Camouflaged object detection focuses on the challenge of segmenting objects that visually blend into their background. The effectiveness of camouflage strategies hinges on how well objects interact with their background to minimize their visibility. Based on this insight, we propose a novel Foreground-Background Interactive Learning Network (FBINet), which independently decouples foreground and background information, and facilitates bi-directional interactions. This allows the network to progressively complement each other, leading to high-quality predictions with clear boundaries. To the best of our knowledge, this is the first attempt to tackle the camouflaged object detection task through interactive learning between foreground and background, which not only better reveals camouflage patterns but also offers a new perspective in this field. Experimental results on three datasets demonstrate that our proposed FBINet outperforms current state-of-the-art methods in performance while maintaining a low computational cost, making it applicable for real-world scenarios. The code will be available at https://github.com/bbdjj/FBINet.

Benign overfitting refers to the phenomenon where an over-parameterized model fits the training data perfectly, including noise in the data, but still generalizes well to the unseen test data. While prior work provides some theoretical understanding of this phenomenon under the in-distribution setup, modern machine learning often operates in a more challenging Out-of-Distribution (OOD) regime, where the target (test) distribution can be rather different from the source (training) distribution. In this work, we take an initial step towards understanding benign overfitting in the OOD regime by focusing on the basic setup of over-parameterized linear models under covariate shift. We provide non-asymptotic guarantees proving that benign overfitting occurs in standard ridge regression, even under the OOD regime when the target covariance satisfies certain structural conditions. We identify several vital quantities relating to source and target covariance, which govern the performance of OOD generalization. Our result is sharp, which provably recovers prior in-distribution benign overfitting guarantee (Tsigler & Bartlett, 2023), as well as under-parameterized OOD guarantee (Ge et al., 2024) when specializing to each setup. Moreover, we also present theoretical results for a more general family of target covariance matrix, where standard ridge regression only achieves a slow statistical rate of $\mathcal{O}(1/\sqrt{n})$ for the excess risk, while Principal Component Regression (PCR) is guaranteed to achieve the fast rate $\mathcal{O}(1/n)$, where $n$ is the number of samples.

Conformal prediction is a powerful distribution-free framework for constructing prediction sets with coverage guarantees. Classical methods, such as split conformal prediction, provide marginal coverage, ensuring that the prediction set contains the label of a random test point with a target probability. However, these guarantees may not hold uniformly across different subpopulations, leading to disparities in coverage. Prior work has explored coverage guarantees conditioned on events related to the covariates and label of the test point. We present Kandinsky conformal prediction, a framework that significantly expands the scope of conditional coverage guarantees. In contrast to Mondrian conformal prediction, which restricts its coverage guarantees to disjoint groups—reminiscent of the rigid, structured grids of Piet Mondrian’s art—our framework flexibly handles overlapping and fractional group memberships defined jointly on covariates and labels, reflecting the layered, intersecting forms in Wassily Kandinsky’s compositions. Our algorithm unifies and extends existing methods, encompassing covariate-based group conditional, class conditional, and Mondrian conformal prediction as special cases, while achieving a minimax-optimal high-probability conditional coverage bound. Finally, we demonstrate the practicality of our approach through empirical evaluation on real-world datasets.

Graph Neural Networks (GNNs) are widely used for node classification tasks but often fail to generalize when training and test nodes come from different distributions, limiting their practicality. To address this challenge, recent approaches have adopted invariant learning and sample reweighting techniques from the out-of-distribution (OOD) generalization field. However, invariant learning-based methods face difficulties when applied to graph data, as they rely on the impractical assumption of obtaining real environment labels and strict invariance, which may not hold in real-world graph structures. Moreover, current sample reweighting methods tend to overlook topological information, potentially leading to suboptimal results. In this work, we introduce the Topology-Aware Dynamic Reweighting (TAR) framework to address distribution shifts by leveraging the inherent graph structure. TAR dynamically adjusts sample weights through gradient flow on the graph edges during training. Instead of relying on strict invariance assumptions, we theoretically prove that our method is able to provide distributional robustness, thereby enhancing the out-of-distribution generalization performance on graph data. Our framework's superiority is demonstrated through standard testing on extensive node classification OOD datasets, exhibiting marked improvements over existing methods.

