AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

IJCAI 2026

Distribution-Aware Energy Minimization: Physical-Inspired Efficient Active Learning and Quantum Potentials

Zhicheng Yao, Wenguo Yang, Yancheng Chen, Dun Ma, Shengminjie Chen, Xiaoming Sun

Active learning aims to maximize model performance with minimal annotation costs by selecting the most informative samples from large unlabeled pools, which often face a budget dilemma: uncertainty-based methods induce redundancy under low budgets, while representativeness-based methods struggle to mine challenging samples under high budgets. Although some heuristic parameter interpolation schemes attempt to bridge this gap, such strategies suffer from a misalignment between theoretical assumptions and real-world distributions, failing to achieve a good exploration-exploitation balance across all scenarios. In this paper, we propose a general active learning framework based on Distribution-Aware Energy Minimization, which reformulates sample selection as minimizing the energy function for the distributional discrepancy between the selected subset and the global uncertainty field. This physical-inspired perspective naturally derives a Hamiltonian comprising attractive terms and repulsive terms, mathematically achieving an intrinsic and dynamic balance between uncertainty and representativeness. Furthermore, we transform the optimization objective to the ground-state search of an Ising Model, enabling efficient solutions via Coherent Ising Machine. Extensive numerical experiments show that our method outperforms prior state-of-the-art methods across multi-budget regimes on several benchmark datasets. Validation on a real quantum hardware also demonstrates the potential for quantum computer in future large-scale selection tasks.

IJCAI 2026

Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation

Yuanhang Yao, Ping Qian, Zhu Liu, Long Ma, Weimin Wang

Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost; however, lightweight CNN detectors often lack sufficient semantics, leading to noisy pseudo-masks and unstable optimization. To address this, we propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training. We formulate point-supervised learning as a bilevel optimization process: the inner loop adapts a VFM-embedded teacher on reweighted training samples, while the outer loop transfers validation-guided knowledge to a lightweight student to mitigate pseudo-label noise and training-set bias. We further introduce Semantic-Conditioned Affine Modulation (SCAM) to inject VFM semantics into CNN features at multiple layers. In addition, a dynamic collaborative learning strategy with cluster-level sample reweighting enhances robustness to imperfect pseudo-masks. Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability. Our code is available at https://github.com/yuanhang-yao/semantic-prior.

IJCAI 2026

A Local-Rotation-Driven Global Consistency Framework with Dual-View Decoding for Semi-Supervised Medical Image Segmentation

Zhen Yang, Dongshuai Zhang, Yunliang Qi, Guidong Zhang, Shouliang Li, Shuai Wu

Medical image segmentation is still challenging, especially in semi-supervised scenarios where limited annotations are expected to support both accurate boundary delineation and coherent anatomical structures. We propose LR-GCF, a Local-Rotation-Driven Global Consistency Framework that couples strong local geometric perturbations with global consistency regularization in a dual-view architecture. Given an image, LR-GCF transforms it to different variants through patch-wise jigsaw-rotated perturbations. Such variants are decoded using parallel Swin Transformer decoders and perform consistency regularization by virtue of cross pseudo supervision. A rotation prediction head is designed to predict the rotation of each local patch. This makes locally discriminative representations robust to rotations and helps the model recognize global anatomical structure under strong perturbations. To further stabilize global modeling, we introduce a rotation-aligned attention consistency loss that encourages the inter-patch correlation across different variants to be as similar as possible. Moreover, we design a Position Encoding Duplicating scheme to propagate positional encodings from the low-resolution token map to high-resolution token maps, which helps alleviate the misalignment problem in rotation-aligned attention consistency. Extensive experiments on multiple medical image segmentation benchmarks demonstrate that LR-GCF consistently achieves superior performance under limited supervision, by jointly optimizing local detail extraction and stable global anatomical modeling. Source code is available at https://github.com/shuaiaihang/LR-GCF.

