Infrared Small Target Detection (IRSTD) aims to segment small targets from infrared clutter background. Existing methods mainly focus on discriminative approaches, i.e., a pixel-level front-background binary segmentation. Since infrared small targets are small and low signal-to-clutter ratio, empirical risk has few disturbances when a certain false alarm and missed detection exist, which seriously affect the further improvement of such methods. Motivated by the dense prediction generative methods, in this paper, we propose a diffusion model framework for Infrared Small Target Detection which compensates pixel-level discriminant with mask posterior distribution modeling. Furthermore, we design a Low-frequency Isolation in the wavelet domain to suppress the interference of intrinsic infrared noise on the diffusion noise estimation. This transition from the discriminative paradigm to generative one enables us to bypass the target-level insensitivity. Experiments show that the proposed method achieves competitive performance gains over state-of-the-art methods on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST datasets. Code are available at https://github.com/Li-Haoqing/IRSTD-Diff.
Infrared Small Target Detection is a challenging task to separate small targets from infrared clutter background. Recently, deep learning paradigms have achieved promising results. However, these data-driven methods need plenty of manual annotation. Due to the small size of infrared targets, manual annotation consumes more resources and restricts the development of this field. This letter proposed a labor-efficient and cursory annotation framework with level set, which obtains a high-quality pseudo mask with only one cursory click. A variational level set formulation with an expectation difference energy functional is designed, in which the zero level contour is intrinsically maintained during the level set evolution. It solves the issue that zero level contour disappearing due to small target size and excessive regularization. Experiments on the NUAA-SIRST and IRSTD-1k datasets reveal that our approach achieves superior performance. Code is available at https://github.com/Li-Haoqing/COM.
Infrared small target detection is a technique for finding small targets from infrared clutter background. Due to the dearth of high-level semantic information, small infrared target features are weakened in the deep layers of the CNN, which underachieves the CNN's representation ability. To address the above problem, in this paper, we propose an infrared low-level network (ILNet) that considers infrared small targets as salient areas with little semantic information. Unlike other SOTA methods, ILNet pays greater attention to low-level information instead of treating them equally. A new lightweight feature fusion module, named Interactive Polarized Orthogonal Fusion module (IPOF), is proposed, which integrates more important low-level features from the shallow layers into the deep layers. A Dynamic One-Dimensional Aggregation layers (DODA) are inserted into the IPOF, to dynamically adjust the aggregation of low dimensional information according to the number of input channels. In addition, the idea of ensemble learning is used to design a Representative Block (RB) to dynamically allocate weights for shallow and deep layers. Experimental results on the challenging NUAA-SIRST (78.22% nIoU and 1.33e-6 Fa) and IRSTD-1K (68.91% nIoU and 3.23e-6 Fa) dataset demonstrate that the proposed ILNet can get better performances than other SOTA methods. Moreover, ILNet can obtain a greater improvement with the increasement of data volume. Training code are available at https://github.com/Li-Haoqing/ILNet.
We study a normalizing flow in the latent space of a top-down generator model, in which the normalizing flow model plays the role of the informative prior model of the generator. We propose to jointly learn the latent space normalizing flow prior model and the top-down generator model by a Markov chain Monte Carlo (MCMC)-based maximum likelihood algorithm, where a short-run Langevin sampling from the intractable posterior distribution is performed to infer the latent variables for each observed example, so that the parameters of the normalizing flow prior and the generator can be updated with the inferred latent variables. We show that, under the scenario of non-convergent short-run MCMC, the finite step Langevin dynamics is a flow-like approximate inference model and the learning objective actually follows the perturbation of the maximum likelihood estimation (MLE). We further point out that the learning framework seeks to (i) match the latent space normalizing flow and the aggregated posterior produced by the short-run Langevin flow, and (ii) bias the model from MLE such that the short-run Langevin flow inference is close to the true posterior. Empirical results of extensive experiments validate the effectiveness of the proposed latent space normalizing flow model in the tasks of image generation, image reconstruction, anomaly detection, supervised image inpainting and unsupervised image recovery.
Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument. The problem of estimating a set of parameters configuration that best restore a sound timbre is an important yet complicated problem, i.e.: the synthesizer parameters estimation problem. We proposed a multi-modal deep-learning-based pipeline Sound2Synth, together with a network structure Prime-Dilated Convolution (PDC) specially designed to solve this problem. Our method achieved not only SOTA but also the first real-world applicable results on Dexed synthesizer, a popular FM synthesizer.
