The goal of this paper is to alleviate the training cost for few-shot semantic segmentation (FSS) models. Despite that FSS in nature improves model generalization to new concepts using only a handful of test exemplars, it relies on strong supervision from a considerable amount of labeled training data for base classes. However, collecting pixel-level annotations is notoriously expensive and time-consuming, and small-scale training datasets convey low information density that limits test-time generalization. To resolve the issue, we take a pioneering step towards label-efficient training of FSS models from fully unlabeled training data, or additionally a few labeled samples to enhance the performance. This motivates an approach based on a novel unsupervised meta-training paradigm. In particular, the approach first distills pre-trained unsupervised pixel embedding into compact semantic clusters from which a massive number of pseudo meta-tasks is constructed. To mitigate the noise in the pseudo meta-tasks, we further advocate a robust Transformer-based FSS model with a novel prototype-based cross-attention design. Extensive experiments have been conducted on two standard benchmarks, i.e., PASCAL-5i and COCO-20i, and the results show that our method produces impressive performance without any annotations, and is comparable to fully supervised competitors even using only 20% of the annotations. Our code is available at: https://github.com/SSSKYue/UMTFSS.
论文检索
输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
Deep neural networks (DNNs) have achieved remarkable success in various fields, and two powerful techniques, feature normalization and attention mechanisms, have been widely used to enhance model performance. However, they are usually considered as two separate approaches or combined in a simplistic manner. In this paper, we investigate the intrinsic relationship between feature normalization and attention mechanisms and propose an Efficient Attention module guided by Normalization, dubbed EAN. Instead of using costly fully-connected layers for attention learning, EAN leverages the strengths of feature normalization and incorporates an Attention Generation (AG) unit to re-calibrate features. The proposed AG unit exploits the normalization component as a measure of the importance of distinct features and generates an attention mask using GroupNorm, L2 Norm, and Adaptation operations. By employing a grouping, AG unit and aggregation strategy, EAN is established, offering a unified module that harnesses the advantages of both normalization and attention, while maintaining minimal computational overhead. Furthermore, EAN serves as a plug-and-play module that can be seamlessly integrated with classic backbone architectures. Extensive quantitative evaluations on various visual tasks demonstrate that EAN achieves highly competitive performance compared to the current state-of-the-art attention methods while sustaining lower model complexity.
Clustering-based methods are emerging as a ubiquitous technology in unsupervised object Re-Identification (ReID), which alternate between pseudo-label generation and representation learning. Recent advances in this field mainly fall into two groups: pseudo-label correction and robust representation learning. Differently, in this work, we improve unsupervised object ReID from feature calibration, a completely different but complementary insight from the current approaches. Specifically, we propose to insert a conceptually simple yet empirically powerful Feature Calibration Module (FCM) before pseudo-label generation. In practice, FCM calibrates the features using a nonparametric graph attention network, enforcing similar instances to move together in the feature space while allowing dissimilar instances to separate. As a result, we can generate more reliable pseudo-labels using the calibrated features and further improve subsequent representation learning. FCM is simple, effective, parameter-free, training-free, plug-and-play, and can be considered as a catalyst, increasing the ’chemical reaction’ between pseudo-label generation and representation learning. Moreover, it maintains the efficiency of testing time with negligible impact on training time. In this paper, we insert FCM into a simple baseline. Experiments across different scenarios and benchmarks show that FCM consistently improves the baseline (e.g., 8.2% mAP gain on MSMT17), and achieves the new state-of-the-art results. Code is available at: https://github.com/lhf12278/FCM-ReID.
This paper introduces a learnable Deformable Hypothesis Sampler (DeformSampler) to address the challenging issue of noisy depth estimation in faithful PatchMatch multi-view stereo (MVS). We observe that the heuristic depth hypothesis sampling modes employed by PatchMatch MVS solvers are insensitive to (i) the piece-wise smooth distribution of depths across the object surface and (ii) the implicit multi-modal distribution of depth prediction probabilities along the ray direction on the surface points. Accordingly, we develop DeformSampler to learn distribution-sensitive sample spaces to (i) propagate depths consistent with the scene's geometry across the object surface and (ii) fit a Laplace Mixture model that approaches the point-wise probabilities distribution of the actual depths along the ray direction. We integrate DeformSampler into a learnable PatchMatch MVS system to enhance depth estimation in challenging areas, such as piece-wise discontinuous surface boundaries and weakly-textured regions. Experimental results on DTU and Tanks & Temples datasets demonstrate its superior performance and generalization capabilities compared to state-of-the-art competitors. Code is available at https://github.com/Geo-Tell/DS-PMNet.