RGB-Thermal salient object detection (RGB-T SOD) aims to identify and segment visually prominent objects by leveraging complementary information from RGB and thermal modalities. A key challenge lies in exploiting both the uniqueness and shared characteristics of these modalities to enhance their collaboration. Existing methods often ignore the optimization of unimodal features and the level-specific modality discrepancy, leading to noisy and redundant multi-modal feature representations. To address these limitations, we propose a novel RGB-T SOD network, HEFNet, which employs hierarchical unimodal enhancement and multi-modal fusion to achieve precise segmentation. Specifically, we introduce the unimodal feature enhancement (UFE) module, which refines RGB and thermal features by incorporating complementary information from adjacent levels, thereby enhancing saliency cues and suppressing noise distractions. Additionally, the hierarchical multi-modal fusion (HMF) module is designed to generate robust cross-modal feature representation. By employing tailored refinement and fusion strategies within the UFE and HMF modules, our network fully exploits the strengths of each modality, facilitating the generation of discriminative cross-modal features. Finally, the multi-level feature integration (MFI) module is introduced to progressively aggregate features across levels to ensure accurate saliency predictions. Extensive experiments demonstrate that our method achieves state-of-the-art performance, verifying its effectiveness and superiority over existing RGB-T SOD approaches. Our results are available at https://github.com/ZhangQing0329/HEFNet

Camouflaged Object Detection (COD) aims to identify objects that blend seamlessly into their surroundings. The inherent visual complexity of camouflaged objects, including their low contrast with the background, diverse textures, and subtle appearance variations, often obscures semantic cues, making accurate segmentation highly challenging. Existing methods primarily rely on visual features, which are insufficient to handle the variability and intricacy of camouflaged objects, leading to unstable object perception capability and ambiguous segmentation results. To tackle these limitations, we introduce a novel COD task, class-guided camouflaged object detection (CGCOD), which extends the conventional COD task by incorporating object-specific class knowledge to enhance detection robustness and accuracy. To facilitate this task, we present a new dataset, CamoClass, comprising camouflaged objects with class annotations. Furthermore, we propose a multi-stage framework, CGNet, which incorporates a plug-and-play class prompt generator and a simple yet effective class-guided detector. This establishes a new paradigm for COD, bridging the gap between contextual understanding and class-guided detection. Extensive experimental results demonstrate the effectiveness of our flexible framework in improving the performance of proposed and existing detectors by leveraging class-level textual information. The Camoclass dataset and the corresponding source code will be made publicly available upon acceptance at: https://github.com/bbdjj/CGCOD.

Recommendation systems are frequently challenged by pervasive biases in the training set that can compromise model effectiveness. To address this issue, various debiasing techniques have been developed to eliminate biases and produce debiased models. However, when encountering varying test environments, some data patterns manifested by the training data could be beneficial to the model’s performance. Completely removing biases may overlook the beneficial data patterns and consequently diminish recommendation accuracy. Thus, it is crucial to carefully integrate certain biases to optimize performance, while the ideal level of bias integration is highly dependent on the test environment. Moreover, these systems operate in dynamic scenarios where the test environments could vary, necessitating an adaptive integration strategy customized to the environment. Our research establishes that discrepancies in predictions of models can guide the selection of the most fitting model for specific situations. Building on this understanding, we present AdaptSel, a pioneering method for the adaptive selection of the superior model during the testing phase. Empirical evaluations substantiate the foundational assumptions of AdaptSel, accentuating its effectiveness in adaptively selecting the most suitable model for varying test environments.

Enhancing the stability of machine learning algorithms under distributional shifts is at the heart of the Out-of-Distribution (OOD) Generalization problem. Derived from causal learning, recent works of invariant learning pursue strict invariance with multiple training environments. Although intuitively reasonable, strong assumptions on the availability and quality of environments are made to learn the strict invariance property. In this work, we come up with the “distributional stability" notion to mitigate such limitations. It quantifies the stability of prediction mechanisms among sub-populations down to a prescribed scale. Based on this, we propose the learnability assumption and derive the generalization error bound under distribution shifts. Inspired by theoretical analyses, we propose our novel stable risk minimization (SRM) algorithm to enhance the model’s stability w.r.t. shifts in prediction mechanisms (Y|X-shifts). Experimental results are consistent with our intuition and validate the effectiveness of our algorithm. The code can be found at https://github.com/LJSthu/SRM.