IJCAI 2026

PointGP: Geometry-Primed Attention for Point Cloud Analysis

Yong Yang, Jianming Huang, Mengyuan Ge, Chunyang Huang, Bingbing Hu, Junfeng Yao

Transformer-based architectures have demonstrated strong performance in 3D point cloud understanding, yet many existing methods generate attention weights mainly from semantic feature similarity. In deep networks, feature-centric attention may become less selective as point features are progressively smoothed, a behavior associated with feature homogenization and rank collapse, which can weaken the structural discrimination of local aggregation.We propose PointGP, a geometry-primed framework that uses rectified local geometric topology as the primary cue for attention generation. PointGP introduces a Semantic-Guided Manifold Rectifier to predict feature-conditioned local coordinate offsets, and a Dual-Stream Geometric Kernel to compute attention logits from both raw and rectified geometric cues. By reducing reliance on explicit query-key feature matching while implicitly incorporating semantic guidance through geometric rectification, PointGP provides an effective and efficient mechanism for local point aggregation.Experiments across five benchmarks covering classification, part segmentation, and indoor scene segmentation show that PointGP achieves competitive accuracy with strong parameter and computational efficiency compared with representative strong baselines.

IJCAI 2026

Less Is More: Proportional Memory-Guided Differential-Attention MIL for Whole-Slide Image Classification

Hongpeng Yang, Yingxin Chen, Shiqiang Ma, Fei Guo

Whole-slide images (WSIs) provide gigapixel-scale visual evidence for cancer diagnosis, yet diagnostically relevant regions are typically sparse and embedded within large amounts of weakly informative tissue. Existing multiple instance learning methods often aggregate all patches by using attention mechanisms or sequence modeling, leading to redundant computation and limited adaptability to slides with highly variable sizes and lesion burdens. We propose Proportional Memory-guided Differential-attention Multiple Instance Learning (PMDMIL) network, a scalable MIL framework that follows a “less is more” principle for WSI classification. PMDMIL retains a fixed ratio of patches, pre-filters noise with a class-wise memory bank, and fuses the sparse survivors through differential attention to amplify subtle yet decisive morphological differences. Experiments on five public WSI benchmarks demonstrate that PMDMIL consistently outperforms representative MIL and sequence-based baselines across multiple evaluation metrics. Notably, on the DHMC dataset, our model can achieve competitive performance, while processing only 10% of patches, indicating that effective instance selection is more important than exhaustive aggregation for WSI classification.

IJCAI 2026

Unrestricted Targeted Deep Hashing Attack via Contrastive Latent Diffusion

Fan Yang, Chuan Ma, Yuhui Zheng, Xiaobo Shen, Joey Tianyi Zhou

Deep hashing is widely used for large-scale image retrieval but remains vulnerable to adversarial examples, raising practical security concerns. Existing targeted adversarial attacks on deep hashing typically rely on lp-norm constrained perturbations, which struggle to balance attack effectiveness and imperceptibility, often requiring perceptible noise and limiting their practicality in real-world retrieval scenarios. We propose UTDHA, the first unrestricted targeted attack for deep hashing models using contrastive-guided latent diffusion. UTDHA generates adversarial examples with a latent diffusion model and performs optimization in the latent space rather than the pixel space, enabling semantic manipulation while preserving image naturalness. Through contrastive guidance, the attack pulls adversarial examples toward the target label while pushing them away from non-target labels. Meanwhile, UTDHA enforces structural and perceptual consistency, producing adversarial examples that are both imperceptible and visually natural. Extensive experiments on three benchmarks demonstrate that UTDHA outperforms existing targeted adversarial attack baselines for deep hashing models in both attack effectiveness and imperceptibility.

IJCAI 2026

DSSL-Hash: Dynamic Semantic Structure Learning for Unsupervised Cross-Modal Hashing

Fan Yang, Tongxuan Pei, Yuanzhi Zhao, Yudong Zhao

A central bottleneck in unsupervised cross-modal hashing is that both similarity guidance and objective weighting are typically static, while the semantic structure induced during training is inherently dynamic. We present DSSL-Hash, which turns semantic structure learning into an evolving process rather than a one-shot preprocessing step. Specifically, DSSL-Hash distills semantic cues from a vision–language foundation model and constructs a dynamic perception graph via an adaptive similarity matrix, enabling graph propagation to capture higher-order relations beyond pairwise matching. We further reshape Hamming-space learning with a semantic-channel constraint that explicitly regulates distances for partially similar pairs, reducing semantic distortion after binarization. Finally, we develop a Retrieval-Aware Adaptive Scheduler (RAAS) that leverages retrieval feedback to co-adjust modality interactions and objective weights, achieving robust optimization without extensive manual hyper-parameter search. Extensive experiments on MS COCO, NUS-WIDE, and MIRFLICKR-25K across multiple code lengths demonstrate that DSSL-Hash consistently outperforms recent state-of-the-art unsupervised cross-modal hashing methods.

