Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples, leaving some undiscovered semantic pattern within the unlabeled data. To obtain a more generalized classification model, it is crucial to discover potential novel categories with knowledge only from the labeled set. Previous methods generally achieve this goal by employing naive contrastive learning or unsupervised clustering for all the samples. Nevertheless, they usually ignore the inherent critical information within the historical predictions of the model being trained. Specifically, we empirically reveal that a significant number of unlabelled samples yield consistent historical predictions corresponding to their ground truth class. Motivated by this observation, we propose a Memory Consistency guided Divide-and-conquer Learning (MCDL) framework. In this framework, we introduce two online-updating memory banks to record historical predictions of unlabeled data, which are exploited to accurately measure the credibility of each sample in terms of its prediction consistency. With the guidance of credibility, we design a divide-and-conquer learning strategy to utilize the credible, discriminative information of unlabeled data while alleviating the negative influence of noisy labels. Extensive experimental results on multiple benchmarks demonstrate the generality and superiority of our method, where our method consistently outperforms state-of-the-art models by a large margin and boost their performance in a plug-in-play manner on both seen and unseen classes of the generic image recognition and challenging semantic shift settings (e.g., with +8.4

Current few-shot action recognition involves two primary sources of information for classification:(1) intra-video information, determined by frame content within a single video clip, and (2) inter-video information, measured by relationships (e.g., feature similarity) among videos. However, existing methods inadequately exploit these two information sources. In terms of intra-video information, current sampling operations for input videos may omit critical action information, reducing the utilization efficiency of video data. For the inter-video information, the action misalignment among videos makes it challenging to calculate precise relationships. Moreover, how to jointly consider both inter- and intra-video information remains under-explored for few-shot action recognition. To this end, we propose a novel framework, Video Information Maximization (VIM), for few-shot video action recognition. VIM is equipped with an adaptive spatial-temporal video sampler and a spatiotemporal action alignment model to maximize intra- and inter-video information, respectively. The video sampler adaptively selects important frames and amplifies critical spatial regions for each input video based on the task at hand. This preserves and emphasizes informative parts of video clips while eliminating interference at the data level. The alignment model performs temporal and spatial action alignment sequentially at the feature level, leading to more precise measurements of inter-video similarity. Finally, These goals are facilitated by incorporating additional loss terms based on mutual information measurement. Consequently, VIM acts to maximize the distinctiveness of video information from limited video data. Extensive experimental results on public datasets for few-shot action recognition demonstrate the effectiveness and benefits of our framework.

The rapid advancement of generative models has made synthetic images increasingly realistic, challenging reliable detection. Existing methods are often limited to end-to-end classification or monolithic reasoning, and thus fail to model structured forensic reasoning and heterogeneous visual evidence. We revisit synthetic image detection from a cognitive perspective and propose a Heuristic-to-Reasoning cognitive skill learning framework for evidence-based forensic analysis. Given an input image, our framework first extracts heuristic perceptual clues, selects the optimal forensic skill, and then performs skill-conditioned reasoning for evidence extraction and decision making. To support this paradigm, we introduce ClueAegis-Bench, which decomposes synthetic image detection into explicitly annotated forensic cognitive skills for structured evaluation beyond binary classification. Based on this benchmark, we propose ClueAegis (Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detection), a two-stage agentic framework that conducts heuristic skill selection followed by evidence-guided reasoning through skill-conditioned toolchains. This design reformulates synthetic image detection as a configurable multi-skill reasoning process that bridges perception, skill selection, and forensic reasoning. Extensive experiments show that ClueAegis achieves state-of-the-art performance while improving cross-domain generalization and robustness. It also provides transparent reasoning trajectories and structured forensic evidence, offering a more explainable alternative to conventional end-to-end detectors.

Pre-trained stable diffusion models (SD) have shown great advances in visual correspondence. In this paper, we investigate the capabilities of Diffusion Transformers (DiTs) for accurate dense correspondence. Distinct from SD, DiTs exhibit a critical phenomenon in which very few feature activations exhibit significantly larger values than others, known as massive activations, leading to uninformative representations and significant performance degradation for DiTs. The massive activations consistently concentrate at very few fixed dimensions across all image patch tokens, holding little local information. We analyze these dimension-concentrated massive activations and uncover that their concentration is inherently linked to the Adaptive Layer Normalization (AdaLN) in DiTs. Building on these findings, we propose the Diffusion Transformer Feature (DiTF), a training-free AdaLN-based framework that extracts semantically discriminative features from DiTs. Specifically, DiTF leverages AdaLN to adaptively localize and normalize massive activations through channel-wise modulation. Furthermore, a channel discard strategy is introduced to mitigate the adverse effects of massive activations. Experimental results demonstrate that our DiTF outperforms both DINO and SD-based models and establishes a new state-of-the-art performance for DiTs in different visual correspondence tasks (e.g., with +9.4\% on Spair-71k and +4.4\% on AP-10K-C.S.).