Machine learning algorithms minimizing average risk are susceptible to distributional shifts. Distributionally Robust Optimization (DRO) addresses this issue by optimizing the worst-case risk within an uncertainty set. However, DRO suffers from over-pessimism, leading to low-confidence predictions, poor parameter estimations as well as poor generalization. In this work, we conduct a theoretical analysis of a probable root cause of over-pessimism: excessive focus on noisy samples. To alleviate the impact of noise, we incorporate data geometry into calibration terms in DRO, resulting in our novel Geometry-Calibrated DRO (GCDRO) for regression. We establish the connection between our risk objective and the Helmholtz free energy in statistical physics, and this free-energy-based risk can extend to standard DRO methods. Leveraging gradient flow in Wasserstein space, we develop an approximate minimax optimization algorithm with a bounded error ratio and elucidate how our approach mitigates noisy sample effects. Comprehensive experiments confirm GCDRO’s superiority over conventional DRO methods.

We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration, a criterion that ensures a predictor is calibrated across a family of overlapping groups. Multicalibration is shown to be associated with robustness of statistical inference under covariate shift. We further establish a link between multicalibration and robustness for prediction tasks both under and beyond covariate shift. We accomplish this by extending multicalibration to incorporate grouping functions that consider covariates and labels jointly. This leads to an equivalence of the extended multicalibration and invariance, an objective for robust learning in existence of concept shift. We show a linear structure of the grouping function class spanned by density ratios, resulting in a unifying framework for robust learning by designing specific grouping functions. We propose MC-Pseudolabel, a post-processing algorithm to achieve both extended multicalibration and out-of-distribution generalization. The algorithm, with lightweight hyperparameters and optimization through a series of supervised regression steps, achieves superior performance on real-world datasets with distribution shift.

Distributionally Robust Optimization (DRO) serves as a robust alternative to empirical risk minimization (ERM), which optimizes the worst-case distribution in an uncertainty set typically specified by distance metrics including $f$-divergence and the Wasserstein distance. The metrics defined in the ostensible high dimensional space lead to exceedingly large uncertainty sets, resulting in the underperformance of most existing DRO methods. It has been well documented that high dimensional data approximately resides on low dimensional manifolds. In this work, to further constrain the uncertainty set, we incorporate data geometric properties into the design of distance metrics, obtaining our novel Geometric Wasserstein DRO (GDRO). Empowered by Gradient Flow, we derive a generically applicable approximate algorithm for the optimization of GDRO, and provide the bounded error rate of the approximation as well as the convergence rate of our algorithm. We also theoretically characterize the edge cases where certain existing DRO methods are the degeneracy of GDRO. Extensive experiments justify the superiority of our GDRO to existing DRO methods in multiple settings with strong distributional shifts, and confirm that the uncertainty set of GDRO adapts to data geometry.

The detection of object regions based on local saliency has been with great interest in computer vision for its potential contributions to applications, such as recognition, because objects of interest could be contained in salient regions. However, regions are extracted from local salient locations by simple procedures without the global inference, resulting in poor segmentation of possible objects. In this paper, a two-strategy has been proposed to introduce local saliency into foreground subtraction, a color grouping method. By using only color information and no prior higher level knowledge about objects and scenes, multiple foreground regions are extracted simultaneously according to visual attention based salient locations. The prominence score is defined to further evaluate these regions for their possibility to contain objects of interest.

This work provides a convergence analysis for the estimate error covariance of Kalman filtering based on quantized measurement innovations (QIKF). By taking the quantization errors as random perturbations in observation system, an equivalent state-observation system is given. Accordingly, the quantitative Kalman filter for the original system is equivalent to a Kalman-like filtering for the equivalent state-observation system. In this performance analysis framework, the true covariance matrix of estimating error is strictly analyzed without Gaussian assumption on predicted distribution. A necessary and sufficient condition for the stability of the QIKF is obtained. Then, the relationship between the standard Kalman filtering and the QIKF for the original system is discussed. Finally, the validity of these results are demonstrated by numerical simulations.