IJCAI 2026

A Structural-Analysis-Based Information Fusion for Multi-Modal Cross-View Geo-Localization

Xu Yan, Xiaoran Zhang, Ziwei Shi, Yu Zang, Weiquan Liu, Cheng Wang

Cross-view geo-localization (CVGL) aims at localizing a ground-level query by retrieving its corresponding match from a database of geo-tagged satellite images. Existing multi-modal CVGL methods lack a structured design in the fusion stage, limiting their ability to fully exploit the information from multiple modalities. To overcome this limitation, we propose a Structural-Analysis-Based fusion principle that guides the design of network architecture. Following this principle, we present Decoupled Query Fusion (DQF), a novel fusion module that decouples feature interactions through role-specific learnable queries. These learnable queries aggregate features into distinct slots. Specifically, modality-specific queries capture unique information from each modality, while cross-modal queries extract redundant and synergistic information between different modalities. To better discriminate positive samples at varying geographic distances, we further propose Geo-aware Circle Loss, which adaptively weights supervision signal based on the geographical distance between samples and anchors. Extensive experiments on large-scale benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches. Comprehensive ablation studies further validate the effectiveness of each component. Our code and models will be made publicly available.

IJCAI 2026

Cross Domain Test Time Scaling: Scale Knowledge and Reasoning on Cross Domains

Minxi Yan, Yihua Shao, Yanling Pan, Siyu Chen, Hongjuan Pei, Hao Tang, Fei Ma, Jingcai Guo, Nicu Sebe

Test-time scaling (TTS) has demonstrated remarkable potential in enhancing the reasoning capabilities of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs). However, its application has primarily been limited to domains such as mathematics and programming, owing to their reasoning-intensive nature and the ease of result verification. Its utility in other knowledge-intensive fields, such as medicine and general scientific research, remains underexplored. To bridge this gap and unlock the potential of TTS in broader domains, we propose Cross-Domain TTS, a novel framework that enables task-tailored scaling. This framework consists of two key components: a conformal prediction-based cold-start strategy and an information-gain-based dynamic reasoning adjustment. The CP-based cold-start strategy guides the model's initialization during test-time scaling based on conformal prediction theory, while the information-gain-based dynamic reasoning adjustment guides the model's reasoning progress through a progress vector according to the information gain of reasoning steps. We conducted experiments using LLMs and LVLMs on cross-domain benchmarks. Our results demonstrate that the proposed framework consistently improves performance across various domain-specific datasets. For instance, in the medical domain, it achieves an improvement of up to 17% in pass@1 accuracy while reducing inference latency and saving up to 30% in token consumption. Code is available at https://github.com/Yan0613/Cross-Domain-TTS.

IJCAI 2026

Shot-Conditioned Vision-Language Adaptation for Effective Harmful Content Detection from Online Short Videos

Shuai Xu, Zao Qiu, Xuelin Zhu, Yicong Li

Short video harmful content detection aims to automatically identify diverse anomalies from user-generated media. This task presents unique challenges due to frequent editing cuts and highly variable anomaly densities, limiting the effectiveness of traditional surveillance-based approaches. Moreover, existing Vision-Language Model-based approaches typically rely on rigid instance selection mechanisms that fail to adapt to the unpredictable duration of anomalies in such unconstrained videos. To address these issues, we propose SVLA, a Shot-conditioned Vision-Language Adaptation framework, for effectively detecting harmful contents from online short videos. Our approach introduces a novel π-adaptive strategy to dynamically estimate shot-level anomaly density, replacing rigid selection with calibrated supervision. Furthermore, we employ a shot-conditioned temporal encoder to respect video hierarchy and adopt a dual-path contextual adapter to resolve semantic ambiguity. To benchmark this task, we construct a new dataset (SVA) covering more genuine online short videos that involve seven anomaly categories. Experiments on the SVA dataset demonstrate that SVLA can achieve the state-of-the-art performance and outperform its competitors across diverse scenarios. Codes and datasets are available at: https://github.com/xushuai7/IJCAI-SVLA.

