed to provide soft-bounded noisy outputs for a broad range of existing DP mechanisms. By ``soft-bounded," we refer to the mechanism's ability to release most outputs within a predefined error boundary, thereby improving utility and maintaining privacy simultaneously. The core of BR-DP consists of two components: a DP kernel responsible for generating a noisy answer per iteration, and a recycler that probabilistically recycles/regenerates or releases the noisy answer. We delve into the privacy accounting of BR-DP, culminating in the development of a budgeting principle that optimally sub-allocates the available budget between the DP kernel and the recycler. Furthermore, we introduce algorithms for tight BR-DP accounting in composition scenarios, and our findings indicate that BR-DP achieves reduced privacy leakage post-composition compared to DP. Additionally, we explore the concept of privacy amplification via subsampling within the BR-DP framework and propose optimal sampling rates for BR-DP across various queries. We experiment with real data, and the results demonstrate BR-DP's effectiveness in lifting the utility-privacy tradeoff provided by DP mechanisms.
Exploring and mining subtle yet distinctive features between sub-categories with similar appearances is crucial for fine-grained visual categorization (FGVC). However, less effort has been devoted to assessing the quality of extracted visual representations. Intuitively, the network may struggle to capture discriminative features from low-quality samples, which leads to a significant decline in FGVC performance. To tackle this challenge, we propose a weakly supervised Context-Semantic Quality Awareness Network (CSQA-Net) for FGVC. In this network, to model the spatial contextual relationship between rich part descriptors and global semantics for capturing more discriminative details within the object, we design a novel multi-part and multi-scale cross-attention (MPMSCA) module. Before feeding to the MPMSCA module, the part navigator is developed to address the scale confusion problems and accurately identify the local distinctive regions. Furthermore, we propose a generic multi-level semantic quality evaluation module (MLSQE) to progressively supervise and enhance hierarchical semantics from different levels of the backbone network. Finally, context-aware features from MPMSCA and semantically enhanced features from MLSQE are fed into the corresponding quality probing classifiers to evaluate their quality in real-time, thus boosting the discriminability of feature representations. Comprehensive experiments on four popular and highly competitive FGVC datasets demonstrate the superiority of the proposed CSQA-Net in comparison with the state-of-the-art methods.
Current event-/frame-event based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking algorithms in these scenarios remains unclear. In this paper, we first propose a new long-term and large-scale frame-event single object tracking dataset, termed FELT. It contains 742 videos and 1,594,474 RGB frames and event stream pairs and has become the largest frame-event tracking dataset to date. We re-train and evaluate 15 baseline trackers on our dataset for future works to compare. More importantly, we find that the RGB frames and event streams are naturally incomplete due to the influence of challenging factors and spatially sparse event flow. In response to this, we propose a novel associative memory Transformer network as a unified backbone by introducing modern Hopfield layers into multi-head self-attention blocks to fuse both RGB and event data. Extensive experiments on both FELT and RGB-T tracking dataset LasHeR fully validated the effectiveness of our model. The dataset and source code can be found at \url{https://github.com/Event-AHU/FELT_SOT_Benchmark}.
Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it becomes critical to assess in advance whether they are suitable for a specific target task. Model transferability estimation is an emerging and growing area of interest, aiming to propose a metric to quantify this suitability without training them individually, which is computationally prohibitive. Despite extensive recent advances already devoted to this area, they have custom terminological definitions and experimental settings. In this survey, we present the first review of existing advances in this area and categorize them into two separate realms: source-free model transferability estimation and source-dependent model transferability estimation. Each category is systematically defined, accompanied by a comprehensive taxonomy. Besides, we address challenges and outline future research directions, intending to provide a comprehensive guide to aid researchers and practitioners.
Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. In this work, to cope with the uncertainty problem, we propose VADv2, an end-to-end driving model based on probabilistic planning. VADv2 takes multi-view image sequences as input in a streaming manner, transforms sensor data into environmental token embeddings, outputs the probabilistic distribution of action, and samples one action to control the vehicle. Only with camera sensors, VADv2 achieves state-of-the-art closed-loop performance on the CARLA Town05 benchmark, significantly outperforming all existing methods. It runs stably in a fully end-to-end manner, even without the rule-based wrapper. Closed-loop demos are presented at https://hgao-cv.github.io/VADv2.
Graph contrastive learning is usually performed by first conducting Graph Data Augmentation (GDA) and then employing a contrastive learning pipeline to train GNNs. As we know that GDA is an important issue for graph contrastive learning. Various GDAs have been developed recently which mainly involve dropping or perturbing edges, nodes, node attributes and edge attributes. However, to our knowledge, it still lacks a universal and effective augmentor that is suitable for different types of graph data. To address this issue, in this paper, we first introduce the graph message representation of graph data. Based on it, we then propose a novel Graph Message Augmentation (GMA), a universal scheme for reformulating many existing GDAs. The proposed unified GMA not only gives a new perspective to understand many existing GDAs but also provides a universal and more effective graph data augmentation for graph self-supervised learning tasks. Moreover, GMA introduces an easy way to implement the mixup augmentor which is natural for images but usually challengeable for graphs. Based on the proposed GMA, we then propose a unified graph contrastive learning, termed Graph Message Contrastive Learning (GMCL), that employs attribution-guided universal GMA for graph contrastive learning. Experiments on many graph learning tasks demonstrate the effectiveness and benefits of the proposed GMA and GMCL approaches.
Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data representation, treating the nonlinear neural network as a ``black box". However, the accurate learning results of neural networks are crucial for describing the data distribution features learned by SSL models. Our paper is the first to analyze the learning results of the nonlinear SSL model accurately. We consider a toy data distribution that contains two features: the label-related feature and the hidden feature. Unlike previous linear setting work that depends on closed-form solutions, we use the gradient descent algorithm to train a 1-layer nonlinear SSL model with a certain initialization region and prove that the model converges to a local minimum. Furthermore, different from the complex iterative analysis, we propose a new analysis process which uses the exact version of Inverse Function Theorem to accurately describe the features learned by the local minimum. With this local minimum, we prove that the nonlinear SSL model can capture the label-related feature and hidden feature at the same time. In contrast, the nonlinear supervised learning (SL) model can only learn the label-related feature. We also present the learning processes and results of the nonlinear SSL and SL model via simulation experiments.
Existing datasets for RGB-DVS tracking are collected with DVS346 camera and their resolution ($346 \times 260$) is low for practical applications. Actually, only visible cameras are deployed in many practical systems, and the newly designed neuromorphic cameras may have different resolutions. The latest neuromorphic sensors can output high-definition event streams, but it is very difficult to achieve strict alignment between events and frames on both spatial and temporal views. Therefore, how to achieve accurate tracking with unaligned neuromorphic and visible sensors is a valuable but unresearched problem. In this work, we formally propose the task of object tracking using unaligned neuromorphic and visible cameras. We build the first unaligned frame-event dataset CRSOT collected with a specially built data acquisition system, which contains 1,030 high-definition RGB-Event video pairs, 304,974 video frames. In addition, we propose a novel unaligned object tracking framework that can realize robust tracking even using the loosely aligned RGB-Event data. Specifically, we extract the template and search regions of RGB and Event data and feed them into a unified ViT backbone for feature embedding. Then, we propose uncertainty perception modules to encode the RGB and Event features, respectively, then, we propose a modality uncertainty fusion module to aggregate the two modalities. These three branches are jointly optimized in the training phase. Extensive experiments demonstrate that our tracker can collaborate the dual modalities for high-performance tracking even without strictly temporal and spatial alignment. The source code, dataset, and pre-trained models will be released at https://github.com/Event-AHU/Cross_Resolution_SOT.