Skip to content
Log in
Sponsored Have an interesting project or opportunity? → Hire me ↗
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition

Similar papers

2026

Joint Adversarial and Subdomain Adaptation: A Dual-Strategy Framework for Robust Cross-Domain Modulation Recognition

While deep learning has significantly advanced automatic modulation recognition in complex environments, its performance is often limited by domain shifts caused by factors like channel fading and frequency offset. Domain adaptation has emerged as the primary paradigm to address this challenge. However, existing methods face a critical trade-off, as global alignment strategies tend to disrupt class-specific structures, while local alignment methods are overly sensitive to the quality of pseudo-labels. To address this trade-off, this paper proposes a joint adversarial and subdomain adaptation network (JASA-Net) centered on a dual domain adaptation (DDA) strategy. This strategy employs a “global-first, then-local” alignment ap-proach, where an initial global adversarial alignment establishes a strong foundation for generating high-quality pseudo-labels that subsequently guide a local alignment via the local maximum mean discrepancy (LMMD) metric. To extract robust features, we design a patch adaptive multimodal transformer (PAMT) encoder. Furthermore, an efficient “source domain warm-up + aggressive scheduling” training strategy is developed to enhance performance. Extensive experiments on custom-simulated datasets demonstrate that the proposed framework significantly outperforms representative baselines across various cross-domain tasks. Notably, it exhibits remarkable robustness in few-shot scenarios. This work also provides a critical analysis of the task-dependent nature of entropy weighting, offering valuable insights for future research in the field.

Ming Cheng, Wen Deng, Jintian Xiong et al. · 0 citations

PILO: Principal Component-based Implicit Regularization with Low-rank Optimization for Robust Transfer Learning

PILO is established, a new, more effective paradigm for robust transfer learning through principled and targeted parameter optimization, and significantly outperforms state-of-the-art full-parameter and parameter-efficient methods in robust accuracy across multiple benchmarks.

Shuaihe Liu, Qiugang Zhan, Guisong Liu et al. · 0 citations
Preprint Jul 2026

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.g., zero-shot classification) and consequently lack generalizability across various multimodal tasks. To address this limitation, we propose a dual adversarial fine-tuning framework that jointly optimizes visual and semantic supervision signals from two modalities, enhancing model robustness while generalizing across multiple downstream tasks. The proposed framework comprises two core components, i.e., $\textbf{Visual}$ supervision branch and $\textbf{Semantic}$ supervision branch. The former branch leverages features from clean images, extracted via a frozen original vision encoder, to guide adversarial robustness while the latter incorporates caption-image alignment as a contextual signal to preserve semantic coherence under attack. Moreover, our method achieves cross-task robustness by simply replacing the CLIP vision encoder in the original model, with no need of separate task-specific retraining or architecture modifications.Extensive experiments demonstrate that our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering (VQA) tasks.

Sibo Wang, Jie Zhang, Shiguang Shan et al. · 0 citations
Open access Jul 2026

Enhanced multi-view image clustering via dual-fusion contrastive learning

Multi-view clustering (MVC) in the foundation model era demands architectures that jointly optimize representation power, efficiency, and deployability–core goals of neural architecture search (NAS). Existing deep MVC methods rely on fixed fusion designs, lacking adaptability to heterogeneous views and structural co-optimization with clustering objectives. We propose DFCMVC, a dual-fusion framework featuring a differentiable, attention-based encoder (SBMHE) that implicitly learns view-specific architectural weights via dynamic gating, enabling end-to-end adaptation of representational capacity. This design embodies a NAS-amenable paradigm: its modular, multi-head structure naturally supports searchable fusion topologies and view selection under multi-objective constraints (e.g., accuracy, latency). By aligning deep contrastive learning with interpretable subspace clustering through Jensen-Shannon divergence, DFCMVC ensures both performance and transparency–critical for real-world deployment in multimodal systems. Experiments on seven benchmarks show state-of-the-art results, demonstrating its promise as a scalable, automated foundation for multi-view model design. Code: https://github.com/lab-807/DFCMVC.

Wenzhe Liu, Jingbo Tan, Guodong Ding · 0 citations
Aug 2026

Unity in Diversity: Multi-expert Knowledge Adversarial Learning and Collaboration for Generalizable Vehicle Re-identification.

Generalizable vehicle re-identification (ReID) seeks to develop models capable of adapting to previously unseen domains without additional fine-tuning or retraining. Most existing approaches attempt to learn domain-invariant representations by aligning data distributions across source domains. However, they often neglect the inherent domain-related redundancy within source images, which suppresses the learning of complementary features characterized by lower occurrence probabilities and weaker activations. To overcome this limitation, we introduce Unity in Diversity (UID), a framework of multi-expert knowledge adversarial learning and collaboration. UID incorporates a training-free mechanism to filter out domain-related redundancy in source images, thereby promoting the learning of complementary feature representations. Specifically, we design a Spectrum-based Transformation for Redundancy Elimination and Augmentation Module (STREAM), which generates two distinct types of image inputs for a two-stage complementary feature learning process. In the multi-expert knowledge adversarial learning phase, STREAM enables the model to acquire a diversified identity-oriented prompt set that captures subtle but discriminative visual cues critical for distinguishing highly similar vehicles. This multi-expert prompt set is progressively integrated into complementary feature representations through the proposed knowledge confrontation and collaboration mechanism, which substantially enhances the model's ability to extract fine-grained and complementary information. Extensive experiments conducted on multiple benchmarks demonstrate that UID achieves state-of-the-art performance, validating its effectiveness and generalizability. Our code is available at https://github.com/KZYYYY/UID.

Zhenyu Kuang, Hongyang Zhang, Xiaosong Li et al. · 0 citations
Preprint Aug 2026

Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity

Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives within a single parameter configuration, leading to substantial training cost and unfavorable robustness trade-offs. We propose Robust CurveMoE, an efficient mixture-of-experts framework that connects models specialized for different perturbation norms through a low-loss path and exploits the complementary robustness profiles of models along this path. Robust CurveMoE derives clean and norm-specialized experts from robustness-constrained curve locations and selectively expertizes only influential layers, while sharing the remaining parameters across routing paths. To further reduce curve-construction cost, we introduce contribution-guided partial updating, which selects influential curve parameters using initialization-based gradient scores. We also theoretically bound the objective gap between partial and full curve optimization. Experiments on CIFAR-100 and ImageNet-100 with WideResNet and Vision Transformer architectures show that Robust CurveMoE consistently improves clean, norm-specific, and Union accuracy over MSD and ERMC. In particular, it improves Union accuracy by 2.37 and 2.13 percentage points over the strongest baseline on CIFAR-100 and ImageNet-100, respectively. Extensive ablations further validate the effectiveness of partial updating, selective expertization, and robustness-constrained expert selection.

Xu Zhang, Wanggui Ren · 0 citations