Text-in-image editing has become a key capability for visual content creation, yet existing benchmarks remain overwhelmingly English-centric and often conflate visual plausibility with semantic correctness. We introduce MULTITEXTEDIT, a controlled benchmark of 3,600 instances spanning 12 typologically diverse languages, 5 visual domains, and 7 editing operations. Language variants of each instance share a common visual base and are paired with a human-edited reference and region masks, isolating the language variable for cross-lingual comparison. To capture script-level errors that coarse text-matching metrics miss, such as missing diacritics, reversed RTL order, and mixed-script renderings, we introduce a language fidelity (LSF) metric scored by a two-stage LVM protocol that first traces the edited target text and then judges it in isolation, reaching a quadratic-weighted ąp̨p̨ą of 0.76 against native-speaker annotators. Evaluating 12 open-source and proprietary systems with LSF alongside standard semantic and mask-aware pixel metrics, we find pronounced cross-lingual degradation for every model, largest on Hebrew and Arabic and smallest on Dutch and Spanish, and concentrated in text accuracy and script fidelity rather than in coarse structural dimensions. We also uncover a pervasive semantic and pixel mismatch, where outputs preserve global layout and background fidelity yet distort script-specific forms.

Multimodal Large Language Models (MLLM) often struggle to interpret high-resolution images accurately, where fine-grained details are crucial for complex visual understanding. We introduce Zoom-Refine, a novel training-free method that enhances MLLM capabilities to address this issue. Zoom-Refine operates through a synergistic process of \textit{Localized Zoom} and \textit{Self-Refinement}. In the \textit{Localized Zoom} step, Zoom-Refine leverages the MLLM to provide a preliminary response to an input query and identifies the most task-relevant image region by predicting its bounding box coordinates. During the \textit{Self-Refinement} step, Zoom-Refine then integrates fine-grained details from the high-resolution crop (identified by \textit{Localized Zoom}) with its initial reasoning to re-evaluate and refine its preliminary response. Our method harnesses the MLLM's inherent capabilities for spatial localization, contextual reasoning and comparative analysis without requiring additional training or external experts. Comprehensive experiments demonstrate the efficacy of Zoom-Refine on two challenging high-resolution multimodal benchmarks. Code is available at \href{https://github.com/xavier-yu114/Zoom-Refine}{\color{magenta}github.com/xavier-yu114/Zoom-Refine}

In the task of classifying histological images, prior works widely leverage Graph neural network (GNN) to aggregate histological knowledge from multi-level biological entities (e.g., cell and tissue). However, current GNN-based methods suffer from either inadequate entity representation or intolerable computation burden. To the end, we propose a heterogeneous knowledge distillation (HKD) model to capture and amalgamate the spatial-hierarchical feature of multi-level biological entities. We first design multiple message-passing GNNs with different hidden layers as the teachers for extracting adjacent regions of cells, and leverage a transformer-based GNN as the student to model the global interaction of tissues. Such multi-teacher student architecture enables our HKD to simultaneously obtain topological knowledge at different scales from heterogeneous biological entities. We further propose a biological affiliation recognition module to adaptively align the cell knowledge learned from multi-teacher models with cell-corresponding tissue in the student model, encouraging the student model to attentively amalgamate the semantics of multi-level biological entities for highly accurate classification. Extensive experiments show that our method outperforms the state-of-the-art on three public datasets of histological image classification.

