arXiv subjects

Zhanxuan Hu

Publications and source records attributed to Zhanxuan Hu.

9 recordsLinked to original sources

arXiv2026

One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling

Vision-language models (VLMs) enable visual recognition from semantic class descriptions, which makes them attractive when target annotations are scarce or unavailable. Most deployment pipelines, however, first choose a single VLM and then adapt that model to the unlabeled target set. This single-backbone paradigm hides a critical assumption: the selected VLM is already compatible with the target domain. In realistic cross-domain deployment, several general-purpose and domain-specialized VLMs may be plausible, yet no instance-level target labels are available to identify the reliable ones. Deployment therefore requires a coupled solution for model selection, target adaptation, and prediction integration. We revisit this problem from a system-level multi-VLM perspective. Our central observation is that the three decisions above depend on the same latent object: a trustworthy sample-class structure in the target set. Different VLMs may encode different transfer biases and produce conflicting predictions, but their outputs can still provide complementary evidence for estimating this structure. We propose One Stone, Three Birds, a training-free framework based on self-adaptive optimal transport. Given a pool of frozen candidate VLMs, OSTB estimates a consensus sample-to-class transport plan without updating VLM parameters. The learned transport structure is then reused for all deployment objectives: model selection is performed by ranking the combined semantic and visual reliability induced by the consensus plan; target adaptation is obtained by fitting transport-conditioned visual classifiers; and ensembling is implemented through reliability-aware probabilistic integration. Extensive experiments on natural-image, remote-sensing, and medical-pathology benchmarks show that OSTB improves model ranking, adaptation stability, and ensemble robustness under heterogeneous candidate pools.

cs.CV↗

arXiv2026

Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models

Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VFMs learn discriminative perceptual geometry but lack semantic grounding. We propose GPUA (Geometry-Preserving Unsupervised Alignment), a framework that integrates the complementary strengths of VFMs and VLMs. Inspired by cross-lingual alignment, GPUA treats VFM features as a visual language and learns an orthogonal mapping that translates the VFM space into the VLM semantic space, preserving geometry and narrowing the modality gap without labels or model parameter updates. GPUA is task-agnostic and requires only feature-level access to pretrained models. Experiments across diverse benchmarks demonstrate improved cross-model compatibility and strong gains in downstream zero-shot recognition and segmentation with negligible overhead. Code is available at https://github.com/Yuteam14/GPUA

cs.CV↗

arXiv2026

[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation

Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperform on multi-label recognition where multiple objects co-exist. A key bottleneck is that the [CLS] token, as a single global visual representation, is insufficient to faithfully encode diverse targets with varying scales, contexts, and co-occurrence patterns. To address this limitation, we present a new multi-label image recognition framework, termed PIAA, which formulates prediction as Patch-level Inference followed by Adaptive Aggregation. Specifically, we first enhance patch-wise predictions from two complementary perspectives: (i) mitigating semantic entanglement in the visual encoder to obtain more discriminative patch representations, and (ii) learning an unsupervised visual classifier to narrow the vision-language modality gap. We then introduce an adaptive aggregation module that consolidates patch-level scores into the final multi-label prediction. Notably, the entire pipeline is fully training-free, requiring no gradient updates or parameter fine-tuning. Experiments show that our method achieves strong improvements with minimal extra computation, exceeding a 6% mAP gain on the challenging NUS-WIDE benchmark over representative baselines. Code is available at https://github.com/akang-wang/PIAA.

cs.CV↗

arXiv2026

ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation

Training-free open-vocabulary remote sensing segmentation (OVRSS), empowered by vision-language models, has emerged as a promising paradigm for achieving category-agnostic semantic understanding in remote sensing imagery. Existing approaches mainly focus on enhancing feature representations or mitigating modality discrepancies to improve patch-level prediction accuracy. However, such independent prediction schemes are fundamentally misaligned with the intrinsic characteristics of remote sensing data. In real-world applications, remote sensing scenes are typically large-scale and exhibit strong spatial as well as semantic correlations, making isolated patch-wise predictions insufficient for accurate segmentation. To address this limitation, we propose ConInfer, a context-aware inference framework for OVRSS that performs joint prediction across multiple spatial units while explicitly modeling their inter-unit semantic dependencies. By incorporating global contextual cues, our method significantly enhances segmentation consistency, robustness, and generalization in complex remote sensing environments. Extensive experiments on multiple benchmark datasets demonstrate that our approach consistently surpasses state-of-the-art per-pixel VLM-based baselines such as SegEarth-OV, achieving average improvements of 2.80% and 6.13% on open-vocabulary semantic segmentation and object extraction tasks, respectively. The implementation code is available at: https://github.com/Dog-Yang/ConInfer

cs.CV↗

arXiv2026

SOTA: Self-adaptive Optimal Transport for Zero-Shot Classification with Multiple Foundation Models

