Channel attention mechanisms endeavor to recalibrate channel weights to enhance representation abilities of networks. However, mainstream methods often rely solely on global average pooling as the feature squeezer, which significantly limits the overall potential of models. In this paper, we investigate the statistical moments of feature maps within a neural network. Our findings highlight the critical role of high-order moments in enhancing model capacity. Consequently, we introduce a flexible and comprehensive mechanism termed Extensive Moment Aggregation (EMA) to capture the global spatial context. Building upon this mechanism, we propose the Moment Channel Attention (MCA) framework, which efficiently incorporates multiple levels of moment-based information while minimizing additional computation costs through our Cross Moment Convolution (CMC) module. The CMC module via channel-wise convolution layer to capture multiple order moment information as well as cross channel features. The MCA block is designed to be lightweight and easily integrated into a variety of neural network architectures. Experimental results on classical image classification, object detection, and instance segmentation tasks demonstrate that our proposed method achieves state-of-the-art results, outperforming existing channel attention methods.
论文检索
输入标题、作者或关键词，从 5,999 篇学术成果中精准定位
MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving
PDF ↗Instance segmentation is a fundamental research in computer vision, especially in autonomous driving. However, manual mask annotation for instance segmentation is quite time-consuming and costly. To address this problem, some prior works attempt to apply weakly supervised manner by exploring 2D or 3D boxes. However, no one has ever successfully segmented 2D and 3D instances simultaneously by only using 2D box annotations, which could further reduce the annotation cost by an order of magnitude. Thus, we propose a novel framework called Multimodal Weakly Supervised Instance Segmentation (MWSIS), which incorporates various fine-grained label correction modules for both 2D and 3D modalities, along with a new multimodal cross-supervision approach. In the 2D pseudo label generation branch, the Instance-based Pseudo Mask Generation (IPG) module utilizes predictions for self-supervised correction. Similarly, in the 3D pseudo label generation branch, the Spatial-based Pseudo Label Generation (SPG) module generates pseudo labels by incorporating the spatial prior information of the point cloud. To further refine the generated pseudo labels, the Point-based Voting Label Correction (PVC) module utilizes historical predictions for correction. Additionally, a Ring Segment-based Label Correction (RSC) module is proposed to refine the predictions by leveraging the depth prior information from the point cloud. Finally, the Consistency Sparse Cross-modal Supervision (CSCS) module reduces the inconsistency of multimodal predictions by response distillation. Particularly, transferring the 3D backbone to downstream tasks not only improves the performance of the 3D detectors, but also outperforms fully supervised instance segmentation with only 5% fully supervised annotations. On the Waymo dataset, the proposed framework demonstrates significant improvements over the baseline, especially achieving 2.59% mAP and 12.75% mAP increases for 2D and 3D instance segmentation tasks, respectively. The code is available at https://github.com/jiangxb98/mwsis-plugin.
The pretrain-finetune paradigm has achieved great success in NLP and 2D image fields because of the high-quality representation ability and transferability of their pretrained models. However, pretraining such a strong model is difficult in the 3D point cloud field due to the limited amount of point cloud sequences. This paper introduces Efficient Point Cloud Learning (EPCL), an effective and efficient point cloud learner for directly training high-quality point cloud models with a frozen CLIP transformer. Our EPCL connects the 2D and 3D modalities by semantically aligning the image features and point cloud features without paired 2D-3D data. Specifically, the input point cloud is divided into a series of local patches, which are converted to token embeddings by the designed point cloud tokenizer. These token embeddings are concatenated with a task token and fed into the frozen CLIP transformer to learn point cloud representation. The intuition is that the proposed point cloud tokenizer projects the input point cloud into a unified token space that is similar to the 2D images. Comprehensive experiments on 3D detection, semantic segmentation, classification and few-shot learning demonstrate that the CLIP transformer can serve as an efficient point cloud encoder and our method achieves promising performance on both indoor and outdoor benchmarks. In particular, performance gains brought by our EPCL are 19.7 AP50 on ScanNet V2 detection, 4.4 mIoU on S3DIS segmentation and 1.2 mIoU on SemanticKITTI segmentation compared to contemporary pretrained models. Code is available at \url{https://github.com/XiaoshuiHuang/EPCL}.
Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation
PDF ↗Semi-supervised learning (SSL), as one of the dominant methods, aims at leveraging the unlabeled data to deal with the annotation dilemma of supervised learning, which has attracted much attentions in the medical image segmentation. Most of the existing approaches leverage a unitary network by convolutional neural networks (CNNs) with compulsory consistency of the predictions through small perturbations applied to inputs or models. The penalties of such a learning paradigm are that (1) CNN-based models place severe limitations on global learning; (2) rich and diverse class-level distributions are inhibited. In this paper, we present a novel CNN-Transformer learning framework in the manifold space for semi-supervised medical image segmentation. First, at intra-student level, we propose a novel class-wise consistency loss to facilitate the learning of both discriminative and compact target feature representations. Then, at inter-student level, we align the CNN and Transformer features using a prototype-based optimal transport method. Extensive experiments show that our method outperforms previous state-of-the-art methods on three public medical image segmentation benchmarks.
SpaceGTN: A Time-Agnostic Graph Transformer Network for Handwritten Diagram Recognition and Segmentation
PDF ↗Online handwriting recognition is pivotal in domains like note-taking, education, healthcare, and office tasks. Existing diagram recognition algorithms mainly rely on the temporal information of strokes, resulting in a decline in recognition performance when dealing with notes that have been modified or have no temporal information. The current datasets are drawn based on templates and cannot reflect the real free-drawing situation. To address these challenges, we present SpaceGTN, a time-agnostic Graph Transformer Network, leveraging spatial integration and removing the need for temporal data. Extensive experiments on multiple datasets have demonstrated that our method consistently outperforms existing methods and achieves state-of-the-art performance. We also propose a pipeline that seamlessly connects offline and online handwritten diagrams. By integrating a stroke restoration technique with SpaceGTN, it enables intelligent editing of previously uneditable offline diagrams at the stroke level. In addition, we have also launched the first online handwritten diagram dataset, OHSD, which is collected using a free-drawing method and comes with modification annotations.
Zero-shot Natural Language-Video Localization (NLVL) methods have exhibited promising results in training NLVL models exclusively with raw video data by dynamically generating video segments and pseudo-query annotations. However, existing pseudo-queries often lack grounding in the source video, resulting in unstructured and disjointed content. In this paper, we investigate the effectiveness of commonsense reasoning in zero-shot NLVL. Specifically, we present CORONET, a zero-shot NLVL framework that leverages commonsense to bridge the gap between videos and generated pseudo-queries via a commonsense enhancement module. CORONET employs Graph Convolution Networks (GCN) to encode commonsense information extracted from a knowledge graph, conditioned on the video, and cross-attention mechanisms to enhance the encoded video and pseudo-query representations prior to localization. Through empirical evaluations on two benchmark datasets, we demonstrate that CORONET surpasses both zero-shot and weakly supervised baselines, achieving improvements up to 32.13% across various recall thresholds and up to 6.33% in mIoU. These results underscore the significance of leveraging commonsense reasoning for zero-shot NLVL.
Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis
PDF ↗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.
Multi-modal image segmentation is one of the core issues in computer vision. The main challenge lies in integrating common information between modalities while retaining specific patterns for each modality. Existing methods typically perform full fine-tuning on RGB-based pre-trained parameters to inherit the powerful representation of the foundation model. Although effective, such paradigm is not optimal due to weak transferability and scarce downstream data. Inspired by the recent success of prompt learning in language models, we propose the Grouping Prompt Tuning Framework (GoPT), which introduces explicit semantic grouping to learn modal-related prompts, adapting the frozen pre-trained foundation model to various downstream multi-modal segmentation tasks. Specifically, a class-aware uni-modal prompter is designed to balance intra- and inter-modal semantic propagation by grouping modality-specific class tokens, thereby improving the adaptability of spatial information. Furthermore, an alignment-induced cross-modal prompter is introduced to aggregate class-aware representations and share prompt parameters among different modalities to assist in modeling common statistics. Extensive experiments show the superiority of our GoPT, which achieves SOTA performance on various downstream multi-modal image segmentation tasks by training only < 1% model parameters.