Visual Question Answering (VQA) presents a challenging task at the intersection of computer vision and natural language processing, aiming to bridge the semantic gap between visual perception and linguistic comprehension. Traditional VQA approaches do not distinguish between data processing and reasoning, limiting their interpretability and generalizability in complex and diverse scenarios. Conversely, Programmatic Visual Question Answering (PVQA) models leverage large language models (LLMs) to generate executable codes, providing answers with detailed and interpretable reasoning processes. However, existing PVQA models typically rely on simplistic input-output prompting, which struggles to elicit domain-specific knowledge from LLMs and often produces unclear or extraneous outputs. Furthermore, PVQA models typically rely on a basic in-context example (ICE) selection methodology that is heavily influenced by individual word similarity rather than the overall sentence context. This leads to suboptimal ICE selection and a reliance on dataset-specific ICE candidates. In this paper, we propose ContextualCoder, a novel prompting framework tailored for PVQA models. ContextualCoder leverages frozen LLMs for code generation and pre-trained visual models for code execution, eliminating the need for extensive training and enhancing model flexibility. By incorporating an innovative prompting methodology and a novel ICE selection strategy, ContextualCoder facilitates the use of diverse in-context information for code generation, thereby improving the performance of PVQA models. Our approach surpasses state-of-the-art models, as evidenced by comprehensive experiments across diverse VQA datasets, including multilingual scenarios.

Data-limited semi-supervised learning tends to be severely degraded by miscalibration (i.e., misalignment between confidence and correctness of predicted pseudo labels) and stuck at poor local minima while learning from the same set of over-confident yet incorrect pseudo labels repeatedly. We design a simple and effective self-paced sampling technique that can greatly alleviate the impact of miscalibration and learn more accurate semi-supervised models from limited training data. Instead of employing static or dynamic confidence thresholds which is sensitive to miscalibration, the proposed self-paced sampling follows a simple linear policy to select pseudo labels which eases repeated learning from the same set of falsely predicted pseudo labels at the early training stage and lowers the chance of being stuck at local minima effectively. Despite its simplicity, extensive evaluations over multiple data-limited semi-supervised tasks show the proposed self-paced sampling outperforms the state-of-the-art consistently by large margins.

Domain adaptive LiDAR point cloud segmentation aims to learn an effective target segmentation model from labelled source data and unlabelled target data, which has attracted increasing attention in recent years due to the difficulty in point-cloud annotation. It remains a very open research challenge as point clouds of different domains often have clear distribution discrepancies with variations in LiDAR sensor configurations, environmental conditions, occlusions, etc. We design a simple yet effective spatial consistency training framework that can learn superior domain-invariant feature representations from unlabelled target point clouds. The framework exploits three types of spatial consistency, namely, geometric-transform consistency, sparsity consistency, and mixing consistency which capture the semantic invariance of point clouds with respect to viewpoint changes, sparsity changes, and local context changes, respectively. With a concise mean teacher learning strategy, our experiments show that the proposed spatial consistency training outperforms the state-of-the-art significantly and consistently across multiple public benchmarks. Code is available at https://github.com/xiaoaoran/sct-uda .

Open-vocabulary object detection aims to train a detector capable of recognizing various novel classes. Most existing studies exploit image-level weak supervision to generate pseudo object boxes for novel class training. However, the generated pseudo boxes are often noisy and biased towards base classes, leading to sub-optimal open-vocabulary detectors. We propose DCS, a novel Debiased Curriculum Self-Training technique that generates pseudo object boxes progressively and adaptively for training accurate open-vocabulary detectors. DCS consists of two complementary designs, namely, progressive pseudo-label filtering (PPF) and adaptive pseudo-label selection (APS). Specifically, PPF discards confident but mismatched detection progressively at the early training stage when the trained detector is biased towards the base classes, APS instead fuses class-aware and class-agnostic pseudo labels by prioritizing class-aware pseudo labels at the late training stage when the detector can better recognize novel classes. Without bells and whistles, DCS achieves superior detection performance over two open-vocabulary detection benchmarks.

