Connected component (CC) is a proper text shape representation that aligns with human reading intuition. However, CC-based text detection methods have recently faced a developmental bottleneck that their time-consuming post-processing is difficult to eliminate. To address this issue, we introduce an explicit relational reasoning network (ERRNet) to elegantly model the component relationships without post-processing. Concretely, we first represent each text instance as multiple ordered text components, and then treat these components as objects in sequential movement. In this way, scene text detection can be innovatively viewed as a tracking problem. From this perspective, we design an end-to-end tracking decoder to achieve a CC-based method dispensing with post-processing entirely. Additionally, we observe that there is an inconsistency between classification confidence and localization quality, so we propose a Polygon Monte-Carlo method to quickly and accurately evaluate the localization quality. Based on this, we introduce a position-supervised classification loss to guide the task-aligned learning of ERRNet. Experiments on challenging benchmarks demonstrate the effectiveness of our ERRNet. It consistently achieves state-of-the-art accuracy while holding highly competitive inference speed.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
Aerial Vision-Dialog Navigation (AVDN) is a new task that requires drones to navigate to a target location based on human-robot dialog history. This paper focuses on the critical fine-grained cross-modal alignment problem in AVDN, requiring the drone to align language entities with visual landmarks in top-down views. To achieve this, we first construct a Fine-Grained AVDN (FG-AVDN) dataset via a semi-automatic annotation pipeline, providing diverse multimodal annotations at the entity-landmark level. Based on this, a novel Fine-grained Entity-Landmark Alignment (FELA) method is proposed to learn the cross-modal alignment explicitly. Concretely, FELA first boosts the drone's visual understanding with a precise semantic grid representation, which captures the environmental semantics and spatial structure simultaneously. Subsequently, to learn the entity-landmark alignment, we devise cross-modal auxiliary tasks from three perspectives, including grounding, captioning, and contrastive learning. Extensive experiments demonstrate that our explicit entity-landmark alignment learning is beneficial for AVDN. As a result, FELA achieves leading performance with 3.2% SR and 4.9% GP improvements over prior arts. Code and dataset will be publicly available.
The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible. However, contemporary NLOS systems face several significant challenges: (1) The computational and storage requirements are profound due to the inherent three-dimensional grid data structure, which restricts practical application. (2) The simultaneous reconstruction of albedo and depth information requires a delicate balance using hyperparameters in the loss function, rendering the concurrent reconstruction of texture and depth information difficult. This paper introduces the innovative methodology, DG-NLOS, which integrates an albedo-focused reconstruction branch dedicated to albedo information recovery and a depth-focused reconstruction branch that extracts geometrical structure, to overcome these obstacles. The dual-branch framework segregates content delivery to the respective reconstructions, thereby enhancing the quality of the retrieved data. To our knowledge, we are the first to employ the GNN as a fundamental component to transform dense NLOS grid data into sparse structural features for efficient reconstruction. Comprehensive experiments demonstrate that our method attains the highest level of performance among existing methods across synthetic and real data.
Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive results in diverse dehazing tasks, their quadratic complexity and lack of dehazing priors pose significant drawbacks for real-world applications. In this paper, guided by triple priors, Bright Channel Prior (BCP), Dark Channel Prior (DCP), and Histogram Equalization (HE), we propose a Prior-guided Hierarchical Harmonization Network (PGHHNet) for image dehazing. PGHNet is built upon the UNet-like architecture with an efficient encoder and decoder, consisting of two module types: (1) Prior aggregation module that injects BCP/DCP and selects diverse contexts with gating attention. (2) Feature harmonization modules that subtract low-frequency components from spatial and channel aspects and learn more informative feature distributions to equalize the feature maps. Inspired by observing the sparsity of BCP/DCP and the histogram equalization, we harmonize the deep features using a histogram equation-guided module and further leverage BCP/DCP to guide spatial attention through a sandwich module as the bottleneck. Comprehensive experiments demonstrate that our model efficiently attains the highest level of performance among existing methods across four different datasets for image dehazing tasks.
EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution
PDF ↗Single hyperspectral image super-resolution (single-HSI-SR) aims to improve the resolution of a single input low-resolution HSI. Due to the bottleneck of data scarcity, the development of single-HSI-SR lags far behind that of RGB natural images. In recent years, research on RGB SR has shown that models pre-trained on large-scale benchmark datasets can greatly improve performance on unseen data, which may stand as a remedy for HSI. But how can we transfer the pre-trained RGB model to HSI, to overcome the data-scarcity bottleneck? Because of the significant difference in the channels between the pre-trained RGB model and the HSI, the model cannot focus on the correlation along the spectral dimension, thus limiting its ability to utilize on HSI. Inspired by the HSI spatial-spectral decoupling, we propose a new framework that first fine-tunes the pre-trained model with the spatial components (known as eigenimages), and then infers on unseen HSI using an iterative spectral regularization (ISR) to maintain the spectral correlation. The advantages of our method lie in: 1) we effectively inject the spatial texture processing capabilities of the pre-trained RGB model into HSI while keeping spectral fidelity, 2) learning in the spectral-decorrelated domain can improve the generalizability to spectral-agnostic data, and 3) our inference in the eigenimage domain naturally exploits the spectral low-rank property of HSI, thereby reducing the complexity. This work bridges the gap between pre-trained RGB models and HSI via eigenimages, addressing the issue of limited HSI training data, hence the name EigenSR. Extensive experiments show that EigenSR outperforms the state-of-the-art (SOTA) methods in both spatial and spectral metrics.
Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization Through Spare-Coding Transformer
PDF ↗Non-semantic features or semantic-agnostic features, which are irrelevant to image context but sensitive to image manipulations, are recognized as evidential to Image Manipulation Localization (IML). Since manual labels are impossible, existing works rely on handcrafted methods to extract non-semantic features. Handcrafted non-semantic features jeopardize IML model's generalization ability in unseen or complex scenarios. Therefore, for IML, the elephant in the room is: How to adaptively extract non-semantic features? Non-semantic features are context-irrelevant and manipulation-sensitive. That is, within an image, they are consistent across patches unless manipulation occurs. Then, spare and discrete interactions among image patches are sufficient for extracting non-semantic features. However, image semantics vary drastically on different patches, requiring dense and continuous interactions among image patches for learning semantic representations. Hence, in this paper, we propose a Sparse Vision Transformer (SparseViT), which reformulates the dense, global self-attention in ViT into a sparse, discrete manner. Such sparse self-attention breaks image semantics and forces SparseViT to adaptively extract non-semantic features for images. Besides, compared with existing IML models, the sparse self-attention mechanism largely reduced the model size (max 80% in FLOPs), achieving stunning parameter efficiency and computation reduction. Extensive experiments demonstrate that, without any handcrafted feature extractors, SparseViT is superior in both generalization and efficiency across benchmark datasets.
RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning
PDF ↗Masked point modeling methods have recently achieved great success in self-supervised learning for point cloud data. However, these methods are sensitive to rotations and often exhibit sharp performance drops when encountering rotational variations. In this paper, we propose a novel Rotation-Invariant Masked AutoEncoders (RI-MAE) to address two major challenges: 1) achieving rotation-invariant latent representations, and 2) facilitating self-supervised reconstruction in a rotation-invariant manner. For the first challenge, we introduce RI-Transformer, which features disentangled geometry content, rotation-invariant relative orientation and position embedding mechanisms for constructing rotation-invariant point cloud latent space. For the second challenge, a novel dual-branch student-teacher architecture is devised. It enables the self-supervised learning via the reconstruction of masked patches within the learned rotation-invariant latent space. Each branch is based on an RI-Transformer, and they are connected with an additional RI-Transformer predictor. The teacher encodes all point patches, while the student solely encodes unmasked ones. Finally, the predictor predicts the latent features of the masked patches using the output latent embeddings from the student, supervised by the outputs from the teacher. Extensive experiments demonstrate that our method is robust to rotations, achieving the state-of-the-art performance on various downstream tasks.
Large annotated datasets inevitably contain noisy labels, which poses a major challenge for training deep neural networks as they easily memorize the labels. Noise-robust loss functions have emerged as a notable strategy to counteract this issue, but it remains challenging to create a robust loss function which is not susceptible to underfitting. Through a quantitative approach, this paper explores the limited overlap between the network output at initialization and regions of non-vanishing gradients of bounded loss functions in the initial learning phase. Using these insights, we address underfitting of several noise robust losses with a novel method denoted as logit bias, which adds a real number epsilon to the logit at the position of the correct class. The logit bias enables these losses to achieve state-of-the-art results, even on datasets like WebVision, consisting of over a million images from 1000 classes. In addition, we demonstrate that our method can be used to determine optimal parameters for several loss functions – without having to train networks. Remarkably, our method determines the hyperparameters based on the number of classes, resulting in loss functions which require zero dataset or noise-dependent parameters.