Towards Automated Chinese Ancient Character Restoration: A Diffusion-Based Method with a New Dataset
PDF ↗Automated Chinese ancient character restoration (ACACR) remains a challenging task due to its historical significance and aesthetic complexity. Existing methods are constrained by non-professional masks and even overfitting when training on small-scale datasets, which hinder their interdisciplinary application to traditional fields. In this paper, we are proud to introduce the Chinese Ancient Rubbing and Manuscript Character Dataset (ARMCD), which consists of 15,553 real-world ancient single-character images with 42 rubbings and manuscripts, covering the works of over 200 calligraphy artists spanning from 200 to 1,800 AD. We are also dedicated to providing professional synthetic masks by extracting localized erosion from real eroded images. Moreover, we propose DiffACR (Diffusion model for automated Chinese Ancient Character Restoration), a diffusion-based method for the ACACR task. Specifically, we regard the synthesis of eroded images as a special form of cold diffusion on uneroded ones and extract the prior mask directly from the eroded images. Our experiments demonstrate that our method comprehensively outperforms most existing methods on the proposed ARMCD. Dataset and code are available at https://github.com/lhl322001/DiffACR.
Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing
PDF ↗GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes. Recent inversion methods mainly utilize additional high-bit features to improve image details preservation, as low-bit codes cannot faithfully reconstruct source images, leading to the loss of details. However, during editing, existing works fail to accurately complement the lost details and suffer from poor editability. The main reason is they inject all the lost details indiscriminately at one time, which inherently induces the position and quantity of details to overfit source images, resulting in inconsistent content and artifacts in edited images. This work argues that details should be gradually injected into both the reconstruction and editing process in a multi-stage coarse-to-fine manner for better detail preservation and high editability. Therefore, a novel dual-stream framework is proposed to accurately complement details at each stage. The Reconstruction Stream is employed to embed coarse-to-fine lost details into residual features and then adaptively add them to the GAN generator. In the Editing Stream, residual features are accurately aligned by our Selective Attention mechanism and then injected into the editing process in a multi-stage manner. Extensive experiments have shown the superiority of our framework in both reconstruction accuracy and editing quality compared with existing methods.
Point2Real: Bridging the Gap between Point Cloud and Realistic Image for Open-World 3D Recognition
PDF ↗Recognition in open-world scenarios is an important and challenging field, where Vision-Language Pre-training paradigms have greatly impacted the 2D domain. This inspires a growing interest in introducing 2D pre-trained models, such as CLIP, into the 3D domain to enhance the ability of point cloud understanding. Considering the difference between discrete 3D point clouds and real-world 2D images, reducing the domain gap is crucial. Some recent works project point clouds onto a 2D plane to enable 3D zero-shot capabilities without training. However, this simplistic approach leads to an unclear or even distorted geometric structure, limiting the potential of 2D pre-trained models in 3D. To address the domain gap, we propose Point2Real, a training-free framework based on the realistic rendering technique to automate the transformation of the 3D point cloud domain into the Vision-Language domain. Specifically, Point2Real leverages a shape recovery module that devises an iterative ball-pivoting algorithm to convert point clouds into meshes, narrowing the gap in shape at first. To simulate photo-realistic images, a set of refined textures as candidates is applied for rendering, where the CLIP confidence is utilized to select the suitable one. Moreover, to tackle the viewpoint challenge, a heuristic multi-view adapter is implemented for feature aggregation, which exploits the depth surface as an effective indicator of view-specific discriminability for recognition. We conduct experiments on ModelNet10, ModelNet40, and ScanObjectNN datasets, and the results demonstrate that Point2Real outperforms other approaches in zero-shot and few-shot tasks by a large margin.