Test-time adaptation with pre-trained vision-language models has attracted increasing attention for tackling distribution shifts during the test time. Though prior studies have achieved very promising performance, they in-volve intensive computation which is severely unaligned with test-time adaptation. We design TDA, a training-free dynamic adapter that enables effective and efficient test-time adaptation with vision-language models. TDA works with a lightweight key-value cache that maintains a dy-namic queue with few-shot pseudo labels as values and the corresponding test-sample features as keys. Leveraging the key-value cache, TDA allows adapting to test data gradually via progressive pseudo label refinement which is super-efficient without incurring any backpropagation. In addition, we introduce negative pseudo labeling that alleviates the adverse impact of pseudo label noises by assigning pseudo labels to certain negative classes when the model is uncertain about its pseudo label predictions. Extensive experiments over two benchmarks demonstrate TDA's superior effectiveness and efficiency as compared with the state-of-the-art. The code has been released in https://kdiaaa.github.io/tda/

Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning on data in common image styles. However, their robustness against diverse style shifts, crucial for practical applications, remains largely unexplored. In this paper, we propose a new benchmark, BenchLMM, to assess the robustness of LMMs toward three different styles: artistic image style, imaging sensor style, and application style. Utilizing BenchLMM, we comprehensively evaluate state-of-the-art LMMs and reveal: 1) LMMs generally suffer performance degradation when working with other styles; 2) An LMM performs better than another model in common style does not guarantee its superior performance in other styles; 3) LMMs' reasoning capability can be enhanced by prompting LMMs to predict the style first, based on which we propose a versatile and training-free method for improving LMMs; 4) An intelligent LMM is expected to interpret the causes of its errors when facing stylistic variations. We hope that our benchmark and analysis can shed new light on developing more intelligent and versatile LMMs. The benchmark and evaluation have been released on https://github.com/AIFEG/BenchLMM

Face retouching aims to remove facial blemishes, such as pigmentation and acne, and still retain fine-grain texture details. Nevertheless, existing methods just remove the blemishes but focus little on realism of the intermediate process, limiting their use more to beautifying facial images on social media rather than being effective tools for simulating changes in facial pigmentation and ance. Motivated by this limitation, we propose our Controllable and Gradual Face Retouching (CGFR). Our CGFR is based on physical modelling, adopting Sum-of-Gaussians to approximate skin subsurface scattering in a decomposed melanin and haemoglobin color space. Our CGFR offers a user-friendly control over the facial blemishes, achieving realistic and gradual blemishes retouching. Experimental results based on actual clinical data shows that CGFR can realistically simulate the blemishes' gradual recovering process.

Visible and Infrared Image Fusion (VIF) has garnered significant interest across a wide range of high-level vision tasks, such as object detection and semantic segmentation. However, the evaluation of VIF methods remains challenging due to the absence of ground truth. This paper proposes a Segmentation-oriented Evaluation Approach (SEA) to assess VIF methods by incorporating the semantic segmentation task and leveraging segmentation labels available in latest VIF datasets. Specifically, SEA utilizes universal segmentation models, capable of handling diverse images and classes, to predict segmentation outputs from fused images and compare these outputs with segmentation labels. Our evaluation of recent VIF methods using SEA reveals that their performance is comparable or even inferior to using visible images only, despite nearly half of the infrared images demonstrating better performance than visible images. Further analysis indicates that the two metrics most correlated to our SEA are the gradient-based fusion metric Q_ABF and the visual information fidelity metric Q_VIFF in conventional VIF evaluation metrics, which can serve as proxies when segmentation labels are unavailable. We hope that our evaluation will guide the development of novel and practical VIF methods. The code has been released in .

Domain adaptive LiDAR point cloud segmentation aims to learn a target segmentation model from labeled source point clouds and unlabelled target point clouds, which has recently attracted increasing attention due to various challenges in point cloud annotation. However, its performance is still very constrained as most existing studies did not well capture data-specific characteristics of LiDAR point clouds. Inspired by the observation that the domain discrepancy of LiDAR point clouds is highly correlated with point density, we design a density-aware self-training (DAST) technique that introduces point density into the self-training framework for domain adaptive point cloud segmentation. DAST consists of two novel and complementary designs. The first is density-aware pseudo labelling that introduces point density for accurate pseudo labelling of target data and effective self-supervised network retraining. The second is density-aware consistency regularization that encourages to learn density-invariant representations by enforcing target predictions to be consistent across points of different densities. Extensive experiments over multiple large-scale public datasets show that DAST achieves superior domain adaptation performance as compared with the state-of-the-art.

