Ziqiang Wang

Haoxiang Zhang, He Jiang, Ziqiang Wang et al.

Zero-Shot Sketch-Based Image Retrieval (ZSSBIR) is an emerging task. The pioneering work focused on the modal gap but ignored inter-class information. Although recent work has begun to consider the triplet-based or contrast-based loss to mine inter-class information, positive and negative samples need to be carefully selected, or the model is prone to lose modality-specific information. To respond to these issues, an Ontology-Aware Network (OAN) is proposed. Specifically, the smooth inter-class independence learning mechanism is put forward to maintain inter-class peculiarity. Meanwhile, distillation-based consistency preservation is utilized to keep modality-specific information. Extensive experiments have demonstrated the superior performance of our algorithm on two challenging Sketchy and Tu-Berlin datasets.

Ziqiang Wang, Zhixiang Chi, Yanan Wu et al.

Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch using self-training loss. While these methods yield commendable results in ideal test data streams, where batches are independently and identically sampled from the target distribution, they falter under more practical test data streams that are not independent and identically distributed (non-i.i.d.). The data batches in a non-i.i.d. stream display prominent label shifts relative to each other. It leads to conflicting optimization objectives among batches during the TTA process. Given the inherent risks of adapting the source model to unpredictable test-time distributions, we reverse the adaptation process and propose a novel Distribution Alignment loss for TTA. This loss guides the distributions of test-time features back towards the source distributions, which ensures compatibility with the well-trained source model and eliminates the pitfalls associated with conflicting optimization objectives. Moreover, we devise a domain shift detection mechanism to extend the success of our proposed TTA method in the continual domain shift scenarios. Our extensive experiments validate the logic and efficacy of our method. On six benchmark datasets, we surpass existing methods in non-i.i.d. scenarios and maintain competitive performance under the ideal i.i.d. assumption.

Houston H. Zhang, Tao Zhang, Baoze Lin et al.

User interface to code (UI2Code) aims to generate executable code that can faithfully reconstruct a given input UI. Prior work focuses largely on web pages and mobile screens, leaving app widgets underexplored. Unlike web or mobile UIs with rich hierarchical context, widgets are compact, context-free micro-interfaces that summarize key information through dense layouts and iconography under strict spatial constraints. Moreover, while (image, code) pairs are widely available for web or mobile UIs, widget designs are proprietary and lack accessible markup. We formalize this setting as the Widget-to-Code (Widget2Code) and introduce an image-only widget benchmark with fine-grained, multi-dimensional evaluation metrics. Benchmarking shows that although generalized multimodal large language models (MLLMs) outperform specialized UI2Code methods, they still produce unreliable and visually inconsistent code. To address these limitations, we develop a baseline that jointly advances perceptual understanding and structured code generation. At the perceptual level, we follow widget design principles to assemble atomic components into complete layouts, equipped with icon retrieval and reusable visualization modules. At the system level, we design an end-to-end infrastructure, WidgetFactory, which includes a framework-agnostic widget-tailored domain-specific language (WidgetDSL) and a compiler that translates it into multiple front-end implementations (e.g., React, HTML/CSS). An adaptive rendering module further refines spatial dimensions to satisfy compactness constraints. Together, these contributions substantially enhance visual fidelity, establishing a strong baseline and unified infrastructure for future Widget2Code research.

Zhongyi Zhang, Guixia Li, Ziqiang Wang et al.

Despite high global prevalence of hepatic steatosis, no automated diagnostics demonstrated generalizability in detecting steatosis on multiple international datasets. Traditionally, hepatic steatosis detection relies on clinicians selecting the region of interest (ROI) on computed tomography (CT) to measure liver attenuation. ROI selection demands time and expertise, and therefore is not routinely performed in populations. To automate the process, we validated an existing artificial intelligence (AI) system for 3D liver segmentation and used it to purpose a novel method: AI-ROI, which could automatically select the ROI for attenuation measurements. AI segmentation and AI-ROI method were evaluated on 1,014 non-contrast enhanced chest CT images from eight international datasets: LIDC-IDRI, NSCLC-Lung1, RIDER, VESSEL12, RICORD-1A, RICORD-1B, COVID-19-Italy, and COVID-19-China. AI segmentation achieved a mean dice coefficient of 0.957. Attenuations measured by AI-ROI showed no significant differences (p = 0.545) and a reduction of 71% time compared to expert measurements. The area under the curve (AUC) of the steatosis classification of AI-ROI is 0.921 (95% CI: 0.883 - 0.959). If performed as a routine screening method, our AI protocol could potentially allow early non-invasive, non-pharmacological preventative interventions for hepatic steatosis. 1,014 expert-annotated liver segmentations of patients with hepatic steatosis annotations can be downloaded here: https://drive.google.com/drive/folders/1-g_zJeAaZXYXGqL1OeF6pUjr6KB0igJX.

