We propose a framework for learned image and video compression using the generative sparse visual representation (SVR) guided by fidelity-preserving controls. By embedding inputs into a discrete latent space spanned by learned visual codebooks, SVR-based compression transmits integer codeword indices, which is efficient and cross-platform robust. However, high-quality (HQ) reconstruction in the decoder relies on intermediate feature inputs from the encoder via direct connections. Due to the prohibitively high transmission costs, previous SVR-based compression methods remove such feature links, resulting in largely degraded reconstruction quality. In this work, we treat the intermediate features as fidelity-preserving control signals that guide the conditioned generative reconstruction in the decoder. Instead of discarding or directly transferring such signals, we draw them from a low-quality (LQ) fidelity-preserving alternative input that is sent to the decoder with very low bitrate. These control signals provide complementary fidelity cues to improve reconstruction, and their quality is determined by the compression rate of the LQ alternative, which can be tuned to trade off bitrate, fidelity and perceptual quality. Our framework can be conveniently used for both learned image compression (LIC) and learned video compression (LVC). Since SVR is robust against input perturbations, a large portion of codeword indices between adjacent frames can be the same. By only transferring different indices, SVR-based LIC and LVC can share a similar processing pipeline. Experiments over standard image and video compression benchmarks demonstrate the effectiveness of our approach.
The article explores the intersection of computer vision technology and robotic control, highlighting its importance in various fields such as industrial automation, healthcare, and environmental protection. Computer vision technology, which simulates human visual observation, plays a crucial role in enabling robots to perceive and understand their surroundings, leading to advancements in tasks like autonomous navigation, object recognition, and waste management. By integrating computer vision with robot control, robots gain the ability to interact intelligently with their environment, improving efficiency.
Quantitative Susceptibility Mapping (QSM) dipole inversion is an ill-posed inverse problem for quantifying magnetic susceptibility distributions from MRI tissue phases. While supervised deep learning methods have shown success in specific QSM tasks, their generalizability across different acquisition scenarios remains constrained. Recent developments in diffusion models have demonstrated potential for solving 2D medical imaging inverse problems. However, their application to 3D modalities, such as QSM, remains challenging due to high computational demands. In this work, we developed a 3D image patch-based diffusion model, namely QSMDiff, for robust QSM reconstruction across different scan parameters, alongside simultaneous super-resolution and image-denoising tasks. QSMDiff adopts unsupervised 3D image patch training and full-size measurement guidance during inference for controlled image generation. Evaluation on simulated and in-vivo human brains, using gradient-echo and echo-planar imaging sequences across different acquisition parameters, demonstrates superior performance. The method proposed in QSMDiff also holds promise for impacting other 3D medical imaging applications beyond QSM.
We investigate the empirical counterpart of group distributionally robust optimization (GDRO), which aims to minimize the maximal empirical risk across $m$ distinct groups. We formulate empirical GDRO as a $\textit{two-level}$ finite-sum convex-concave minimax optimization problem and develop a stochastic variance reduced mirror prox algorithm. Unlike existing methods, we construct the stochastic gradient by per-group sampling technique and perform variance reduction for all groups, which fully exploits the $\textit{two-level}$ finite-sum structure of empirical GDRO. Furthermore, we compute the snapshot and mirror snapshot point by a one-index-shifted weighted average, which distinguishes us from the naive ergodic average. Our algorithm also supports non-constant learning rates, which is different from existing literature. We establish convergence guarantees both in expectation and with high probability, demonstrating a complexity of $\mathcal{O}\left(\frac{m\sqrt{\bar{n}\ln{m}}}{\varepsilon}\right)$, where $\bar n$ is the average number of samples among $m$ groups. Remarkably, our approach outperforms the state-of-the-art method by a factor of $\sqrt{m}$. Furthermore, we extend our methodology to deal with the empirical minimax excess risk optimization (MERO) problem and manage to give the expectation bound and the high probability bound, accordingly. The complexity of our empirical MERO algorithm matches that of empirical GDRO at $\mathcal{O}\left(\frac{m\sqrt{\bar{n}\ln{m}}}{\varepsilon}\right)$, significantly surpassing the bounds of existing methods.
Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the training of accurate neural models. Its applications span various domains, including transfer learning, federated learning, and neural architecture search. The most popular methods for constructing the synthetic data rely on matching the convergence properties of training the model with the synthetic dataset and the training dataset. However, targeting the training dataset must be thought of as auxiliary in the same sense that the training set is an approximate substitute for the population distribution, and the latter is the data of interest. Yet despite its popularity, an aspect that remains unexplored is the relationship of DD to its generalization, particularly across uncommon subgroups. That is, how can we ensure that a model trained on the synthetic dataset performs well when faced with samples from regions with low population density? Here, the representativeness and coverage of the dataset become salient over the guaranteed training error at inference. Drawing inspiration from distributionally robust optimization, we introduce an algorithm that combines clustering with the minimization of a risk measure on the loss to conduct DD. We provide a theoretical rationale for our approach and demonstrate its effective generalization and robustness across subgroups through numerical experiments.
Existing learned video compression models employ flow net or deformable convolutional networks (DCN) to estimate motion information. However, the limited receptive fields of flow net and DCN inherently direct their attentiveness towards the local contexts. Global contexts, such as large-scale motions and global correlations among frames are ignored, presenting a significant bottleneck for capturing accurate motions. To address this issue, we propose a joint local and global motion compensation module (LGMC) for leaned video coding. More specifically, we adopt flow net for local motion compensation. To capture global context, we employ the cross attention in feature domain for motion compensation. In addition, to avoid the quadratic complexity of vanilla cross attention, we divide the softmax operations in attention into two independent softmax operations, leading to linear complexity. To validate the effectiveness of our proposed LGMC, we integrate it with DCVC-TCM and obtain learned video compression with joint local and global motion compensation (LVC-LGMC). Extensive experiments demonstrate that our LVC-LGMC has significant rate-distortion performance improvements over baseline DCVC-TCM.
This paper presents a learned video compression method in response to video compression track of the 6th Challenge on Learned Image Compression (CLIC), at DCC 2024.Specifically, we propose a unified contextual video compression framework (UCVC) for joint P-frame and B-frame coding. Each non-intra frame refers to two neighboring decoded frames, which can be either both from the past for P-frame compression, or one from the past and one from the future for B-frame compression. In training stage, the model parameters are jointly optimized with both P-frames and B-frames. Benefiting from the designs, the framework can support both P-frame and B-frame coding and achieve comparable compression efficiency with that specifically designed for P-frame or B-frame.As for challenge submission, we report the optimal compression efficiency by selecting appropriate frame types for each test sequence. Our team name is PKUSZ-LVC.
With the development and popularity of sensors installed in manufacturing systems, complex data are collected during manufacturing processes, which brings challenges for traditional process control methods. This paper proposes a novel process control and monitoring method for the complex structure of high-dimensional image-based overlay errors (modeled in tensor form), which are collected in semiconductor manufacturing processes. The proposed method aims to reduce overlay errors using limited control recipes. We first build a high-dimensional process model and propose different tensor-on-vector regression algorithms to estimate parameters in the model to alleviate the curse of dimensionality. Then, based on the estimate of tensor parameters, the exponentially weighted moving average (EWMA) controller for tensor data is designed whose stability is theoretically guaranteed. Considering the fact that low-dimensional control recipes cannot compensate for all high-dimensional disturbances on the image, control residuals are monitored to prevent significant drifts of uncontrollable high-dimensional disturbances. Through extensive simulations and real case studies, the performances of parameter estimation algorithms and the EWMA controller in tensor space are evaluated. Compared with existing image-based feedback controllers, the superiority of our method is verified especially when disturbances are not stable.
Social relations are leveraged to tackle the sparsity issue of user-item interaction data in recommendation under the assumption of social homophily. However, social recommendation paradigms predominantly focus on homophily based on user preferences. While social information can enhance recommendations, its alignment with user preferences is not guaranteed, thereby posing the risk of introducing informational redundancy. We empirically discover that social graphs in real recommendation data exhibit low preference-aware homophily, which limits the effect of social recommendation models. To comprehensively extract preference-aware homophily information latent in the social graph, we propose Social Heterophily-alleviating Rewiring (SHaRe), a data-centric framework for enhancing existing graph-based social recommendation models. We adopt Graph Rewiring technique to capture and add highly homophilic social relations, and cut low homophilic (or heterophilic) relations. To better refine the user representations from reliable social relations, we integrate a contrastive learning method into the training of SHaRe, aiming to calibrate the user representations for enhancing the result of Graph Rewiring. Experiments on real-world datasets show that the proposed framework not only exhibits enhanced performances across varying homophily ratios but also improves the performance of existing state-of-the-art (SOTA) social recommendation models.