Video summarization intends to produce a concise video summary by effectively capturing and combining the most informative parts of the whole content. Existing approaches for video summarization regard the task as a frame-wise keyframe selection problem and generally construct the frame-wise representation by combining the long-range temporal dependency with the unimodal or bimodal information. However, the optimal video summaries need to reflect the most valuable keyframe with its own information, and one with semantic power of the whole content. Thus, it is critical to construct a more powerful and robust frame-wise representation and predict the frame-level importance score in a fair and comprehensive manner. To tackle the above issues, we propose a multimodal hierarchical shot-aware convolutional network, denoted as MHSCNet, to enhance the frame-wise representation via combining the comprehensive available multimodal information. Specifically, we design a hierarchical ShotConv network to incorporate the adaptive shot-aware frame-level representation by considering the short-range and long-range temporal dependency. Based on the learned shot-aware representations, MHSCNet can predict the frame-level importance score in the local and global view of the video. Extensive experiments on two standard video summarization datasets demonstrate that our proposed method consistently outperforms state-of-the-art baselines. Source code will be made publicly available.
The core of a self-supervised learning method for pre-training language models includes the design of appropriate data augmentation and corresponding pre-training task(s). Most data augmentations in language model pre-training are context-independent. The seminal contextualized augmentation recently proposed by the ELECTRA requires a separate generator, which leads to extra computation cost as well as the challenge in adjusting the capability of its generator relative to that of the other model component(s). We propose a self-augmented strategy (SAS) that uses a single forward pass through the model to augment the input data for model training in the next epoch. Essentially our strategy eliminates a separate generator network and uses only one network to generate the data augmentation and undertake two pre-training tasks (the MLM task and the RTD task) jointly, which naturally avoids the challenge in adjusting the generator's capability as well as reduces the computation cost. Additionally, our SAS is a general strategy such that it can seamlessly incorporate many new techniques emerging recently or in the future, such as the disentangled attention mechanism recently proposed by the DeBERTa model. Our experiments show that our SAS is able to outperform the ELECTRA and other state-of-the-art models in the GLUE tasks with the same or less computation cost.
We propose a generative model of unordered point sets, such as point clouds, in the forms of an energy-based model, where the energy function is parameterized by an input-permutation-invariant bottom-up neural network. The energy function learns a coordinate encoding of each point and then aggregates all individual point features into energy for the whole point cloud. We show that our model can be derived from the discriminative PointNet. The model can be trained by MCMC-based maximum likelihood learning (as well as its variants), without the help of any assisting networks like those in GANs and VAEs. Unlike most point cloud generator that relys on hand-crafting distance metrics, our model does not rely on hand-crafting distance metric for point cloud generation, because it synthesizes point clouds by matching observed examples in terms of statistical property defined by the energy function. Furthermore, we can learn a short-run MCMC toward the energy-based model as a flow-like generator for point cloud reconstruction and interpretation. The learned point cloud representation can be also useful for point cloud classification. Experiments demonstrate the advantages of the proposed generative model of point clouds.
Autonomous driving is a challenging multiagent domain which requires optimizing complex, mixed cooperative-competitive interactions. Learning to predict contingent distributions over other vehicles' trajectories simplifies the problem, allowing approximate solutions by trajectory optimization with dynamic constraints. We take a model-based approach to prediction, in order to make use of structured prior knowledge of vehicle kinematics, and the assumption that other drivers plan trajectories to minimize an unknown cost function. We introduce a novel inverse optimal control (IOC) algorithm to learn other vehicles' cost functions in an energy-based generative model. Langevin Sampling, a Monte Carlo based sampling algorithm, is used to directly sample the control sequence. Our algorithm provides greater flexibility than standard IOC methods, and can learn higher-level, non-Markovian cost functions defined over entire trajectories. We extend weighted feature-based cost functions with neural networks to obtain NN-augmented cost functions, which combine the advantages of both model-based and model-free learning. Results show that model-based IOC can achieve state-of-the-art vehicle trajectory prediction accuracy, and naturally take scene information into account.
Accurate prediction of others' trajectories is essential for autonomous driving. Trajectory prediction is challenging because it requires reasoning about agents' past movements, social interactions among varying numbers and kinds of agents, constraints from the scene context, and the stochasticity of human behavior. Our approach models these interactions and constraints jointly within a novel Multi-Agent Tensor Fusion (MATF) network. Specifically, the model encodes multiple agents' past trajectories and the scene context into a Multi-Agent Tensor, then applies convolutional fusion to capture multiagent interactions while retaining the spatial structure of agents and the scene context. The model decodes recurrently to multiple agents' future trajectories, using adversarial loss to learn stochastic predictions. Experiments on both highway driving and pedestrian crowd datasets show that the model achieves state-of-the-art prediction accuracy.