Li Gu, Zihuan Jiang, Zhixiang Chi et al.

Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train vision-language-model(VLM) agents in interactive environments with a primary focus on performance, generalization remains underexplored due to the lack of standardized benchmarks and open-source RL systems. In this work, we formalize the problem as a Contextual Markov Decision Process (CMDP) and introduce \textbf{AndroidWorld-Generalization}, a benchmark with three increasingly challenging regimes for evaluating zero-shot generalization to unseen task instances, templates, and applications. We further propose an RL training system that integrates Group Relative Policy Optimization (GRPO) with a scalable rollout collection system, consisting of containerized infrastructure and asynchronous execution % , and error recovery to support reliable and efficient training. Experiments on AndroidWorld-Generalization show that RL enables a 7B-parameter VLM agent to surpass supervised fine-tuning baselines, yielding a 26.1\% improvement on unseen instances but only limited gains on unseen templates (15.7\%) and apps (8.3\%), underscoring the challenges of generalization. As a preliminary step, we demonstrate that few-shot adaptation at test-time improves performance on unseen apps, motivating future research in this direction. To support reproducibility and fair comparison, we open-source the full RL training system, including the environment, task suite, models, prompt configurations, and the underlying infrastructure \footnote{https://github.com/zihuanjiang/AndroidWorld-Generalization}.

Yonghao Zhao, Changtao Li, Chi Shu et al.

Survival prognosis is crucial for medical informatics. Practitioners often confront small-sized clinical data, especially cancer patient cases, which can be insufficient to induce useful patterns for survival predictions. This study deals with small sample survival analysis by leveraging transfer learning, a useful machine learning technique that can enhance the target analysis with related knowledge pre-learned from other data. We propose and develop various transfer learning methods designed for common survival models. For parametric models such as DeepSurv, Cox-CC (Cox-based neural networks), and DeepHit (end-to-end deep learning model), we apply standard transfer learning techniques like pretraining and fine-tuning. For non-parametric models such as Random Survival Forest, we propose a new transfer survival forest (TSF) model that transfers tree structures from source tasks and fine-tunes them with target data. We evaluated the transfer learning methods on colorectal cancer (CRC) prognosis. The source data are 27,379 SEER CRC stage I patients, and the target data are 728 CRC stage I patients from the West China Hospital. When enhanced by transfer learning, Cox-CC's $C^{td}$ value was boosted from 0.7868 to 0.8111, DeepHit's from 0.8085 to 0.8135, DeepSurv's from 0.7722 to 0.8043, and RSF's from 0.7940 to 0.8297 (the highest performance). All models trained with data as small as 50 demonstrated even more significant improvement. Conclusions: Therefore, the current survival models used for cancer prognosis can be enhanced and improved by properly designed transfer learning techniques. The source code used in this study is available at https://github.com/YonghaoZhao722/TSF.

Zhixiang Chi, Li Gu, Huan Liu et al.

Few-shot Test-Time Domain Adaptation focuses on adapting a model at test time to a specific domain using only a few unlabeled examples, addressing domain shift. Prior methods leverage CLIP's strong out-of-distribution (OOD) abilities by generating domain-specific prompts to guide its generalized, frozen features. However, since downstream datasets are not explicitly seen by CLIP, solely depending on the feature space knowledge is constrained by CLIP's prior knowledge. Notably, when using a less robust backbone like ViT-B/16, performance significantly drops on challenging real-world benchmarks. Departing from the state-of-the-art of inheriting the intrinsic OOD capability of CLIP, this work introduces learning directly on the input space to complement the dataset-specific knowledge for frozen CLIP. Specifically, an independent side branch is attached in parallel with CLIP and enforced to learn exclusive knowledge via revert attention. To better capture the dataset-specific label semantics for downstream adaptation, we propose to enhance the inter-dispersion among text features via greedy text ensemble and refinement. The text and visual features are then progressively fused in a domain-aware manner by a generated domain prompt to adapt toward a specific domain. Extensive experiments show our method's superiority on 5 large-scale benchmarks (WILDS and DomainNet), notably improving over smaller networks like ViT-B/16 with gains of \textbf{+5.1} in F1 for iWildCam and \textbf{+3.1\%} in WC Acc for FMoW.

