Foundational to the Chinese language and culture, Chinese characters encompass extraordinarily extensive and ever-expanding categories, with the latest Chinese GB18030-2022 standard containing 87,887 categories. The accurate recognition of this vast number of characters, termed mega-category recognition, presents a formidable yet crucial challenge for cultural heritage preservation and digital applications. Despite significant advances in Optical Character Recognition (OCR), mega-category recognition remains unexplored due to the absence of comprehensive datasets, with the largest existing dataset containing merely 16,151 categories. To bridge this critical gap, we introduce MegaHan97K, a mega-category, large-scale dataset covering an unprecedented 97,455 categories of Chinese characters. Our work offers three major contributions: (1) MegaHan97K is the first dataset to fully support the latest GB18030-2022 standard, providing at least six times more categories than existing datasets; (2) It effectively addresses the long-tail distribution problem by providing balanced samples across all categories through its three distinct subsets: handwritten, historical and synthetic subsets; (3) Comprehensive benchmarking experiments reveal new challenges in mega-category scenarios, including increased storage demands, morphologically similar character recognition, and zero-shot learning difficulties, while also unlocking substantial opportunities for future research. To the best of our knowledge, the MetaHan97K is likely the dataset with the largest classes not only in the field of OCR but may also in the broader domain of pattern recognition. The dataset is available at https://github.com/SCUT-DLVCLab/MegaHan97K.
Classifying geospatial imagery remains a major bottleneck for applications such as disaster response and land-use monitoring-particularly in regions where annotated data is scarce or unavailable. Existing tools (e.g., RS-CLIP) that claim zero-shot classification capabilities for satellite imagery nonetheless rely on task-specific pretraining and adaptation to reach competitive performance. We introduce GeoVision Labeler (GVL), a strictly zero-shot classification framework: a vision Large Language Model (vLLM) generates rich, human-readable image descriptions, which are then mapped to user-defined classes by a conventional Large Language Model (LLM). This modular, and interpretable pipeline enables flexible image classification for a large range of use cases. We evaluated GVL across three benchmarks-SpaceNet v7, UC Merced, and RESISC45. It achieves up to 93.2% zero-shot accuracy on the binary Buildings vs. No Buildings task on SpaceNet v7. For complex multi-class classification tasks (UC Merced, RESISC45), we implemented a recursive LLM-driven clustering to form meta-classes at successive depths, followed by hierarchical classification-first resolving coarse groups, then finer distinctions-to deliver competitive zero-shot performance. GVL is open-sourced at https://github.com/microsoft/geo-vision-labeler to catalyze adoption in real-world geospatial workflows.
We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained by fixed image resolutions and limited context, which can hinder their effectiveness in retrieval tasks that require fine-grained cross-modal understanding. DCLIP addresses these challenges through a meta teacher-student distillation framework, where a cross-modal transformer teacher is fine-tuned to produce enriched embeddings via bidirectional cross-attention between YOLO-extracted image regions and corresponding textual spans. These semantically and spatially aligned global representations guide the training of a lightweight student model using a hybrid loss that combines contrastive learning and cosine similarity objectives. Despite being trained on only ~67,500 samples curated from MSCOCO, Flickr30k, and Conceptual Captions-just a fraction of CLIP's original dataset-DCLIP significantly improves image-text retrieval metrics (Recall@K, MAP), while retaining approximately 94% of CLIP's zero-shot classification performance. These results demonstrate that DCLIP effectively mitigates the trade-off between task specialization and generalization, offering a resource-efficient, domain-adaptive, and detail-sensitive solution for advanced vision-language tasks. Code available at https://anonymous.4open.science/r/DCLIP-B772/README.md.
Audio-visual zero-shot learning (ZSL) has been extensively researched for its capability to classify video data from unseen classes during training. Nevertheless, current methodologies often struggle with background scene biases and inadequate motion detail. This paper proposes a novel dual-stream Multi-Timescale Motion-Decoupled Spiking Transformer (MDST++), which decouples contextual semantic information and sparse dynamic motion information. The recurrent joint learning unit is proposed to extract contextual semantic information and capture joint knowledge across various modalities to understand the environment of actions. By converting RGB images to events, our method captures motion information more accurately and mitigates background scene biases. Moreover, we introduce a discrepancy analysis block to model audio motion information. To enhance the robustness of SNNs in extracting temporal and motion cues, we dynamically adjust the threshold of Leaky Integrate-and-Fire neurons based on global motion and contextual semantic information. Our experiments validate the effectiveness of MDST++, demonstrating their consistent superiority over state-of-the-art methods on mainstream benchmarks. Additionally, incorporating motion and multi-timescale information significantly improves HM and ZSL accuracy by 26.2\% and 39.9\%.