ABSTRACT We report the phase-connected timing ephemeris, polarization pulse profiles, Faraday rotation measurements, and Rotating-Vector-Model (RVM) fitting results of 12 millisecond pulsars (MSPs) discovered with the Five-hundred-meter Aperture Spherical radio Telescope (FAST) in the Commensal Radio Astronomy FAST survey (CRAFTS). The timing campaigns were carried out with FAST and Arecibo over 3 yr. 11 of the 12 pulsars are in neutron star–white dwarf binary systems, with orbital periods between 2.4 and 100 d. 10 of them have spin periods, companion masses, and orbital eccentricities that are consistent with the theoretical expectations for MSP–Helium white dwarf (He WD) systems. The last binary pulsar (PSR J1912−0952) has a significantly smaller spin frequency and a smaller companion mass, the latter could be caused by a low orbital inclination for the system. Its orbital period of 29 d is well within the range of orbital periods where some MSP–He WD systems have shown anomalous eccentricities, however, the eccentricity of PSR J1912−0952 is typical of what one finds for the remaining MSP–He WD systems.

The epidermal growth factor (EGF)-like factors, comprising amphiregulin (AREG), betacellulin (BTC), and epiregulin (EREG), play a critical role in regulating the ovulatory process. Pentraxin 3 (PTX3), an essential ovulatory protein, is necessary for maintaining extracellular matrix (ECM) stability during cumulus expansion. The aim of this study was to investigate the impact of EGF-like factors, AREG, BTC, and EREG on the expression and production of PTX3 in human granulosa-lutein (hGL) cells and the molecular mechanisms involved. Our results demonstrated that AREG, BTC, and EREG could regulate follicular function by upregulating the expression and increasing the production of PTX3 in both primary (obtained from 20 consenting patients undergoing IVF treatment) and immortalized hGL cells. The upregulation of PTX3 expression was primarily facilitated by the activation of the extracellular signal-regulated kinase 1 and 2 (ERK1/2) signaling pathway, induced by these EGF-like factors. In addition, we found that the upregulation of PTX3 expression triggered by the EGF-like factors was completely reversed by either pretreatment with the epidermal growth factor receptor (EGFR) inhibitor, AG1478, or knockdown of EGFR, suggesting that EGFR is crucial for activating the ERK1/2 signaling pathway in hGL cells. Overall, our findings indicate that AREG, BTC, and EREG may modulate human cumulus expansion during the periovulatory stage through the upregulation of PTX3.

Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to their intrinsic procedural temporal structure. Specifically, procedural knowledge is critical for accurate correlation analyses on instructional videos. Nevertheless, current procedure-learning methods heavily rely on step-level annotations, which are costly and not scalable. To address this problem, we introduce a weakly supervised framework called Collaborative Procedure Alignment (CPA) for procedure-aware correlation learning on instructional videos. Our framework comprises two core modules: collaborative step mining and frame-to-step alignment. The collaborative step mining module enables simultaneous and consistent step segmentation for paired videos, leveraging the semantic and temporal similarity between frames. Based on the identified steps, the frame-to-step alignment module performs alignment between the frames and steps across videos. The alignment result serves as a measurement of the correlation distance between two videos. We instantiate our framework in two distinct instructional video tasks: sequence verification and action quality assessment. Extensive experiments validate the effectiveness of our approach in providing accurate and interpretable correlation analyses for instructional videos.

With the recent burst of 2D and 3D data, cross-modal retrieval has attracted increasing attention recently. However, manual labeling by non-experts will inevitably introduce corrupted annotations given ambiguous 2D/3D content. Though previous works have addressed this issue by designing a naive division strategy with hand-crafted thresholds, their performance generally exhibits great sensitivity to the threshold value. Besides, they fail to fully utilize the valuable supervisory signals within each divided subset. To tackle this problem, we propose a Divide-and-conquer 2D-3D cross-modal Alignment and Correction framework (DAC), which comprises Multimodal Dynamic Division (MDD) and Adaptive Alignment and Correction (AAC). Specifically, the former performs accurate sample division by adaptive credibility modeling for each sample based on the compensation information within multimodal loss distribution. Then in AAC, samples in distinct subsets are exploited with different alignment strategies to fully enhance the semantic compactness and meanwhile alleviate over-fitting to noisy labels, where a self-correction strategy is introduced to improve the quality of representation. Moreover. To evaluate the effectiveness in real-world scenarios, we introduce a challenging noisy benchmark, namely Objaverse-N200, which comprises 200k-level samples annotated with 1156 realistic noisy labels. Extensive experiments on both traditional and the newly proposed benchmarks demonstrate the generality and superiority of our DAC, where DAC outperforms state-of-the-art models by a large margin. (i.e., with +5.9% gain on ModelNet40 and +5.8% on Objaverse-N200).

Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation. However, existing works usually ignore the correlation between selected samples and its local context in feature space, which leads to inferior usage of annotation budgets. In this work, we revisit the theoretical bound of the classical Core-set method and identify that the performance is closely related to the local sample distribution around selected samples. To estimate the density of local samples efficiently, we introduce a local proxy estimator with Dynamic Masked Convolution and develop a Density-aware Greedy algorithm to optimize the bound. Extensive experiments demonstrate the superiority of our approach. Moreover, with very few labels, our scheme achieves comparable performance to the fully supervised counterpart.

Audio-Visual Segmentation (AVS) is a challenging task, which aims to segment sounding objects in video frames by exploring audio signals. Generally AVS faces two key challenges: (1) Audio signals inherently exhibit a high degree of information density, as sounds produced by multiple objects are entangled within the same audio stream; (2) Objects of the same category tend to produce similar audio signals, making it difficult to distinguish between them and thus leading to unclear segmentation results. Toward this end, we propose TransAVS, the first Transformer-based end-to-end framework for AVS task. Specifically, TransAVS disentangles the audio stream as audio queries, which will interact with images and decode into segmentation masks with full transformer architectures. This scheme not only promotes comprehensive audio-image communication but also explicitly excavates instance cues encapsulated in the scene. Meanwhile, to encourage these audio queries to capture distinctive sounding objects instead of degrading to be homogeneous, we devise two self-supervised loss functions at both query and mask levels, allowing the model to capture distinctive features within similar audio data and achieve more precise segmentation. Our experiments demonstrate that TransAVS achieves state-of-the-art results on the AVSBench dataset, highlighting its effectiveness in bridging the gap between audio and visual modalities.

Robust autonomous driving requires agents to accurately identify unexpected areas (anomalies) in urban scenes. To this end, some critical issues remain open: how to design advisable metric to measure anomalies, and how to properly generate training samples of anomaly data? Classical effort in anomaly detection usually resorts to pixel-wise uncertainty or sample synthesis, which ignores the contextual information and sometimes requires auxiliary data with fine-grained annotations. On the contrary, in this paper, we exploit the strong context-dependent nature of the segmentation task and design an energy-guided self-supervised framework for anomaly segmentation, which optimizes an anomaly head by maximizing the likelihood of self-generated anomaly pixels. For this purpose, we design two estimators to model anomaly likelihood, one is a task-agnostic binary estimator and the other depicts the likelihood as residual of task-oriented joint energy. Based on the proposed estimators, we devise an adaptive self-supervised training framework, which exploits the contextual reliance and estimated likelihood to refine mask annotations in anomaly areas. We conduct extensive experiments on challenging Fishyscapes and Road Anomaly benchmarks, demonstrating that without any auxiliary data or synthetic models, our method can still achieve comparable performance to supervised competitors. Code is available at https://github.com/yuanpengtu/SLEEG..

Pedestrian detection is notoriously considered a challenging task due to the frequent occlusion between humans. Unlike generic object detection, pedestrian detection involves a single category but dense instances, making it crucial to achieve accurate and robust object localization. By analogizing instance-level localization to a variational autoencoder and regarding the dense proposals as the latent variables, we establish a unique perspective of formulating pedestrian detection as a variational inference problem. From this vantage, we propose the Variational Pedestrian Detector (VPD), which uses a probabilistic model to estimate the true posterior of inferred proposals and applies a reparameterization trick to approximate the expected detection likelihood. In order to adapt the variational inference problem to the case of pedestrian detection, we propose a series of customized designs to cope with the issue of occlusion and spatial vibration. Specifically, we propose the Normal Gaussian and its variant of the Mixture model to parameterize the posterior in complicated scenarios. The inferred posterior is regularized by a conditional prior related to the ground-truth distribution, thus directly coupling the latent variables to specific target objects. Based on the posterior distribution, maximum detection likelihood estimation is applied to optimize the pedestrian detector, where a lightweight statistic decoder is designed to cast the detection likelihood into a parameterized form and enhance the confidence score estimation. With this variational inference process, VPD endows each proposal with the discriminative ability from its adjacent distractor due to the disentangling nature of the latent variable in variational inference, achieving accurate and robust detection in crowded scenes. Experiments conducted on CrowdHuman, CityPersons, and MS COCO demonstrate that our method is not only plug-and-play for numerous popular single-stage methods and two-stage methods but also can achieve a remarkable performance gain in highly occluded scenarios. The code for this project can be found at https://github.com/hhy-ee/VPD .

Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples. Recently, numerous 2D anomaly detection methods have been proposed and have achieved promising results, however, using only the 2D RGB data as input is not sufficient to identify imperceptible geometric surface anomalies. Hence, in this work, we focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets, i.e., ImageNet, to construct feature databases. And we empirically find that directly using these pre-trained models is not optimal, it can either fail to detect subtle defects or mistake abnormal features as normal ones. This may be attributed to the domain gap between target industrial data and source data.Towards this problem, we propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.Both intra-modal adaptation and cross-modal alignment are optimized from a local-to-global perspective in LSFA to ensure the representation quality and consistency in the inference stage.Extensive experiments demonstrate that our method not only brings a significant performance boost to feature embedding based approaches, but also outperforms previous State-of-The-Art (SoTA) methods prominently on both MVTec-3D AD and Eyecandies datasets, e.g., LSFA achieves 97.1% I-AUROC on MVTec-3D, surpass previous SoTA by +3.4%.

Classifying an entire Whole Slide Image (WSI) in a single forward pass is challenging due to its vast resolution. Consequently, current effort on WSI classification resorts to multiple instance learning (MIL), using patch-wise instances to predict categories under image-wise supervision. However, recent MIL methods usually follow implicit instance selection strategy and ignore the effect from inherent patch category imbalances. In a statistical sense, negative patches dominate in WSIs and provide sufficient samples for accurate density estimation. Therefore, in this paper, we learn from anomaly detection and propose a deep MIL framework which learns a hybrid negative probability model to bootstrap discovery of potential positive lesion. We associate attention-based MIL approach with a regularization loss function to explicitly improve patch selection process in positive images. Experiments conducted on benchmarks of WSI recognition demonstrate that our method brings significant improvement to classic attention-based MIL baseline and achieves state-of-the-art performance.

Image retrieval aims to identify visually similar images within a database using a given query image. Traditional methods typically employ both global and local features extracted from images for matching, and may also apply re-ranking techniques to enhance accuracy. However, these methods often fail to account for the noise present in query images, which can stem from natural or human-induced factors, thereby negatively impacting retrieval performance. To mitigate this issue, we introduce a novel setting for low-quality image retrieval, and propose an Adaptive Noise-Based Network (AdapNet) to learn robust abstract representations. Specifically, we devise a quality compensation block trained to compensate for various low-quality factors in input images. Besides, we introduce an innovative adaptive noise-based loss function, which dynamically adjusts its focus on the gradient in accordance with image quality, thereby augmenting the learning of unknown noisy samples during training and enhancing intra-class compactness. To assess the performance, we construct two datasets with low-quality queries, which is built by applying various types of noise on clean query images on the standard Revisited Oxford and Revisited Paris datasets. Comprehensive experimental results illustrate that AdapNet surpasses state-of-the-art methods on the Noise Revisited Oxford and Noise Revisited Paris benchmarks, while maintaining competitive performance on high-quality datasets. The code and constructed datasets will be made available.

Magnetars are neutron stars with extremely strong magnetic fields, frequently powering high-energy activity in X-rays. Pulsed radio emission following some X-ray outbursts has been detected, albeit its physical origin is unclear. It has long been speculated that the origin of magnetars' radio signals is different from those from canonical pulsars, although convincing evidence is still lacking. Five months after magnetar SGR 1935+2154's X-ray outburst and its associated fast radio burst 20200428, a radio pulsar phase was discovered. Here we report the discovery of X-ray spectral hardening associated with the emergence of periodic radio pulsations from SGR 1935+2154 and a detailed analysis of the properties of the radio pulses. The observations suggest that radio emission originates from the outer magnetosphere of the magnetar, and the surface heating due to the bombardment of inward-going particles from the radio emission region is responsible for the observed X-ray spectral hardening.