Wenhao Gu, Li Gu, Ziqiang Wang et al.

Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder~(MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets.

Linlian Jiang, Rui Ma, Li Gu et al.

Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during training, limiting their ability to adapt to novel structural patterns and sensor-induced distortions at test time. To address this limitation, we propose PointMAC, a meta-learned framework for robust test-time adaptation in point cloud completion. It enables sample-specific refinement without requiring additional supervision. Our method optimizes the completion model under two self-supervised auxiliary objectives that simulate structural and sensor-level incompleteness. A meta-auxiliary learning strategy based on Model-Agnostic Meta-Learning (MAML) ensures that adaptation driven by auxiliary objectives is consistently aligned with the primary completion task. During inference, we adapt the shared encoder on-the-fly by optimizing auxiliary losses, with the decoder kept fixed. To further stabilize adaptation, we introduce Adaptive $λ$-Calibration, a meta-learned mechanism for balancing gradients between primary and auxiliary objectives. Extensive experiments on synthetic, simulated, and real-world datasets demonstrate that PointMAC achieves state-of-the-art results by refining each sample individually to produce high-quality completions. To the best of our knowledge, this is the first work to apply meta-auxiliary test-time adaptation to point cloud completion.

Zhixiang Chi, Yanan Wu, Li Gu et al.

CLIP exhibits strong visual-textual alignment but struggle with open-vocabulary segmentation due to poor localization. Prior methods enhance spatial coherence by modifying intermediate attention. But, this coherence isn't consistently propagated to the final output due to subsequent operations such as projections. Additionally, intermediate attention lacks direct interaction with text representations, such semantic discrepancy limits the full potential of CLIP. In this work, we propose a training-free, feedback-driven self-adaptive framework that adapts output-based patch-level correspondences back to the intermediate attention. The output predictions, being the culmination of the model's processing, encapsulate the most comprehensive visual and textual semantics about each patch. Our approach enhances semantic consistency between internal representations and final predictions by leveraging the model's outputs as a stronger spatial coherence prior. We design key modules, including attention isolation, confidence-based pruning for sparse adaptation, and adaptation ensemble, to effectively feedback the output coherence cues. Our method functions as a plug-in module, seamlessly integrating into four state-of-the-art approaches with three backbones (ViT-B, ViT-L, ViT-H). We further validate our framework across multiple attention types (Q-K, self-self, and Proxy augmented with MAE, SAM, and DINO). Our approach consistently improves their performance across eight benchmarks.

Ziqiang Wang, Zhi Liu, Gongyang Li et al.

3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed local spacetime according to its kernel size, while human attention is always attracted by relational visual features at different time. To overcome this limitation, we propose a novel Spatio-Temporal Self-Attention 3D Network (STSANet) for video saliency prediction, in which multiple Spatio-Temporal Self-Attention (STSA) modules are employed at different levels of 3D convolutional backbone to directly capture long-range relations between spatio-temporal features of different time steps. Besides, we propose an Attentional Multi-Scale Fusion (AMSF) module to integrate multi-level features with the perception of context in semantic and spatio-temporal subspaces. Extensive experiments demonstrate the contributions of key components of our method, and the results on DHF1K, Hollywood-2, UCF, and DIEM benchmark datasets clearly prove the superiority of the proposed model compared with all state-of-the-art models.

Ziqiang Wang, Hegen Xu, Youwen Wan

Warehouse logistics robots will work in different warehouse environments. In order to enable robots to perceive environment and plan path faster without modifying existing warehouses, we uses monocular camera to achieve an efficient robot integrated system. Mapping and path planning the two main tasks presented in this paper. The direct method visual odometry is applied to localize, and the 3D position of major obstacles in the environment is calculated. We describe the terrain with occupied grid map, the 3D points are projected onto the robot motion plane, thus accessibility of each grid is determined. Based on the terrain information, the optimized A* algorithm is used for path planning. Finally, according to localization and planning, we control the robot to track path. We also develop a path-tracking robot prototype. Simulation and experimental results verify the effectiveness and reliability of the proposed method.