IJCAI 2026

IPSM-Bench: A New Intermediate Phase Segmentation Benchmark in Microstructure Images of Zinc-Based Absorbable Biomaterials

Jinglin Xu, Shangyan Zhao, Jiabo Wang, Xinghong Mu, Yulong Lei, JiaCheng Zhang, Hongbo Sun, Yageng Li

Zinc-based alloys are indispensable emerging absorbable metallic biomaterials, and their macroscopic performance is governed by microstructural characteristics. Intermediate phases—key microstructural constituents—are pivotal in regulating mechanical and functional properties. However, intermediate phase segmentation in zinc alloy microstructures faces formidable challenges: scarce annotated datasets, low contrast, difficulty detecting small targets, and heterogeneous morphologies. To this end, we construct IPSM-Bench, the largest high-quality dataset for zinc-alloy intermediate phase segmentation. Furthermore, we propose SCoP-SAM, a new Spatial Context Prior-guided SAM method that leverages the gradient structure and grayscale properties of intermediate phases to capture spatial context priors and incorporates them into the entire SAM encoding-decoding process, improving segmentation performance. Based on the proposed IPSM-Bench, we establish a new benchmark for intermediate phase segmentation to systematically evaluate state-of-the-art (SOTA) methods and advance research on zinc alloy microstructure analysis. Extensive experiments on IPSM-Bench and additional public alloy benchmarks demonstrate that our SCoP-SAM not only achieves SOTA performance for zinc-alloy intermediate phase segmentation but also generalizes remarkably well to other alloy scenarios.

IJCAI 2026

MedVCoT: Bridging the Modality Gap in Medical VQA Through Latent Visual Reasoning

bo xu, Quanhao Zhu, Boling Zhu, Chenyuan Wang, Liang Zhao, Hongfei Lin, Feng Xia

With the rising demand for trustworthy AI in clinical practice, strong interpretability is now a critical requirement as well as accuracy. However, the modality gap for medical visual question answering is quite severe when continuous visual signals are forcibly projected into discrete text space for reasoning, and the loss of necessary diagnostic information leads to low precision and black-box opacity. To address this problem, we propose MedVCoT, which incorporates latent visual reasoning into the medical visual question answering(VQA) domain. Rather than merely integrating modules, MedVCoT utilizes the specialized expertise of MedSAM to train a large vision-language model so that it can autonomously generate consistent and continuous latent visual tokens within Visual Chain-of-Thought. This mechanism forces the model to explicitly "see" the lesion in the latent space before formulating a textual diagnosis, ensuring answers are causally rooted in verifiable visual evidence rather than statistical hallucination. We achieve this through a progressive 3-stage training procedure: medical feature alignment, visual reasoning learning by utilizing latent tokens generated, and instruction tuning for complex clinical scenarios. Extensive experiments show that MedVCoT can achieve state-of-the-art performance on multiple benchmarks, outperforming other methods by large margins. Meanwhile, it provides pixel-level segmentation masks to validate its diagnostic reasoning. Our demo is available at https://zhuqh19.github.io/MedVCoT.

IJCAI 2026

FlowOCT: Wavelet Flow Matching for OCT-to-OCTA Translation

Ze Xiong, Dehui Qiu, Liguo Deng, Longfei Zhou, Zhetao Xu, Fa Zhang, Xiaohua Wan

Retinal angiography provides critical vascular information, yet optical coherence tomography angiography (OCTA) acquisition remains slower and less accessible than conventional structural OCT. A key open question is: how angiographic signals can be recovered? To address the issues of artifacts and structural blurring in existing generative methods, we propose a wavelet flow matching-based model, FlowOCT. This method operates directly on OCT wavelet coefficients, learning frequency-specific velocity fields to map them to the OCTA wavelet distribution. To ensure anatomical accuracy of the vasculature, we introduce constraints such as depth-wise contrastive alignment and two-dimensional projection consistency. Given the sparse nature of vascular signals in OCTA data, a structure-focused loss function and corresponding evaluation metrics are designed. Experiment results show that FlowOCT outperforms existing methods in terms of both image quality and perceptual similarity. Downstream diagnostic tasks further validate its superior authenticity and generalization capability. Code is available at https://github.com/cnu-medilab/FlowOCT.