Compared to conventional semantic segmentation with pixel-level supervision, weakly supervised semantic segmentation (WSSS) with image-level labels poses the challenge that it commonly focuses on the most discriminative regions, resulting in a disparity between weakly and fully supervision scenarios. A typical manifestation is the diminished precision on object boundaries, leading to deteriorated accuracy of WSSS. To alleviate this issue, we propose to adaptively partition the image content into certain regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing. For uncertain cues, we propose an adaptive masking strategy and seek to recover the local information with self-distilled knowledge. We further assume that confident regions should be robust enough to preserve the global semantics, and introduce a complementary self-distillation method that constrains semantic consistency between confident regions and an augmented view with the same class labels. Extensive experiments conducted on PASCAL VOC 2012 and MS COCO 2014 demonstrate that our proposed single-stage approach for WSSS not only outperforms state-of-the-art counterparts but also surpasses multi-stage methods that trade complexity for accuracy.
The aim of audio-visual segmentation (AVS) is to precisely differentiate audible objects within videos down to the pixel level. Traditional approaches often tackle this challenge by combining information from various modalities, where the contribution of each modality is implicitly or explicitly modeled. Nevertheless, the interconnections between different modalities tend to be overlooked in audio-visual modeling. In this paper, inspired by the human ability to mentally simulate the sound of an object and its visual appearance, we introduce a bidirectional generation framework. This framework establishes robust correlations between an object's visual characteristics and its associated sound, thereby enhancing the performance of AVS. To achieve this, we employ a visual-to-audio projection component that reconstructs audio features from object segmentation masks and minimizes reconstruction errors. Moreover, recognizing that many sounds are linked to object movements, we introduce an implicit volumetric motion estimation module to handle temporal dynamics that may be challenging to capture using conventional optical flow methods. To showcase the effectiveness of our approach, we conduct comprehensive experiments and analyses on the widely recognized AVSBench benchmark. As a result, we establish a new state-of-the-art performance level in the AVS benchmark, particularly excelling in the challenging MS3 subset which involves segmenting multiple sound sources. Code is released in: https://github.com/OpenNLPLab/AVS-bidirectional.
Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly. Project Page: https://vinayak-vg.github.io/GSN/
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the shared information among multiple augmented views of samples, while disregarding the non-shared information that may be beneficial for downstream tasks. To address this issue, we introduce a module called CompMod with Meta Comprehensive Regularization (MCR), embedded into existing self-supervised frameworks, to make the learned representations more comprehensive. Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features. Additionally, guided by the constrained extraction of features using maximum entropy coding, the self-supervised learning model learns more comprehensive features on top of learning consistent features. In addition, we provide theoretical support for our proposed method from information theory and causal counterfactual perspective. Experimental results show that our method achieves significant improvement in classification, object detection and semantic segmentation tasks on multiple benchmark datasets.
Salient Object Ranking (SOR) is the process of predicting the order of an observer's attention to objects when viewing a complex scene. Existing SOR methods primarily focus on ranking various scene objects simultaneously by exploring their spatial and semantic properties. However, their solutions of simultaneously ranking all salient objects do not align with human viewing behavior, and may result in incorrect attention shift predictions. We observe that humans view a scene through a sequential and continuous process involving a cycle of foveating to objects of interest with our foveal vision while using peripheral vision to prepare for the next fixation location. For instance, when we see a flying kite, our foveal vision captures the kite itself, while our peripheral vision can help us locate the person controlling it such that we can smoothly divert our attention to it next. By repeatedly carrying out this cycle, we can gain a thorough understanding of the entire scene. Based on this observation, we propose to model the dynamic interplay between foveal and peripheral vision to predict human attention shifts sequentially. To this end, we propose a novel SOR model, SeqRank, which reproduces foveal vision to extract high-acuity visual features for accurate salient instance segmentation while also modeling peripheral vision to select the object that is likely to grab the viewer’s attention next. By incorporating both types of vision, our model can mimic human viewing behavior better and provide a more faithful ranking among various scene objects. Most notably, our model improves the SA-SOR/MAE scores by +6.1%/-13.0% on IRSR, compared with the state-of-the-art. Extensive experiments show the superior performance of our model on the SOR benchmarks. Code is available at https://github.com/guanhuankang/SeqRank.
Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article Gronding
PDF ↗Weakly Supervised temporal Article Grounding (WSAG) is a challenging and practical task in video understanding. Specifically, given a video and a relevant article, whose sentences are at different semantic scales, WSAG aims to localize corresponding video segments for all “groundable” sentences. Compared to other grounding tasks, e.g., localizing one target segment with respect to a given sentence query, WSAG confronts an essential obstacle rooted in the intricate multi-scale information inherent within both textual and visual modalities. Existing methods overlook the modeling and alignment of such structured information present in multi-scale video segments and hierarchical textual content. To this end, we propose a Multi-Scale Video-Text Correspondence Learning (MVTCL) framework, which enhances the grounding performance in complex scenes by modeling multi-scale semantic correspondence both within and between modalities. Specifically, MVTCL initially aggregates video content spanning distinct temporal scales and leverages hierarchical textual relationships in both temporal and semantic dimensions via a semantic calibration module. Then multi-scale contrastive learning module is introduced to generate more discriminative representations by selecting typical contexts and performing inter-video contrastive learning. Through the multi-scale semantic calibration architecture and supervision design, our method achieves new state-of-the-art performance on existing WSAG benchmarks.
3D decision-critical tasks urgently require research on explanations to ensure system reliability and transparency. Extensive explanatory research has been conducted on 2D images, but there is a lack in the 3D field. Furthermore, the existing explanations for 3D models are post-hoc and can be misleading, as they separate explanations from the original model. To address these issues, we propose an ad-hoc interpretable classifier for 3D point clouds (i.e., Interpretable3D). As an intuitive case-based classifier, Interpretable3D can provide reliable ad-hoc explanations without any embarrassing nuances. It allows users to understand how queries are embedded within past observations in prototype sets. Interpretable3D has two iterative training steps: 1) updating one prototype with the mean of the embeddings within the same sub-class in Prototype Estimation, and 2) penalizing or rewarding the estimated prototypes in Prototype Optimization. The mean of embeddings has a clear statistical meaning, i.e., class sub-centers. Moreover, we update prototypes with their most similar observations in the last few epochs. Finally, Interpretable3D classifies new samples according to prototypes. We evaluate the performance of Interpretable3D on four popular point cloud models: DGCNN, PointNet2, PointMLP, and PointNeXt. Our Interpretable3D demonstrates comparable or superior performance compared to softmax-based black-box models in the tasks of 3D shape classification and part segmentation. Our code is released at: github.com/FengZicai/Interpretable3D.
An Embedding-Unleashing Video Polyp Segmentation Framework via Region Linking and Scale Alignment
PDF ↗Automatic polyp segmentation from colonoscopy videos is a critical task for the development of computer-aided screening and diagnosis systems. However, accurate and real-time video polyp segmentation (VPS) is a very challenging task due to low contrast between background and polyps and frame-to-frame dramatic variations in colonoscopy videos. We propose a novel embedding-unleashing framework consisting of a proposal-generative network (PGN) and an appearance-embedding network (AEN) to comprehensively address these challenges. Our framework, for the first time, models VPS as an appearance-level semantic embedding process to facilitate generate more global information to counteract background disturbances and dramatic variations. Specifically, PGN is a video segmentation network to obtain segmentation mask proposals, while AEN is a network we specially designed to produce appearance-level embedding semantics for PGN, thereby unleashing the capability of PGN in VPS. Our AEN consists of a cross-scale region linking (CRL) module and a cross-wise scale alignment (CSA) module. The former screens reliable background information against background disturbances by constructing linking of region semantics, while the latter performs the scale alignment to resist dramatic variations by modeling the center-perceived motion dependence with a cross-wise manner. We further introduce a parameter-free semantic interaction to embed the semantics of AEN into PGN to obtain the segmentation results. Extensive experiments on CVC-612 and SUN-SEG demonstrate that our approach achieves better performance than other state-of-the-art methods. Codes are available at https://github.com/zhixue-fang/EUVPS.
Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. However, fully extracting the target mask with limited user inputs remains challenging. We introduce a novel method, Variance-Insensitive and Target-Preserving Mask Refinement to enhance segmentation quality with fewer user inputs. Regarding the last segmentation result as the initial mask, an iterative refinement process is commonly employed to continually enhance the initial mask. Nevertheless, conventional techniques suffer from sensitivity to the variance in the initial mask. To circumvent this problem, our proposed method incorporates a mask matching algorithm for ensuring consistent inferences from different types of initial masks. We also introduce a target-aware zooming algorithm to preserve object information during downsampling, balancing efficiency and accuracy. Experiments on GrabCut, Berkeley, SBD, and DAVIS datasets demonstrate our method's state-of-the-art performance in interactive image segmentation.
Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation
PDF ↗Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posing inter-modal heterogeneity as a challenge to effectively training a global model on all participants’ data. In addition, each participant would expect to obtain a personalized model tailored for its local data characteristics from the FL in such a scenario. In this work, we propose a new FL framework with federated modality-specific encoders and multimodal anchors (FedMEMA) to simultaneously address the two concurrent issues. Above all, FedMEMA employs an exclusive encoder for each modality to account for the inter-modal heterogeneity in the first place. In the meantime, while the encoders are shared by the participants, the decoders are personalized to meet individual needs. Specifically, a server with full-modal data employs a fusion decoder to aggregate and fuse representations from all modality-specific encoders, thus bridging the modalities to optimize the encoders via backpropagation reversely. Meanwhile, multiple anchors are extracted from the fused multimodal representations and distributed to the clients in addition to the encoder parameters. On the other end, the clients with incomplete modalities calibrate their missing-modal representations toward the global full-modal anchors via scaled dot-product cross-attention, making up the information loss due to absent modalities while adapting the representations of present ones. FedMEMA is validated on the BraTS 2020 benchmark for multimodal brain tumor segmentation. Results show that it outperforms various up-to-date methods for multimodal and personalized FL and that its novel designs are effective. Our code is available.
Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods struggle with nuanced object boundaries and overconfident incorrect predictions. In response, we propose a new paradigm that treats COD as a conditional mask-generation task leveraging diffusion models. Our method, dubbed CamoDiffusion, employs the denoising process to progressively refine predictions while incorporating image conditions. Due to the stochastic sampling process of diffusion, our model is capable of sampling multiple possible predictions, avoiding the problem of overconfident point estimation. Moreover, we develop specialized network architecture, training, and sampling strategies, to enhance the model’s expressive power, refinement capabilities and suppress overconfident mis-segmentations, thus aptly tailoring the diffusion model to the demands of COD. Extensive experiments on three COD datasets attest to the superior performance of our model compared to existing state-of-the-art methods, particularly on the most challenging COD10K dataset, where our approach achieves 0.019 in terms of MAE. Codes and models are available at https://github.com/Rapisurazurite/CamoDiffusion.
Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
PDF ↗As the exorbitant expense of labeling autopilot datasets and the growing trend of utilizing unlabeled data, semi-supervised segmentation on point clouds becomes increasingly imperative. Intuitively, finding out more ``unspoken words'' (i.e., latent instance information) beyond the label itself should be helpful to improve performance. In this paper, we discover two types of latent labels behind the displayed label embedded in LiDAR and image data. First, in the LiDAR Branch, we propose a novel augmentation, Cylinder-Mix, which is able to augment more yet reliable samples for training. Second, in the Image Branch, we propose the Instance Position-scale Learning (IPSL) Module to learn and fuse the information of instance position and scale, which is from a 2D pre-trained detector and a type of latent label obtained from 3D to 2D projection. Finally, the two latent labels are embedded into the multi-modal panoptic segmentation network. The ablation of the IPSL module demonstrates its robust adaptability, and the experiments evaluated on SemanticKITTI and nuScenes demonstrate that our model outperforms the state-of-the-art method, LaserMix.