Current parametric models have made notable progress in 3D hand pose and shape estimation. However, due to the fixed hand topology and complex hand poses, current models are hard to generate meshes that are aligned with the image well. To tackle this issue, we introduce a dual noise estimation method in this paper. Given a single-view image as input, we first adopt a baseline parametric regressor to obtain the coarse hand meshes. We assume the mesh vertices and their image-plane projections are noisy, and can be associated in a unified probabilistic model. We then learn the distributions of noise to refine mesh vertices and their projections. The refined vertices are further utilized to refine camera parameters in a closed-form manner. Consequently, our method obtains well-aligned and high-quality 3D hand meshes. Extensive experiments on the large-scale Interhand2.6M dataset demonstrate that the proposed method not only improves the performance of its baseline by more than 10% but also achieves state-of-the-art performance. Project page: https://github.com/hanhuili/DNE4Hand.
Audio-driven talking head synthesis is a promising topic with wide applications in digital human, film making and virtual reality. Recent NeRF-based approaches have shown superiority in quality and fidelity compared to previous studies. However, when it comes to few-shot talking head generation, a practical scenario where only few seconds of talking video is available for one identity, two limitations emerge: 1) they either have no base model, which serves as a facial prior for fast convergence, or ignore the importance of audio when building the prior; 2) most of them overlook the degree of correlation between different face regions and audio, e.g., mouth is audio related, while ear is audio independent. In this paper, we present Audio Enhanced Neural Radiance Field (AE-NeRF) to tackle the above issues, which can generate realistic portraits of a new speaker with few-shot dataset. Specifically, we introduce an Audio Aware Aggregation module into the feature fusion stage of the reference scheme, where the weight is determined by the similarity of audio between reference and target image. Then, an Audio-Aligned Face Generation strategy is proposed to model the audio related and audio independent regions respectively, with a dual-NeRF framework. Extensive experiments have shown AE-NeRF surpasses the state-of-the-art on image fidelity, audio-lip synchronization, and generalization ability, even in limited training set or training iterations.
One at a Time: Progressive Multi-Step Volumetric Probability Learning for Reliable 3D Scene Perception
PDF ↗Numerous studies have investigated the pivotal role of reliable 3D volume representation in scene perception tasks, such as multi-view stereo (MVS) and semantic scene completion (SSC). They typically construct 3D probability volumes directly with geometric correspondence, attempting to fully address the scene perception tasks in a single forward pass. However, such a single-step solution makes it hard to learn accurate and convincing volumetric probability, especially in challenging regions like unexpected occlusions and complicated light reflections. Therefore, this paper proposes to decompose the complicated 3D volume representation learning into a sequence of generative steps to facilitate fine and reliable scene perception. Considering the recent advances achieved by strong generative diffusion models, we introduce a multi-step learning framework, dubbed as VPD, dedicated to progressively refining the Volumetric Probability in a Diffusion process. Specifically, we first build a coarse probability volume from input images with the off-the-shelf scene perception baselines, which is then conditioned as the basic geometry prior before being fed into a 3D diffusion UNet, to progressively achieve accurate probability distribution modeling. To handle the corner cases in challenging areas, a Confidence-Aware Contextual Collaboration (CACC) module is developed to correct the uncertain regions for reliable volumetric learning based on multi-scale contextual contents. Moreover, an Online Filtering (OF) strategy is designed to maintain representation consistency for stable diffusion sampling. Extensive experiments are conducted on scene perception tasks including multi-view stereo (MVS) and semantic scene completion (SSC), to validate the efficacy of our method in learning reliable volumetric representations. Notably, for the SSC task, our work stands out as the first to surpass LiDAR-based methods on the SemanticKITTI dataset.
Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification
PDF ↗Existing image augmentation methods consist of two categories: perturbation-based methods and generative methods. Perturbation-based methods apply pre-defined perturbations to augment an original image, but only locally vary the image, thus lacking image diversity. In contrast, generative methods bring more image diversity in the augmented images but may not preserve semantic consistency, thus may incorrectly change the essential semantics of the original image. To balance image diversity and semantic consistency in augmented images, we propose SGID, a Semantic-guided Generative Image augmentation method with Diffusion models for image classification. Specifically, SGID employs diffusion models to generate augmented images with good image diversity. More importantly, SGID takes image labels and captions as guidance to maintain semantic consistency between the augmented and original images. Experimental results show that SGID outperforms the best augmentation baseline by 1.72% on ResNet-50 (from scratch), 0.33% on ViT (ImageNet-21k), and 0.14% on CLIP-ViT (LAION-2B). Moreover, SGID can be combined with other image augmentation baselines and further improves the overall performance. We demonstrate the semantic consistency and image diversity of SGID through quantitative human and automated evaluations, as well as qualitative case studies.
Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images sharing the same category across diverse domains without relying on labeled data. Prior approaches have typically decomposed the UCIR problem into two distinct tasks: intra-domain representation learning and cross-domain feature alignment. However, these segregated strategies overlook the potential synergies between these tasks. This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework. ProtoOT leverages the strengths of the K-means clustering method to effectively manage distribution imbalances inherent in UCIR. By utilizing K-means for generating initial prototypes and approximating class marginal distributions, we modify the constraints in Optimal Transport accordingly, significantly enhancing its performance in UCIR scenarios. Furthermore, we incorporate contrastive learning into the ProtoOT framework to further improve representation learning. This encourages local semantic consistency among features with similar semantics, while also explicitly enforcing separation between features and unmatched prototypes, thereby enhancing global discriminativeness. ProtoOT surpasses existing state-of-the-art methods by a notable margin across benchmark datasets. Notably, on DomainNet, ProtoOT achieves an average P@200 enhancement of 24.44%, and on Office-Home, it demonstrates a P@15 improvement of 12.12%. Code is available at https://github.com/HCVLAB/ProtoOT.
Point Transformer with Federated Learning for Predicting Breast Cancer HER2 Status from Hematoxylin and Eosin-Stained Whole Slide Images
PDF ↗Directly predicting human epidermal growth factor receptor 2 (HER2) status from widely available hematoxylin and eosin (HE)-stained whole slide images (WSIs) can reduce technical costs and expedite treatment selection. Accurately predicting HER2 requires large collections of multi-site WSIs. Federated learning enables collaborative training of these WSIs without gigabyte-size WSIs transportation and data privacy concerns. However, federated learning encounters challenges in addressing label imbalance in multi-site WSIs from the real world. Moreover, existing WSI classification methods cannot simultaneously exploit local context information and long-range dependencies in the site-end feature representation of federated learning. To address these issues, we present a point transformer with federated learning for multi-site HER2 status prediction from HE-stained WSIs. Our approach incorporates two novel designs. We propose a dynamic label distribution strategy and an auxiliary classifier, which helps to establish a well-initialized model and mitigate label distribution variations across sites. Additionally, we propose a farthest cosine sampling based on cosine distance. It can sample the most distinctive features and capture the long-range dependencies. Extensive experiments and analysis show that our method achieves state-of-the-art performance at four sites with a total of 2687 WSIs. Furthermore, we demonstrate that our model can generalize to two unseen sites with 229 WSIs. Code is available at: https://github.com/boyden/PointTransformerFL
The task of Composed Image Retrieval (CoIR) involves queries that combine image and text modalities, allowing users to express their intent more effectively. However, current CoIR datasets are orders of magnitude smaller compared to other vision and language (V&L) datasets. Additionally, some of these datasets have noticeable issues, such as queries containing redundant modalities. To address these shortcomings, we introduce the Large Scale Composed Image Retrieval (LaSCo) dataset, a new CoIR dataset which is ten times larger than existing ones. Pre-training on our LaSCo, shows a noteworthy improvement in performance, even in zero-shot. Furthermore, we propose a new approach for analyzing CoIR datasets and methods, which detects modality redundancy or necessity, in queries. We also introduce a new CoIR baseline, the Cross-Attention driven Shift Encoder (CASE). This baseline allows for early fusion of modalities using a cross-attention module and employs an additional auxiliary task during training. Our experiments demonstrate that this new baseline outperforms the current state-of-the-art methods on established benchmarks like FashionIQ and CIRR.
Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perceptrons and bidirectional feature transformation for comprehensive representation modeling in the background restoration phase. The efficacy of our approach is empirically validated across two large-scale datasets, and our findings reveal a marked enhancement over existing watermark removal techniques.