Robust point cloud parsing under all-weather conditions is crucial to level-5 autonomy in autonomous driving. However, how to learn a universal 3D semantic segmentation (3DSS) model is largely neglected as most existing benchmarks are dominated by point clouds captured under normal weather. We introduce SemanticSTF, an adverse-weather point cloud dataset that provides dense point-level annotations and allows to study 3DSS under various adverse weather conditions. We study all-weather 3DSS modeling under two setups: 1) domain adaptive 3DSS that adapts from normal-weather data to adverse-weather data; 2) domain generalizable 3DSS that learns all-weather 3DSS models from normal-weather data. Our studies reveal the challenge while existing 3DSS methods encounter adverse-weather data, showing the great value of SemanticSTF in steering the future endeavor along this very meaningful research direction. In addition, we design a domain randomization technique that alternatively randomizes the geometry styles of point clouds and aggregates their embeddings, ultimately leading to a generalizable model that can improve 3DSS under various adverse weather effectively. The SemanticSTF and related codes are available at https: //github.com/xiaoaoran/SemanticSTF.

Recent advances in large-scale vision-language models have achieved very impressive performance in various zero-shot image classification tasks. While prior studies have demonstrated significant improvements by introducing few-shot labelled target samples, they still require labelling of target samples, which greatly degrades their scalability while handling various visual recognition tasks. We design NtUA, a Noise-tolerant Unsupervised Adapter that allows learning superior target models with few-shot unlabelled target samples. NtUA works as a key-value cache that formulates visual features and predicted pseudo-labels of the few-shot unlabelled target samples as key-value pairs. It consists of two complementary designs. The first is adaptive cache formation that combats pseudo-label noises by weighting the key-value pairs according to their prediction confidence. The second is pseudo-label rectification, which corrects both pair values (i.e., pseudo-labels) and cache weights by leveraging knowledge distillation from large-scale vision language models. Extensive experiments show that NtUA achieves superior performance consistently across multiple widely adopted benchmarks.

Point cloud data have been widely explored due to its superior accuracy and robustness under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved very impressive success in various applications such as surveillance and autonomous driving. The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data. Unsupervised point cloud representation learning, which aims to learn general and useful point cloud representations from unlabelled point cloud data, has recently attracted increasing attention due to the constraint in large-scale point cloud labelling. This paper provides a comprehensive review of unsupervised point cloud representation learning using DNNs. It first describes the motivation, general pipelines as well as terminologies of the recent studies. Relevant background including widely adopted point cloud datasets and DNN architectures is then briefly presented. This is followed by an extensive discussion of existing unsupervised point cloud representation learning methods according to their technical approaches. We also quantitatively benchmark and discuss the reviewed methods over multiple widely adopted point cloud datasets. Finally, we share our humble opinion about several challenges and problems that could be pursued in the future research in unsupervised point cloud representation learning.

Training deep neural networks (DNNs) with noisy labels often leads to poorly generalized models as DNNs tend to memorize the noisy labels in training. Various strategies have been developed for improving sample selection precision and mitigating the noisy label memorization issue. However, most existing works adopt a class-dependent softmax classifier that is vulnerable to noisy labels by entangling the classification of multi-class features. This paper presents a class-independent regularization (CIR) method that can effectively alleviate the negative impact of noisy labels in DNN training. CIR regularizes the class-dependent softmax classifier by introducing multi-binary classifiers each of which takes care of one class only. Thanks to its class-independent nature, CIR is tolerant to noisy labels as misclassification by one binary classifier does not affect others. For effective training of CIR, we design a heterogeneous adaptive co-teaching strategy that forces the class-independent and class-dependent classifiers to focus on sample selection and image classification, respectively, in a cooperative manner. Extensive experiments show that CIR achieves superior performance consistently across multiple benchmarks with both synthetic and real images. Code is available at https://github.com/RumengYi/CIR.