IJCAI 2026

SAFformer: Improving Spiking Transformer via Active Predictive Filtering

Zequan Xie, Weiming Zeng, Yunhua Chen, Sichang Lin, Tongyang Chen, Jinsheng Xiao

Spiking Neural Networks (SNNs) offer notable advantages in biological plausibility and energy efficiency, making them promising candidates for building low-power Transformers. However, existing Spiking Transformers largely adhere to a passive reactive paradigm, which struggles to focus on task-relevant information and incurs substantial computational overhead when processing redundant visual data. To overcome this fundamental yet underexplored limitation, we propose SAFformer, a novel Spiking Transformer architecture based on an active predictive filtering paradigm. Inspired by the brain’s predictive coding mechanism, SAFformer actively suppresses predictable signals and focuses on salient visual features. Extensive experiments show that SAFformer establishes new state-of-the-art performance on CIFAR-10/100 and CIFAR10-DVS. Remarkably, on ImageNet-1K, it achieves 80.44% Top-1 accuracy with only 26.58M parameters and an energy consumption of 5.88 mJ, demonstrating an exceptional balance between accuracy and efficiency.

IJCAI 2026

DSSG: Dual-Stream Semantic Guidance for Source-Fully-Free Adaptation of Vision-Language Models

Weiwei Xiang, Shun Peng, Guangyi Xiao, Hao Chen, Lei Yang

Source-Fully-Free Domain Adaptation (SFF-DA) has emerged as a strategic paradigm to adapt Vision-Language Models (VLMs) without any access to source data or task-specific source models. However, we identify a critical "Dual Semantic Drift" that hinders this process: static drift caused by the stagnation of frozen hand-crafted templates, and dynamic drift resulting from noisy, instance-level generated captions. These issues lead to a severe stability-plasticity dilemma, manifesting as semantic misalignment and class collapse. To address this, we propose DSSG (Dual-Stream Semantic Guidance), an end-to-end framework that reconciles fine-grained plasticity with global stability. Our core contribution is the Dual Semantic Guidance (DSG) module, which integrates a captioning stream for detailed domain nuances with a template stream to anchor global categorical consistency. Furthermore, a Dynamic Cross-Modal Knowledge Distillation (CMKD) module is introduced to adaptively optimize teacher-student alignment across modalities. Extensive experiments demonstrate that DSSG significantly outperforms current state-of-the-art methods across multiple benchmarks, providing a robust solution for the unsupervised transfer of foundation models. The code is available on https://github.com/mrmenand/DSSG.

IJCAI 2026

Continual Unsupervised Domain Adaptation for Cardiac Image Segmentation with Style-Adapting Generative Replay and Prototype Consolidation

Shun Xiang, Yan Yi, Haiyong Chen, Yuanquan Wang, Yining Wang

Continual unsupervised domain adaptation (UDA) for multi-domain cardiac image segmentation is crucial for clinical deployment under strict privacy constraints, where data from different centers cannot be stored or revisited. However, existing methods still suffer from catastrophic forgetting and training instability caused by noisy pseudo-labels and representation drift. In this study, we propose a novel continual UDA framework that enforces dual-level alignment at the input and feature levels. At the input level, the Domain-Style Adapting Generative Replay (DSA-GR) module employs trajectory-consistent diffusion distillation and style adaptation to synthesize high-fidelity, domain-consistent replay images without storing raw data. At the feature level, the Cross-domain Prototype-guided Feature Consolidation (CPFC) mechanism mitigates representation drift by maintaining a cross-domain prototype memory bank that aggregates features from the current and replay streams. These prototypes act as robust anchors for prototype-guided contrastive learning, rectifying the feature space and suppressing pseudo-label drift. Extensive experiments on two public datasets demonstrate that our framework consistently outperforms state-of-the-art methods. Code will be released at https://github.com/hlyf-xs/CUDA_Seg.

