arXiv subjects

Fangyong Wang

Publications and source records attributed to Fangyong Wang.

6 recordsLinked to original sources

arXiv2026

Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation

Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that existing methods possess pixel-level vision-language alignment capability. Typically, this capability involves computing the cosine similarity, \ie, logits, between visual and linguistic features, and minimizing the distribution discrepancy between the logits and the ground truth (GT) to generate optimal logits that are subsequently used to construct segmentation maps, yet it depends on time-consuming iterative training or model-specific attention modulation. In this work, we propose a more direct approach that eschews the logits-optimization process by directly deriving an analytic solution for the segmentation map. We posit a key hypothesis: the distribution discrepancy encodes semantic information; specifically, this discrepancy exhibits consistency across patches belonging to the same category but inconsistency across different categories. Based on this hypothesis, we directly utilize the analytic solution of this distribution discrepancy as the semantic maps. In other words, we reformulate the optimization of the distribution discrepancy as deriving its analytic solution, thereby eliminating time-consuming iterative training, freeing us from model-specific attention modulation, and achieving state-of-the-art performance on eight benchmark datasets.

cs.CV↗

arXiv2026

PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation

3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentation (3DRES). While existing methods achieve high accuracy in simple, single-object scenes, they suffer from severe performance degradation in complex, multi-object scenes that are common in real-world settings, hindering practical deployment. Existing methods face two key challenges in complex, multi-object scenes: inadequate parsing of implicit localization cues critical for disambiguating visually similar objects, and ineffective suppression of dynamic spatial interference from co-occurring objects, resulting in degraded grounding accuracy. To address these challenges, we propose PC-CrossDiff, a unified dual-task framework with a dual-level cross-modal differential attention architecture for 3DREC and 3DRES. Specifically, the framework introduces: (i) Point-Level Differential Attention (PLDA) modules that apply bidirectional differential attention between text and point clouds, adaptively extracting implicit localization cues via learnable weights to improve discriminative representation; (ii) Cluster-Level Differential Attention (CLDA) modules that establish a hierarchical attention mechanism to adaptively enhance localization-relevant spatial relationships while suppressing ambiguous or irrelevant spatial relations through a localization-aware differential attention block. Our method achieves state-of-the-art performance on the ScanRefer, NR3D, and SR3D benchmarks. Notably, on the Implicit subsets of ScanRefer, it improves the Overall@0.50 score by +10.16% for the 3DREC task, highlighting its strong ability to parse implicit spatial cues.

cs.CV↗

arXiv2025

Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective

Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhancing the multimodal dense prediction capability, specifically this pixel-level multimodal alignment. Although existing methods achieve promising results by leveraging CLIP's vision-language alignment, they rarely investigate the performance boundaries of CLIP for dense prediction from an interpretability mechanisms perspective. In this work, we systematically investigate CLIP's internal mechanisms and identify a critical phenomenon: analogous to human distraction, CLIP diverts significant attention resources from target regions to irrelevant tokens. Our analysis reveals that these tokens arise from dimension-specific over-activation; filtering them enhances CLIP's dense prediction performance. Consequently, we propose ReFocusing CLIP (RF-CLIP), a training-free approach that emulates human distraction-refocusing behavior to redirect attention from distraction tokens back to target regions, thereby refining CLIP's multimodal alignment granularity. Our method achieves SOTA performance on eight benchmarks while maintaining high inference efficiency.

cs.CV↗

arXiv2025

Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation

Open-vocabulary semantic segmentation (OVSS) conducts pixel-level classification via text-driven alignment, where the domain discrepancy between base category training and open-vocabulary inference poses challenges in discriminative modeling of latent unseen category. To address this challenge, existing vision-language model (VLM)-based approaches demonstrate commendable performance through pre-trained multi-modal representations. However, the fundamental mechanisms of latent semantic comprehension remain underexplored, making the bottleneck for OVSS. In this work, we initiate a probing experiment to explore distribution patterns and dynamics of latent semantics in VLMs under inductive learning paradigms. Building on these insights, we propose X-Agent, an innovative OVSS framework employing latent semantic-aware ``agent'' to orchestrate cross-modal attention mechanisms, simultaneously optimizing latent semantic dynamic and amplifying its perceptibility. Extensive benchmark evaluations demonstrate that X-Agent achieves state-of-the-art performance while effectively enhancing the latent semantic saliency.

cs.CV↗

arXiv2025

Joint Multitarget Detection and Tracking with mmWave Radar

Accurate targets detection and tracking with mmWave radar is a key sensing capability that will enable more intelligent systems, create smart, efficient, automated system. This paper proposes an end-to-end detection-estimation-track framework named MNOMP-SPA-KF consisting of the target detection and estimation module, the data association (DA) module and the target tracking module. In the target estimation and detection module, a low complexity, super-resolution and constant false alarm rate (CFAR) based two dimensional multisnapshot Newtonalized orthogonal matching pursuit (2D-MNOMP) is designed to extract the multitarget's radial distances and velocities, followed by the conventional (Bartlett) beamformer to extract the multitarget's azimuths. In the DA module, a sum product algorithm (SPA) is adopted to obtain the association probabilities of the existed targets and measurements by incorporating the radial velocity information. The Kalman filter (KF) is implemented to perform target tracking in the target tracking module by exploiting the asymptotic distribution of the estimators. To improve the detection probability of the weak targets, extrapolation is also coupled into the MNOMP-SPA-KF. Numerical and real data experiments demonstrate the effectiveness of the MNOMP-SPA-KF algorithm, compared to other benchmark algorithms.

eess.SP↗

arXiv2024

DM-SBL: Channel Estimation under Structured Interference

Channel estimation is a fundamental task in communication systems and is critical for effective demodulation. While most works deal with a simple scenario where the measurements are corrupted by the additive white Gaussian noise (AWGN), this work addresses the more challenging scenario where both AWGN and structured interference coexist. Such conditions arise, for example, when a sonar/radar transmitter and a communication receiver operate simultaneously within the same bandwidth. To ensure accurate channel estimation in these scenarios, the sparsity of the channel in the delay domain and the complicate structure of the interference are jointly exploited. Firstly, the score of the structured interference is learned via a neural network based on the diffusion model (DM), while the channel prior is modeled as a Gaussian distribution, with its variance controlling channel sparsity, similar to the setup of the sparse Bayesian learning (SBL). Then, two efficient posterior sampling methods are proposed to jointly estimate the sparse channel and the interference. Nuisance parameters, such as the variance of the prior are estimated via the expectation maximization (EM) algorithm. The proposed method is termed as DM based SBL (DM-SBL). Numerical simulations demonstrate that DM-SBL significantly outperforms conventional approaches that deal with the AWGN scenario, particularly under low signal-to-interference ratio (SIR) conditions. Beyond channel estimation, DM-SBL also shows promise for addressing other linear inverse problems involving structured interference.

eess.SP↗