Contrastive Language-Image Pretraining (CLIP) has demonstrated strong zero-shot performance across diverse downstream text-image tasks. Existing CLIP methods typically optimize a contrastive objective using negative samples drawn from each minibatch. To achieve robust representation learning, these methods require extremely large batch sizes and escalate computational demands to hundreds or even thousands of GPUs. Prior approaches to mitigate this issue often compromise downstream performance, prolong training duration, or face scalability challenges with very large datasets. To overcome these limitations, we propose AmorLIP, an efficient CLIP pretraining framework that amortizes expensive computations involved in contrastive learning through lightweight neural networks, which substantially improves training efficiency and performance. Leveraging insights from a spectral factorization of energy-based models, we introduce novel amortization objectives along with practical techniques to improve training stability. Extensive experiments across 38 downstream tasks demonstrate the superior zero-shot classification and retrieval capabilities of AmorLIP, consistently outperforming standard CLIP baselines with substantial relative improvements of up to 12.24%.
This paper presents a novel method for monocular patient-to-image intraoperative registration, specifically designed to operate without any external hardware tracking equipment or fiducial point markers. Leveraging a synthetic microscopy surgical scene dataset with a wide range of transformations, our approach directly maps preoperative CT scans to 2D intraoperative surgical frames through a lightweight neural network for real-time cochlear implant surgery guidance via a zero-shot learning approach. Unlike traditional methods, our framework seamlessly integrates with monocular surgical microscopes, making it highly practical for clinical use without additional hardware dependencies and requirements. Our method estimates camera poses, which include a rotation matrix and a translation vector, by learning from the synthetic dataset, enabling accurate and efficient intraoperative registration. The proposed framework was evaluated on nine clinical cases using a patient-specific and cross-patient validation strategy. Our results suggest that our approach achieves clinically relevant accuracy in predicting 6D camera poses for registering 3D preoperative CT scans to 2D surgical scenes with an angular error within 10 degrees in most cases, while also addressing limitations of traditional methods, such as reliance on external tracking systems or fiducial markers.
Batteries are essential for various applications, including electric vehicles and renewable energy storage, making safety and efficiency critical concerns. Anomaly detection in battery thermal images helps identify failures early, but traditional deep learning methods require extensive labeled data, which is difficult to obtain, especially for anomalies due to safety risks and high data collection costs. To overcome this, we explore zero-shot anomaly detection using Visual Question Answering (VQA) models, which leverage pretrained knowledge and textbased prompts to generalize across vision tasks. By incorporating prior knowledge of normal battery thermal behavior, we design prompts to detect anomalies without battery-specific training data. We evaluate three VQA models (ChatGPT-4o, LLaVa-13b, and BLIP-2) analyzing their robustness to prompt variations, repeated trials, and qualitative outputs. Despite the lack of finetuning on battery data, our approach demonstrates competitive performance compared to state-of-the-art models that are trained with the battery data. Our findings highlight the potential of VQA-based zero-shot learning for battery anomaly detection and suggest future directions for improving its effectiveness.
We present CrypticBio, the largest publicly available multimodal dataset of visually confusing species, specifically curated to support the development of AI models in the context of biodiversity applications. Visually confusing or cryptic species are groups of two or more taxa that are nearly indistinguishable based on visual characteristics alone. While much existing work addresses taxonomic identification in a broad sense, datasets that directly address the morphological confusion of cryptic species are small, manually curated, and target only a single taxon. Thus, the challenge of identifying such subtle differences in a wide range of taxa remains unaddressed. Curated from real-world trends in species misidentification among community annotators of iNaturalist, CrypticBio contains 52K unique cryptic groups spanning 67K species, represented in 166 million images. Rich research-grade image annotations--including scientific, multicultural, and multilingual species terminology, hierarchical taxonomy, spatiotemporal context, and associated cryptic groups--address multimodal AI in biodiversity research. For easy dataset curation, we provide an open-source pipeline CrypticBio-Curate. The multimodal nature of the dataset beyond vision-language arises from the integration of geographical and temporal data as complementary cues to identifying cryptic species. To highlight the importance of the dataset, we benchmark a suite of state-of-the-art foundation models across CrypticBio subsets of common, unseen, endangered, and invasive species, and demonstrate the substantial impact of geographical context on vision-language zero-shot learning for cryptic species. By introducing CrypticBio, we aim to catalyze progress toward real-world-ready biodiversity AI models capable of handling the nuanced challenges of species ambiguity.