Detecting human-object interactions (HOI) in a few-shot setting remains a challenge. Existing meta-learning methods struggle to extract representative features for classification due to the limited data, while existing few-shot HOI models rely on HOI text labels for classification. Moreover, some query images may display visual similarity to those outside their class, such as similar backgrounds between different HOI classes. This makes learning more challenging, especially with limited samples. Bongard-HOI epitomizes this HOI few-shot problem, making it the benchmark we focus on in this paper. In our proposed method, we introduce novel label-uncertain query augmentation techniques to enhance the diversity of the query inputs, aiming to distinguish the positive HOI class from the negative ones. As these augmented inputs may or may not have the same class label as the original inputs, their class label is unknown. Those belonging to a different class become hard samples due to their visual similarity to the original ones. Additionally, we introduce a novel pseudo-label generation technique that enables a mean teacher model to learn from the augmented label-uncertain inputs. We propose to augment the negative support set for the student model to enrich the semantic information, fostering diversity that challenges and enhances the student’s learning. Experimental results demonstrate that our method sets a new state-of-the-art (SOTA) performance by achieving 68.74% accuracy on the Bongard-HOI benchmark, a significant improvement over the existing SOTA of 66.59%. In our evaluation on HICO-FS, a more general few-shot recognition dataset, our method achieves 73.27% accuracy, outperforming the previous SOTA of 71.20% in the 5- way 5-shot task.
Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a sufficient amount of labeled data since their rich features code not only objects but also less relevant image background. In contrast, Instance Discrimination (ID) methods focus on objects. In this work, we study how to combine the efficiency and scalability of MIM with the ability of ID to perform downstream classification in the absence of large amounts of labeled data. To this end, we introduce Masked Autoencoder Contrastive Tuning (MAE-CT), a sequential approach that utilizes the implicit clustering of the Nearest Neighbor Contrastive Learning (NNCLR) objective to induce abstraction in the topmost layers of a pre-trained MAE. MAE-CT tunes the rich features such that they form semantic clusters of objects without using any labels. Notably, MAE-CT does not rely on hand-crafted augmentations and frequently achieves its best performances while using only minimal augmentations (crop & flip). Further, MAE-CT is compute efficient as it requires at most 10% overhead compared to MAE re-training. Applied to large and huge Vision Transformer (ViT) models, MAE-CT excels over previous self-supervised methods trained on ImageNet in linear probing, k-NN and low-shot classification accuracy as well as in unsupervised clustering accuracy. With ViT-H/16 MAE-CT achieves a new state-of-the-art in linear probing of 82.2%. Project page: github.com/ml-jku/MAE-CT.
Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization methods with a decent localization performance are necessary, but these methods employed in CNN-based models are still not available in ViT due to its unique structure. In this work, we propose an attention-guided visualization method applied to ViT that provides a high-level semantic explanation for its decision. Our method selectively aggregates the gradients directly propagated from the classification output to each self-attention, collecting the contribution of image features extracted from each location of the input image. These gradients are additionally guided by the normalized self-attention scores, which are the pairwise patch correlation scores. They are used to supplement the gradients on the patch-level context information efficiently detected by the self-attention mechanism. This approach of our method provides elaborate high-level semantic explanations with great localization performance only with the class labels. As a result, our method outperforms the previous leading explainability methods of ViT in the weakly-supervised localization task and presents great capability in capturing the full instances of the target class object. Meanwhile, our method provides a visualization that faithfully explains the model, which is demonstrated in the perturbation comparison test.
Single-domain generalization (S-DG) aims to generalize a model to unseen environments with a single-source domain. However, most S-DG approaches have been conducted in the field of classification. When these approaches are applied to object detection, the semantic features of some objects can be damaged, which can lead to imprecise object localization and misclassification. To address these problems, we propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection. Our method consists of data augmentation and training strategy, which are called OA-Mix and OA-Loss, respectively. OA-Mix generates multi-domain data with multi-level transformation and object-aware mixing strategy. OA-Loss enables models to learn domain-invariant representations for objects and backgrounds from the original and OA-Mixed images. Our proposed method outperforms state-of-the-art works on standard benchmarks. Our code is available at https://github.com/WoojuLee24/OA-DG.
In this paper, we introduce a new challenge for synthesizing novel view images in practical environments with limited input multi-view images and varying lighting conditions. Neural radiance fields (NeRF), one of the pioneering works for this task, demand an extensive set of multi-view images taken under constrained illumination, which is often unattainable in real-world settings. While some previous works have managed to synthesize novel views given images with different illumination, their performance still relies on a substantial number of input multi-view images. To address this problem, we suggest ExtremeNeRF, which utilizes multi-view albedo consistency, supported by geometric alignment. Specifically, we extract intrinsic image components that should be illumination-invariant across different views, enabling direct appearance comparison between the input and novel view under unconstrained illumination. We offer thorough experimental results for task evaluation, employing the newly created NeRF Extreme benchmark—the first in-the-wild benchmark for novel view synthesis under multiple viewing directions and varying illuminations.