In this work, we address unsupervised temporal action segmentation, which segments a set of long, untrimmed videos into semantically meaningful segments that are consistent across videos. While recent approaches combine representation learning and clustering in a single step for this task, they do not cope with large variations within temporal segments of the same class. To address this limitation, we propose a novel method, termed Hierarchical Vector Quantization (HVQ), that consists of two subsequent vector quantization modules. This results in a hierarchical clustering where the additional subclusters cover the variations within a cluster. We demonstrate that our approach captures the distribution of segment lengths much better than the state of the art. To this end, we introduce a new metric based on the Jensen-Shannon Distance (JSD) for unsupervised temporal action segmentation. We evaluate our approach on three public datasets, namely Breakfast, YouTube Instructional and IKEA ASM. Our approach outperforms the state of the art in terms of F1 score, recall and JSD.
Adversarial robustness in the context of Unsupervised Domain Adaptation (UDA) is particularly challenging due to the lack of labels in the target domain. Pseudo labels are often used to make adversarial robust models but compromise robustness and accuracy, falling short of the performance due to noise and inaccuracies in these pseudo labels. The main challenges in achieving robustness and accuracy include ensuring reliable pseudo labels and developing effective training methods that bring alignment between clean and adversarial examples of target data. To address these challenges, we propose a novel training method within the self-training paradigm Consistent Attention Mapping with Self Pseudo Label Refinement (CAM+SPLR). It begins with the pre-training of the UDA model, resulting in a UDA pre-trained model, which is initialized into two separate models: the Anchor model and the TargetNet model. The Anchor model encourages the attention maps of clean images and their adversarial counterparts to be similar, while the TargetNet model simultaneously performs self-training using Adversarial target data and refining the pseudo labels. CAM+SPLR improves both semantically relevant key features and pseudo-labels through a two-step stochastic gradient descent process during training. We conducted extensive experiments on benchmark datasets, including OfficeHome, PACS, and VisDA, demonstrating significant improvements in both robustness and accuracy. Our method achieves an average accuracy improvement of 6% and 8.1% and an average robustness improvement of 10.2% and 4.9%, compared to state-of-the-art methods on the PACS and VisDA datasets.
Multi-object tracking is a challenging vision task that requires simultaneous reasoning about object detection and object association. Conventional solutions use frame as the basic unit and typically rely on a motion predictor that exploits the appearance features to associate detected candidates, leading to insufficient adaptability to long-term associations. In this study, we propose a section-based multi-object tracking approach that integrates a temporal coherent Object Flow Tracker (OFTrack), capable of achieving simultaneous multi-frame tracking by treating multiple consecutive frames as the basic processing unit, denoted as a “section”. Our OFTrack boosts the optical flow to the object flow by employing object perception and section-based motion estimation strategies. Object perception adopts object-aware sampling and scale-aware correlation to enable precise target discrimination. Motion estimation models the correlation of different objects in multi-frames via specialized temporal-spatial attention to achieve robust association in very long videos. Additionally, to address the oscillation of unpredictable trajectories in multi-frame estimation, we have designed temporal coherent enhancement including the trajectory masking pre-training and the smoothing constraint on trajectory curves. Comprehensive experiments on several widely used benchmarks demonstrate the superior performance of our approach.
ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps
PDF ↗Solving jigsaw puzzles has been extensively studied. While most existing models focus on solving either small-scale puzzles or puzzles with no gap between fragments, solving large-scale puzzles with gaps presents distinctive challenges in both image understanding and combinatorial optimization. To tackle these challenges, we propose a framework of Evolutionary Reinforcement Learning with Multi-head Puzzle Perception (ERL-MPP) to derive a better set of swapping actions for solving the puzzles. Specifically, to tackle the challenges of perceiving the puzzle with gaps, a Multi-head Puzzle Perception Network (MPPN) with a shared encoder is designed, where multiple puzzlet heads comprehensively perceive the local assembly status, and a discriminator head provides a global assessment of the puzzle. To explore the large swapping action space efficiently, an Evolutionary Reinforcement Learning (EvoRL) agent is designed, where an actor recommends a set of suitable swapping actions from a large action space based on the perceived puzzle status, a critic updates the actor using the estimated rewards and the puzzle status, and an evaluator coupled with evolutionary strategies evolves the actions aligning with the historical assembly experience. The proposed ERL-MPP is comprehensively evaluated on the JPLEG-5 dataset with large gaps and the MIT dataset with large-scale puzzles. It significantly outperforms all state-of-the-art models on both datasets.