Foundation models have attracted widespread attention across domains due to their powerful zero-shot classification capabilities. This work is motivated by two key observations: (1) \textit{Vision-Language Models} (VLMs), such as CLIP, often over-rely on class-level textual priors and struggle to capture fine-grained visual cues, whereas \textit{Vision-only Foundation Models} (VFMs), such as DINO, provide rich and discriminative visual features but lack semantic alignment; (2) the performance of different VLMs varies considerably across datasets owing to differences in pre-training. To address these challenges, we propose \textbf{SOTA} (\textit{Self-adaptive Optimal TrAnsport}), a \textit{training-free} ensemble framework that integrates the outputs of multiple foundation models~(VFMs or VLMs) by learning a self-adaptive transport plan. Notably, \textbf{SOTA} is prior-free and automatically balances model contributions. Extensive experiments across diverse domains, including natural images, medical pathology, and remote sensing, validate the generalizability of \textbf{SOTA}. The results consistently show that it effectively leverages the complementary strengths of different foundation models and achieves substantial improvements over individual models. The implementation code is available at: https://github.com/Afleve/self-adaptive-Optimal-Transport.

cs.CV↗

arXiv2025

A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention

Generalized Category Discovery (GCD) aims to classify unlabeled data from both known and unknown categories by leveraging knowledge from labeled known categories. While existing methods have made notable progress, they often overlook a hidden stumbling block in GCD: distracted attention. Specifically, when processing unlabeled data, models tend to focus not only on key objects in the image but also on task-irrelevant background regions, leading to suboptimal feature extraction. To remove this stumbling block, we propose Attention Focusing (AF), an adaptive mechanism designed to sharpen the model's focus by pruning non-informative tokens. AF consists of two simple yet effective components: Token Importance Measurement (TIME) and Token Adaptive Pruning (TAP), working in a cascade. TIME quantifies token importance across multiple scales, while TAP prunes non-informative tokens by utilizing the multi-scale importance scores provided by TIME. AF is a lightweight, plug-and-play module that integrates seamlessly into existing GCD methods with minimal computational overhead. When incorporated into one prominent GCD method, SimGCD, AF achieves up to 15.4% performance improvement over the baseline with minimal computational overhead. The implementation code is provided in https://github.com/Afleve/AFGCD.

cs.CV↗

arXiv2022

Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction

The Dynamic Saliency Prediction (DSP) task simulates the human selective attention mechanism to perceive the dynamic scene, which is significant and imperative in many vision tasks. Most of existing methods only consider visual cues, while neglect the accompanied audio information, which can provide complementary information for the scene understanding. In fact, there exists a strong relation between auditory and visual cues, and humans generally perceive the surrounding scene by collaboratively sensing these cues. Motivated by this, an audio-visual collaborative representation learning method is proposed for the DSP task, which explores the audio modality to better predict the dynamic saliency map by assisting vision modality. The proposed method consists of three parts: 1) audio-visual encoding, 2) audio-visual location, and 3) collaborative integration parts. Firstly, a refined SoundNet architecture is adopted to encode audio modality for obtaining corresponding features, and a modified 3D ResNet-50 architecture is employed to learn visual features, containing both spatial location and temporal motion information. Secondly, an audio-visual location part is devised to locate the sound source in the visual scene by learning the correspondence between audio-visual information. Thirdly, a collaborative integration part is devised to adaptively aggregate audio-visual information and center-bias prior to generate the final saliency map. Extensive experiments are conducted on six challenging audiovisual eye-tracking datasets, including DIEM, AVAD, Coutrot1, Coutrot2, SumMe, and ETMD, which shows significant superiority over state-of-the-art DSP models.

cs.CV↗

arXiv2020

Low Rank Regularization: A Review

Low rank regularization, in essence, involves introducing a low rank or approximately low rank assumption for matrix we aim to learn, which has achieved great success in many fields including machine learning, data mining and computer version. Over the last decade, much progress has been made in theories and practical applications. Nevertheless, the intersection between them is very slight. In order to construct a bridge between practical applications and theoretical research, in this paper we provide a comprehensive survey for low rank regularization. We first review several traditional machine learning models using low rank regularization, and then show their (or their variants) applications in solving practical issues, such as non-rigid structure from motion and image denoising. Subsequently, we summarize the regularizers and optimization methods that achieve great success in traditional machine learning tasks but are rarely seen in solving practical issues. Finally, we provide a discussion and comparison for some representative regularizers including convex and non-convex relaxations. Extensive experimental results demonstrate that non-convex regularizers can provide a large advantage over the nuclear norm, the regularizer widely used in solving practical issues.

cs.CV↗

arXiv2019

An Iteratively Re-weighted Method for Problems with Sparsity-Inducing Norms

This work aims at solving the problems with intractable sparsity-inducing norms that are often encountered in various machine learning tasks, such as multi-task learning, subspace clustering, feature selection, robust principal component analysis, and so on. Specifically, an Iteratively Re-Weighted method (IRW) with solid convergence guarantee is provided. We investigate its convergence speed via numerous experiments on real data. Furthermore, in order to validate the practicality of IRW, we use it to solve a concrete robust feature selection model with complicated objective function. The experimental results show that the model coupled with proposed optimization method outperforms alternative methods significantly.

cs.LG↗