Video semantic segmentation has witnessed substantial advancements, largely due to the vast volume of labeled training samples. Nevertheless, domain adaptive video segmentation that adapts from a labeled source domain to an unlabeled target domain remains insufficiently delved into. In this paper, we propose Temporality-guided Masked Image Consistency (TgMIC), a simple yet effective approach that leverages the concept of Masked Image Modeling (MIM) to learn semantic features in the target domain. Unlike random masking strategy applied in traditional MIM, TgMIC introduces a novel temporality-guided masking strategy that samples the mask according to the distribution of optical flow, which facilitate the learning of spatial context relations in video sequence. Specifically, TgMIC masks the patches in vision transformers where the variance of optical flow is large, as these patches are known to contain noisy estimates of optical flow. In order to learn semantic information for video segmentation, TgMIC reconstructs the predictions of original frames from the masked frames. Comprehensive tests and detailed analysis on various public datasets show that our mechanism stands out, outpacing contemporaneous techniques, while ensuring no additional time costs.

Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and target distributions at a global image level but neglect the inconsistency around local image regions. This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. MLAN has two novel designs, namely, region-level adversarial learning (RL-AL) and co-regularized adversarial learning (CR-AL). Specifically, RL-AL models prototypical regional context-relations explicitly in the feature space of a labelled source domain and transfers them to an unlabelled target domain via adversarial learning. CR-AL fuses region-level AL and image-level AL optimally via mutual regularization. In addition, we design a multi-level consistency map that can guide domain adaptation in both input space (i.e., image-to-image translation) and output space (i.e., self-training) effectively. Extensive experiments show that MLAN outperforms the state-of-the-art with a large margin consistently across multiple datasets.

Knowledge transfer from synthetic to real data has been widely studied to mitigate data annotation constraints in various computer vision tasks such as semantic segmentation. However, the study focused on 2D images and its counterpart in 3D point clouds segmentation lags far behind due to the lack of large-scale synthetic datasets and effective transfer methods. We address this issue by collecting SynLiDAR, a large-scale synthetic LiDAR dataset that contains point-wise annotated point clouds with accurate geometric shapes and comprehensive semantic classes. SynLiDAR was collected from multiple virtual environments with rich scenes and layouts which consists of over 19 billion points of 32 semantic classes. In addition, we design PCT, a novel point cloud translator that effectively mitigates the gap between synthetic and real point clouds. Specifically, we decompose the synthetic-to-real gap into an appearance component and a sparsity component and handle them separately which improves the point cloud translation greatly. We conducted extensive experiments over three transfer learning setups including data augmentation, semi-supervised domain adaptation and unsupervised domain adaptation. Extensive experiments show that SynLiDAR provides a high-quality data source for studying 3D transfer and the proposed PCT achieves superior point cloud translation consistently across the three setups. The dataset is available at https://github.com/xiaoaoran/SynLiDAR.

LiDAR point clouds, which are usually scanned by rotating LiDAR sensors continuously, capture precise geometry of the surrounding environment and are crucial to many autonomous detection and navigation tasks. Though many 3D deep architectures have been developed, efficient collection and annotation of large amounts of point clouds remain one major challenge in the analytic and understanding of point cloud data. This paper presents PolarMix, a point cloud augmentation technique that is simple and generic but can mitigate the data constraint effectively across different perception tasks and scenarios. PolarMix enriches point cloud distributions and preserves point cloud fidelity via two cross-scan augmentation strategies that cut, edit, and mix point clouds along the scanning direction. The first is scene-level swapping which exchanges point cloud sectors of two LiDAR scans that are cut along the azimuth axis. The second is instance-level rotation and paste which crops point instances from one LiDAR scan, rotates them by multiple angles (to create multiple copies), and paste the rotated point instances into other scans. Extensive experiments show that PolarMix achieves superior performance consistently across different perception tasks and scenarios. In addition, it can work as plug-and-play for various 3D deep architectures and also performs well for unsupervised domain adaptation.