As virtual experiences grow in popularity, the demand for realistic, personalized, and animatable human avatars increases. Traditional methods, relying on fixed templates, often produce costly avatars that lack expressiveness and realism. To overcome these challenges, we introduce Controllable Avatars generation via disentangled invertible networks (CtrlAvatar), a real-time framework for generating lifelike and customizable avatars. CtrlAvatar uses disentangled invertible networks to separate the deformation process into implicit body geometry and explicit texture components. This approach eliminates the need for repeated occupancy reconstruction, enabling detailed and coherent animations. The body geometry component ensures anatomical accuracy, while the texture component allows for complex, artifact-free clothing customization. This architecture ensures smooth integration between body movements and surface details. By optimizing transformations with position-varying offsets from the avatar’s initial Linear Blend Skinning vertices, CtrlAvatar achieves flexible, natural deformations that adapt to various scenarios. Extensive experiments show that CtrlAvatar outperforms other methods in quality, diversity, controllability, and cost-efficiency, marking a significant advancement in avatar generation.
Fine-Grained Perception in Panoramic Scenes: A Novel Task, Dataset, and Method for Object Importance Ranking
PDF ↗Existing Salient Object Ranking (SOR) aims to infer ranking of salient objects based on their saliency degree. However, it tends to only focus on salient objects while neglecting non-salient ones. This coarse-grained ranking limits the performance of downstream tasks. For instance, in image retrieval tasks, focusing solely on the relationship between salient objects is insufficient for achieving fine-grained scene analysis, which may result in retrieved results that do not satisfy user requirements. High-quality retrieval requires fine-grained analysis, making it essential to rank non-salient objects. Based on this need, we propose a new task: Fine-grained Object Importance Ranking in 360 Scenes (FOIR-360), which focus on predicting the relative importance of "ALL objects'' at the instance-level. Our task takes into account all objects, allowing us to refine the original "coarse-grained'' to a "fine-grained'' level. Currently, the main challenge for this new task is the lack of supervised data for model training or even for model testing. Therefore, we propose a novel weakly supervised method to address the shortage of datasets. Furthermore, to the best of our knowledge, there is no existing suitable annotation protocol for this new task. The main reason is that annotating fine-grained rankings is extremely difficult, especially in panoramic scenes that contain numerous instances where even humans are unable to determine which one is more important than others. As the first attempt, we introduce a new annotation protocol designed to highlight the ranking of objects that are non-salient yet still important. Based on this protocol, we construct the first fine-grained 360Rank dataset. In summary, all these new task, weakly supervised method, annotation protocol, and dataset have the potential to drive advancements in the field.
Video Action Detection (VAD) entails localizing and categorizing action instances within videos, which inherently consist of diverse information sources such as audio, visual cues, and surrounding scene contexts. Leveraging this multi-modal information effectively for VAD poses a significant challenge, as the model must identify action-relevant cues with precision. In this study, we introduce a novel multi-modal VAD architecture, referred to as the Joint Actor-centric Visual, Audio, Language Encoder (JoVALE). JoVALE is the first VAD method to integrate audio and visual features with scene descriptive context sourced from large-capacity image captioning models. At the heart of JoVALE is the actor-centric aggregation of audio, visual, and scene descriptive information, enabling adaptive integration of crucial features for recognizing each actor's actions. We have developed a Transformer-based architecture, the Actor-centric Multi-modal Fusion Network, specifically designed to capture the dynamic interactions among actors and their multi-modal contexts. Our evaluation on three prominent VAD benchmarks—AVA, UCF101-24, and JHMDB51-21—demonstrates that incorporating multi-modal information significantly enhances performance, setting new state-of-the-art performances in the field.
SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living
PDF ↗The introduction of vision-language models like CLIP has enabled the development of foundational video models capable of generalizing to unseen videos and human actions. However, these models are typically trained on web videos, which often fail to capture the challenges present in Activities of Daily Living (ADL) videos. Existing works address ADL-specific challenges, such as similar appearances, subtle motion patterns, and multiple viewpoints, by combining 3D skeletons and RGB videos. However, these approaches are not integrated with language, limiting their ability to generalize to unseen action classes. In this paper, we introduce SKI models, which integrate 3D skeletons into the vision-language embedding space. SKI models leverage a skeleton-language model, SkeletonCLIP, to infuse skeleton information into Vision Language Models (VLMs) and Large Vision Language Models (LVLMs) through collaborative training. Notably, SKI models do not require skeleton data during inference, enhancing their robustness for real-world applications. The effectiveness of SKI models is validated on three popular ADL datasets for zero-shot action recognition and video caption generation tasks.