One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet crucial problem due to its ability to generalize knowledge to unseen classes from just one human-annotated image. In this paper, we introduce a transductive one-shot learning approach that employs subspace decomposition to utilize the information from labeled images in the support set and unlabeled images in the query set. These images are decomposed into a linear combination of latent variables representing primitives captured by smaller subspaces. By representing images in the query set as linear combinations of these latent primitives, we can propagate the label from a single image in the support set to query images that share similar combinations of primitives. Through a comprehensive quantitative analysis across various neural network feature extractors and datasets, we demonstrate that our approach can effectively generalize to novel classes from just one labeled image.
We introduce Perceptual-Initialization (PI), a paradigm shift in visual representation learning that incorporates human perceptual structure during the initialization phase rather than as a downstream fine-tuning step. By integrating human-derived triplet embeddings from the NIGHTS dataset to initialize a CLIP vision encoder, followed by self-supervised learning on YFCC15M, our approach demonstrates significant zero-shot performance improvements, without any task-specific fine-tuning, across 29 zero shot classification and 2 retrieval benchmarks. On ImageNet-1K, zero-shot gains emerge after approximately 15 epochs of pretraining. Benefits are observed across datasets of various scales, with improvements manifesting at different stages of the pretraining process depending on dataset characteristics. Our approach consistently enhances zero-shot top-1 accuracy, top-5 accuracy, and retrieval recall (e.g., R@1, R@5) across these diverse evaluation tasks, without requiring any adaptation to target domains. These findings challenge the conventional wisdom of using human-perceptual data primarily for fine-tuning and demonstrate that embedding human perceptual structure during early representation learning yields more capable and vision-language aligned systems that generalize immediately to unseen tasks. Our work shows that "beginning with you", starting with human perception, provides a stronger foundation for general-purpose vision-language intelligence.
Current low-light image enhancement (LLIE) techniques truly enhance luminance but have limited exploration on another harmful factor of nighttime visibility, the glow effects with multiple shapes in the real world. The presence of glow is inevitable due to widespread artificial light sources, and direct enhancement can cause further glow diffusion. In the pursuit of Overall Nighttime Visibility Enhancement (ONVE), we propose a physical model guided framework ONVE to derive a Nighttime Imaging Model with Near-Field Light Sources (NIM-NLS), whose APSF prior generator is validated efficiently in six categories of glow shapes. Guided by this physical-world model as domain knowledge, we subsequently develop an extensible Light-aware Blind Deconvolution Network (LBDN) to face the blind decomposition challenge on direct transmission map D and light source map G based on APSF. Then, an innovative Glow-guided Retinex-based progressive Enhancement module (GRE) is introduced as a further optimization on reflection R from D to harmonize the conflict of glow removal and brightness boost. Notably, ONVE is an unsupervised framework based on a zero-shot learning strategy and uses physical domain knowledge to form the overall pipeline and network. Empirical evaluations on multiple datasets validate the remarkable efficacy of the proposed ONVE in improving nighttime visibility and performance of high-level vision tasks.
Remarkable progress in zero-shot learning (ZSL) has been achieved using generative models. However, existing generative ZSL methods merely generate (imagine) the visual features from scratch guided by the strong class semantic vectors annotated by experts, resulting in suboptimal generative performance and limited scene generalization. To address these and advance ZSL, we propose an inductive variational autoencoder for generative zero-shot learning, dubbed GenZSL. Mimicking human-level concept learning, GenZSL operates by inducting new class samples from similar seen classes using weak class semantic vectors derived from target class names (i.e., CLIP text embedding). To ensure the generation of informative samples for training an effective ZSL classifier, our GenZSL incorporates two key strategies. Firstly, it employs class diversity promotion to enhance the diversity of class semantic vectors. Secondly, it utilizes target class-guided information boosting criteria to optimize the model. Extensive experiments conducted on three popular benchmark datasets showcase the superiority and potential of our GenZSL with significant efficacy and efficiency over f-VAEGAN, e.g., 24.7% performance gains and more than $60\times$ faster training speed on AWA2. Codes are available at https://github.com/shiming-chen/GenZSL.
Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks. Prior research highlights the crucial role of visual augmentation techniques, like random cropping, in alignment with fine-grained class descriptions generated by large language models (LLMs), significantly enhancing zero-shot performance by incorporating multi-view information. However, the inherent randomness of these augmentations can inevitably introduce background artifacts and cause models to overly focus on local details, compromising global semantic understanding. To address these issues, we propose an \textbf{A}ttention-\textbf{B}ased \textbf{S}election (\textbf{ABS}) method from local details to global context, which applies attention-guided cropping in both raw images and feature space, supplement global semantic information through strategic feature selection. Additionally, we introduce a soft matching technique to effectively filter LLM descriptions for better alignment. \textbf{ABS} achieves state-of-the-art performance on out-of-distribution generalization and zero-shot classification tasks. Notably, \textbf{ABS} is training-free and even rivals few-shot and test-time adaptation methods. Our code is available at \href{https://github.com/BIT-DA/ABS}{\textcolor{darkgreen}{https://github.com/BIT-DA/ABS}}.
Learning robust representations from data often requires scale, which has led to the success of recent zero-shot models such as CLIP. However, the obtained robustness can easily be deteriorated when these models are fine-tuned on other downstream tasks (e.g., of smaller scales). Previous works often interpret this phenomenon in the context of domain shift, developing fine-tuning methods that aim to preserve the original domain as much as possible. However, in a different context, fine-tuned models with limited data are also prone to learning features that are spurious to humans, such as background or texture. In this paper, we propose StarFT (Spurious Textual Alignment Regularization), a novel framework for fine-tuning zero-shot models to enhance robustness by preventing them from learning spuriosity. We introduce a regularization that aligns the output distribution for spuriosity-injected labels with the original zero-shot model, ensuring that the model is not induced to extract irrelevant features further from these descriptions. We leverage recent language models to get such spuriosity-injected labels by generating alternative textual descriptions that highlight potentially confounding features. Extensive experiments validate the robust generalization of StarFT and its emerging properties: zero-shot group robustness and improved zero-shot classification. Notably, StarFT boosts both worst-group and average accuracy by 14.30% and 3.02%, respectively, in the Waterbirds group shift scenario, where other robust fine-tuning baselines show even degraded performance.
Pre-trained vision-language models such as contrastive language-image pre-training (CLIP) have demonstrated a remarkable generalizability, which has enabled a wide range of applications represented by zero-shot classification. However, vision-language models still suffer when they face datasets with large gaps from training ones, i.e., distribution shifts. We found that CLIP is especially vulnerable to sensor degradation, a type of realistic distribution shift caused by sensor conditions such as weather, light, or noise. Collecting a new dataset from a test distribution for fine-tuning highly costs since sensor degradation occurs unexpectedly and has a range of variety. Thus, we investigate test-time adaptation (TTA) of zero-shot classification, which enables on-the-fly adaptation to the test distribution with unlabeled test data. Existing TTA methods for CLIP mainly focus on modifying image and text embeddings or predictions to address distribution shifts. Although these methods can adapt to domain shifts, such as fine-grained labels spaces or different renditions in input images, they fail to adapt to distribution shifts caused by sensor degradation. We found that this is because image embeddings are "corrupted" in terms of uniformity, a measure related to the amount of information. To make models robust to sensor degradation, we propose a novel method called uniformity-aware information-balanced TTA (UnInfo). To address the corruption of image embeddings, we introduce uniformity-aware confidence maximization, information-aware loss balancing, and knowledge distillation from the exponential moving average (EMA) teacher. Through experiments, we demonstrate that our UnInfo improves accuracy under sensor degradation by retaining information in terms of uniformity.
Humans can easily tell if an attribute (also called state) is realistic, i.e., feasible, for an object, e.g. fire can be hot, but it cannot be wet. In Open-World Compositional Zero-Shot Learning, when all possible state-object combinations are considered as unseen classes, zero-shot predictors tend to perform poorly. Our work focuses on using external auxiliary knowledge to determine the feasibility of state-object combinations. Our Feasibility with Language Model (FLM) is a simple and effective approach that leverages Large Language Models (LLMs) to better comprehend the semantic relationships between states and objects. FLM involves querying an LLM about the feasibility of a given pair and retrieving the output logit for the positive answer. To mitigate potential misguidance of the LLM given that many of the state-object compositions are rare or completely infeasible, we observe that the in-context learning ability of LLMs is essential. We present an extensive study identifying Vicuna and ChatGPT as best performing, and we demonstrate that our FLM consistently improves OW-CZSL performance across all three benchmarks.
Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across datasets, making the definition of clusters highly dataset-dependent. Furthermore, the absence of supervised signals complicates hyperparameter tuning in deep learning clustering methods, frequently resulting in unstable performance. To address these issues and reduce the need for per-dataset tuning, we adopt an emerging approach in deep learning: zero-shot learning. We propose ZEUS, a self-contained model capable of clustering new datasets without any additional training or fine-tuning. It operates by decomposing complex datasets into meaningful components that can then be clustered effectively. Thanks to pre-training on synthetic datasets generated from a latent-variable prior, it generalizes across various datasets without requiring user intervention. To the best of our knowledge, ZEUS is the first zero-shot method capable of generating embeddings for tabular data in a fully unsupervised manner. Experimental results demonstrate that it performs on par with or better than traditional clustering algorithms and recent deep learning-based methods, while being significantly faster and more user-friendly.