Video Correlation Learning (VCL) delineates a high-level research domain that centers on analyzing the semantic and temporal correspondences between videos through a comparative paradigm. Recently, instructional video-related tasks have drawn increasing attention due to their promising potential. Compared with general videos, instructional videos possess more complex procedure information, making correlation learning quite challenging. To obtain procedural knowledge, current methods rely heavily on fine-grained step-level annotations, which are costly and non-scalable. To improve VCL on instructional videos, we introduce a weakly supervised framework named Collaborative Procedure Alignment (CPA). To be specific, our framework comprises two core components: the collaborative step mining (CSM) module and the frame-to-step alignment (FSA) module. Free of the necessity for step-level annotations, the CSM module can properly conduct temporal step segmentation and pseudo-step learning by exploring the inner procedure correspondences between paired videos. Subsequently, the FSA module efficiently yields the probability of aligning one video’s frame-level features with another video’s pseudo-step labels, which can act as a reliable correlation degree for paired videos. The two modules are inherently interconnected and can mutually enhance each other to extract the step-level knowledge and measure the video correlation distances accurately. Our framework provides an effective tool for instructional video correlation learning. We instantiate our framework on four representative tasks, including sequence verification, few-shot action recognition, temporal action segmentation, and action quality assessment. Furthermore, we extend our framework to more innovative functions to further exhibit its potential. Extensive and in-depth experiments validate CPA’s strong correlation learning capability on instructional videos. The implementation can be found at https://github.com/hotelll/Collaborative_Procedure_Alignment .

With the growing popularity of the robot operating system （ROS）， these systems are becoming increasingly complex， and the computing platforms they run on are transforming into multi-core platforms. In ROS， the order of task execution is determined by the underlying task scheduling strategy and the priorities assigned to the tasks. Minimizing the execution time of all tasks is a crucial goal in task scheduling for parallel systems. To address this challenge， we propose a reinforcement learning-based task priority assignment method， inspired by recent achievements in using reinforcement learning for handling various combinatorial optimization problems and considering the scheduling mechanisms and execution constraints of ROS2 multi-threaded executors. This method extracts the temporal and structural features of the task set， which is represented in the form of a directed acyclic graph （DAG）， and efficiently learns the ROS2 scheduling policy through a combination of policy gradient and Monte Carlo tree search methods， providing a reasonable priority setting scheme. The goal of minimizing the completion time of DAG parallel tasks is achieved through this method. The proposed method is evaluated by simulating randomly generated task graphs in a simulation platform environment. The results show that it outperforms the benchmark method. As an off-line analysis method， the method can be easily extended to more complex ROS and can find a near-optimal solution in an acceptable amount of time.

We report the radio observations of the eclipsing black widow pulsar J1720-0534, a 3.26 ms pulsar in orbit with a low mass companion of mass 0.029 to 0.034 M⊙. We obtain the phase-connected timing ephemeris and polarization profile of this millisecond pulsar(MSP) using the Five-hundred-meter Aperture Spherical radio Telescope(FAST), the Green Bank Telescope(GBT), and the Parkes Telescope. For the first time from such a system, an oscillatory polarization angle change was observed from a particular eclipse egress with partial depolarization, indicating 10-milliGauss-level reciprocating magnetic fields oscillating in a length scale of 5 ×103km(assuming an orbital inclination angle of 90°) outside the companion’s magnetosphere. The dispersion measure variation observed during the ingresses and egresses shows the rapid raising of the electron density in the shock boundary between the companion’s magnetosphere and the surrounding pulsar wind. We suggest that the observed oscillatory magnetic fields originate from the pulsar wind outside the companion’s magnetosphere.

Magnetars are neutron stars with extremely strong magnetic fields, frequently powering high-energy activity in X-rays1. Pulsed radio emission following some X-ray outbursts have been detected2,3, albeit its physical origin is unclear. It has long been speculated that the origin of magnetars’ radio signals is different from those from canonical pulsars, although convincing evidence is still lacking. Five months after magnetar SGR 1935+2154’s X-ray outburst and its associated Fast Radio Burst (FRB) 202004284,5, a radio pulsar phase was discovered6,7. Here we report the discovery of X-ray spectral hardening associated with the emergence of periodic radio pulsations from SGR 1935+2154 and a detailed analysis of the properties of the radio pulses. The complex radio pulse morphology, which contains both narrow-band emission and frequency drifts, has not been seen before in other magnetars, but is similar to those of repeating FRBs – even though the luminosities are many orders of magnitude different. The observations suggest that radio emission originates from the outer magnetosphere of the magnetar, and the surface heating due to the bombardment of inward-going particles from the radio emission region is responsible for the observed X-ray spectral hardening.