IJCAI 2026

Disentangled Knowledge Forgetting in Machine Unlearning

Yuhang Xia, Cheng Zhen, Yirui Wu, Lixin Yuan, Wenxiao Zhang, Jun Liu

With the increasing demand of privacy protection, Machine Unlearning (MU) appears to remove private data from an already trained model without retraining from scratch. Most current works suffer from overly unlearning (low fidelity) or incomplete unlearning (low effectiveness). To identify the issues behind, we conduct causal analysis to obtain a resolvable route, i.e., disentangling shared knowledge into attribute-level semantics to remove it as the confounder. We further perform MU loss analysis to reformulate it as balanced form of constraints, thus guaranteeing high fidelity and effectiveness. Based on theoretical analysis, we propose disentangled knowledge forgetting constrained by the reformulated MU loss, which disentangles knowledge with variational auto-encoder and refines knowledge with counterfactual inference. Extensive experimental results demonstrate that our method achieves state-of-the-art performance.

IJCAI 2026

FedENC: Federated Adaptive CLIP Model via Energy Alignment and Neural Collapse

Yihang Wu, Ahmad Chaddad, Sarah A. Alkhodair

Federated Learning (FL) faces two major challenges when deploying large vision-language models such as contrastive language-image pretraining (CLIP) model, namely high computation/communication overhead and performance degradation due to data heterogeneity. To address these, we propose FedENC, a novel federated adaptive CLIP framework. FedENC keeps the CLIP encoder frozen and introduces a lightweight communicable global expert adaptation module for learning general knowledge across clients and two local experts for client-specific adaptation to reduce computation and communication overhead. To mitigate data heterogeneity, we introduce neural collapse (NC) alignment to encourage the model to learn unified and balanced image feature representations. To enrich the performance, we propose a cosine and Kullback–Leibler (KL) divergence based alignment function to improve the prediction consistency between the global and local experts. Finally, we ensemble their outputs for robust inference. Extensive experiments on six datasets (4 natural + 2 medical) in challenging settings (e.g., domain shift) show that FedENC improves the test accuracy (e.g., by +5.37% on DomainNet compared to LoRA) with reasonable communication load (e.g., 15.2x lower than LoRA, with 3.3GB GPU memory usage). The code is available at https://github.com/AIPMLab/FedENC.

IJCAI 2026

PURE: Purging Unrelated Representations for Content-Agnostic Forgery Detection

Xinyu Wu, Dong Li, Minglai Shao, Xintao Wu, Zhong Chen, Chen Zhao

Existing AI-generated image (AIGI) detectors perform well in-domain but degrade severely under distribution shift. We observe that this failure is mainly caused by content shortcuts, where detectors spuriously couple forgery artifacts with semantic content, such as object categories or demographic attributes, learning content–label correlations instead of generalizable forgery patterns. To address this issue, we propose PURE (Purging Unrelated Representations for Content-Agnostic Forgery Detection), which achieves content-agnostic detection through two complementary components: a Causal Semantic Generative (CSG) mechanism that disentangles semantic representations from forgery-irrelevant nuisance factors, and a Gaussian Mixture Model (GMM)-based prototype alignment module that suppresses category-specific content bias. Extensive experiments on CIFAKE, GenImage, and AlFace show that PURE achieves superior generalization under spurious correlation reversal. The code is available at https://github.com/wuxinyu519/PURE.

IJCAI 2026

PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learning

Jiaying Wu, Can Gao, Jinglu Hu, Hui Li, Xiaofeng Cao, Jingcai Guo

Few-shot learning aims to recognize novel categories from limited labeled samples, where prototypes estimated from 1--5 supports per class are often unreliable. Semantic-based approaches alleviate this by introducing class-level priors, but they often ignore instance-level cues and rarely optimize queries under the inductive protocol. We propose PMCE, a Probabilistic framework that leverages Multi-granularity semantics with Caption-guided Enhancement for few-shot classification. On base classes, we build a knowledge bank with class-wise visual statistics and class-name embeddings. At test time, the semantic embedding of a novel class retrieves a few similar base classes whose visual priors are aggregated into a class-specific prior and combined with the support-based prototype via MAP estimation. Simultaneously, we train a lightweight enhancer on base classes that fuses frozen BLIP captions with visual features, and apply it to both supports and queries without using query-set statistics or novel labels. A simple caption-consistency regularizer further improves robustness to noisy captions. Experiments on four standard benchmarks with ResNet-12 and Swin-T backbones show that PMCE outperforms state-of-the-art few-shot baselines, achieving up to 7.71% gains over the strongest competitor on MiniImageNet in the challenging 1-shot setting. Our code is available at https://github.com/channa419/PMCE.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.