Accurate pose estimation of surgical tools in Robot-assisted Minimally Invasive Surgery (RMIS) is essential for surgical navigation and robot control. While traditional marker-based methods offer accuracy, they face challenges with occlusions, reflections, and tool-specific designs. Similarly, supervised learning methods require extensive training on annotated datasets, limiting their adaptability to new tools. Despite their success in other domains, zero-shot pose estimation models remain unexplored in RMIS for pose estimation of surgical instruments, creating a gap in generalising to unseen surgical tools. This paper presents a novel 6 Degrees of Freedom (DoF) pose estimation pipeline for surgical instruments, leveraging state-of-the-art zero-shot RGB-D models like the FoundationPose and SAM-6D. We advanced these models by incorporating vision-based depth estimation using the RAFT-Stereo method, for robust depth estimation in reflective and textureless environments. Additionally, we enhanced SAM-6D by replacing its instance segmentation module, Segment Anything Model (SAM), with a fine-tuned Mask R-CNN, significantly boosting segmentation accuracy in occluded and complex conditions. Extensive validation reveals that our enhanced SAM-6D surpasses FoundationPose in zero-shot pose estimation of unseen surgical instruments, setting a new benchmark for zero-shot RGB-D pose estimation in RMIS. This work enhances the generalisability of pose estimation for unseen objects and pioneers the application of RGB-D zero-shot methods in RMIS.
Recent advances in vision language models (VLMs) have enabled broad progress in the general medical field. However, pathology still remains a more challenging subdomain, with current pathology specific VLMs exhibiting limitations in both diagnostic accuracy and reasoning plausibility. Such shortcomings are largely attributable to the nature of current pathology datasets, which are primarily composed of image description pairs that lack the depth and structured diagnostic paradigms employed by real world pathologists. In this study, we leverage pathology textbooks and real world pathology experts to construct high-quality, reasoning-oriented datasets. Building on this, we introduce Patho-R1, a multimodal RL-based pathology Reasoner, trained through a three-stage pipeline: (1) continued pretraining on 3.5 million image-text pairs for knowledge infusion; (2) supervised fine-tuning on 500k high-quality Chain-of-Thought samples for reasoning incentivizing; (3) reinforcement learning using Group Relative Policy Optimization and Decoupled Clip and Dynamic sAmpling Policy Optimization strategies for multimodal reasoning quality refinement. To further assess the alignment quality of our dataset, we propose PathoCLIP, trained on the same figure-caption corpus used for continued pretraining. Comprehensive experimental results demonstrate that both PathoCLIP and Patho-R1 achieve robust performance across a wide range of pathology-related tasks, including zero-shot classification, cross-modal retrieval, Visual Question Answering, and Multiple Choice Question. Our project is available at the Patho-R1 repository: https://github.com/Wenchuan-Zhang/Patho-R1.
Understanding the factors contributing to traffic crashes and developing strategies to mitigate their severity is essential. Traditional statistical methods and machine learning models often struggle to capture the complex interactions between various factors and the unique characteristics of each crash. This research leverages large language model (LLM) to analyze freeway crash data and provide crash causation analysis accordingly. By compiling 226 traffic safety studies related to freeway crashes, a training dataset encompassing environmental, driver, traffic, and geometric design factors was created. The Llama3 8B model was fine-tuned using QLoRA to enhance its understanding of freeway crashes and their contributing factors, as covered in these studies. The fine-tuned Llama3 8B model was then used to identify crash causation without pre-labeled data through zero-shot classification, providing comprehensive explanations to ensure that the identified causes were reasonable and aligned with existing research. Results demonstrate that LLMs effectively identify primary crash causes such as alcohol-impaired driving, speeding, aggressive driving, and driver inattention. Incorporating event data, such as road maintenance, offers more profound insights. The model's practical applicability and potential to improve traffic safety measures were validated by a high level of agreement among researchers in the field of traffic safety, as reflected in questionnaire results with 88.89%. This research highlights the complex nature of traffic crashes and how LLMs can be used for comprehensive analysis of crash causation and other contributing factors. Moreover, it provides valuable insights and potential countermeasures to aid planners and policymakers in developing more effective and efficient traffic safety practices.