OGP-Net: Optical Guidance Meets Pixel-Level Contrastive Distillation for Robust Multi-Modal and Missing Modality Segmentation
PDF ↗Enhancing the performance of semantic segmentation models with multi-spectral images (RGB-IR) is crucial, particularly for low-light and adverse environments. While multi-modal fusion techniques aim to learn cross-modality features for generating fused images or engage in knowledge distillation, they often treat multi-modal and missing modality scenarios as separate challenges, which is not an optimal approach. To address this, a novel multi-modal fusion approach called Optically-Guided Pixel-level contrastive learning Network (OGP-Net) is proposed, which uses Distillation with Multi-View Contrastive (DMC) and Distillation for Uni-modal Re- tention (DUR) to maintain the correlation between modality-shared and modality-specific features. DMC aligns the uni-modal features by projecting the semantic information across modalities into a unified latent space, ensuring that the feature maps retain multi-modal representations. Pixel-level multi-view contrastive learning is introduced to enable modality-invariant representation learning. To retain modality-specific information, DUR is proposed, which distills detailed textures from RGB images into the optical branch of OGP-Net. Additionally, the Gated Spectral Unit (GSU) is integrated into the framework to eliminate the need for manual tuning and avoid forced feature alignment. Comprehensive experiments show that OGP-Net outperforms state-of-the-art models in multi-modal and missing modality scenarios across three public benchmarking datasets. It achieves quicker convergence and learns efficiently from limited training samples.
SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection
PDF ↗Unsupervised camouflaged object detection (UCOD) poses significant challenges, primarily attributed to the absence of human labels. Existing UCOD methodologies, leveraging attention mechanisms, often struggle to achieve precise localization of camouflaged objects. To overcome this limitation, we introduce a groundbreaking fully unsupervised algorithm for attention-guided camouflaged object localization, shift, and inference, termed the self-distilled attention localization and shift network (SdalsNet). In this study, we formulate an attention localization methodology aimed at accurately identifying the central coordinate of the camouflaged object. Furthermore, we propose four distinct loss functions tailored to refine the precision of attentional positioning. These loss functions effectively constrain the distances between three types of class tokens, facilitating seamless attentional shifting across the input sample. Additionally, we design a sophisticated prediction inference technique to reconstruct the binary output of an attention map, thereby providing a comprehensive understanding of the detected camouflaged objects. Experimental results on four challenging COD benchmark datasets corroborate the effectiveness of our proposed approach, demonstrating notable superiority over state-of-the-art methods.
Diffusion Models have emerged as powerful generative models for high-quality image synthesis, with many subsequent image editing techniques based on them. However, the ease of text-based image editing introduces significant risks, such as malicious editing for scams or intellectual property infringement. Previous works have attempted to safeguard images from diffusion-based editing by adding imperceptible perturbations. These methods are costly and specifically target prevalent Latent Diffusion Models (LDMs), while Pixel-domain Diffusion Models (PDMs) remain largely unexplored and robust against such attacks. Our work addresses this gap by proposing a novel attack framework, AtkPDM. AtkPDM is mainly composed of a feature representation attacking loss that exploits vulnerabilities in denoising UNets and a latent optimization strategy to enhance the naturalness of adversarial images. Extensive experiments demonstrate the effectiveness of our approach in attacking dominant PDM-based editing methods (e.g., SDEdit) while maintaining reasonable fidelity and robustness against common defense methods. Additionally, our framework is extensible to LDMs, achieving comparable performance to existing approaches.
The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it does not directly enhance or enrich the features of tiny objects. Furthermore, FPN lacks spatial perception ability. To address these issues, we propose a novel High Frequency and Spatial Perception Feature Pyramid Network (HS-FPN) with two innovative modules. First, we designed a high frequency perception module (HFP) that generates high frequency responses through high pass filters. These high frequency responses are used as mask weights from both spatial and channel perspectives to enrich and highlight the features of tiny objects in the original feature maps. Second, we developed a spatial dependency perception module (SDP) to capture the spatial dependencies that FPN lacks. Our experiments demonstrate that detectors based on HS-FPN exhibit competitive advantages over state-of-the-art models on the AI-TOD dataset for tiny object detection.