论文检索

Yuanzhi Wang, Zhen Cui, Yong Li

Recovering missed modality is popular in incomplete multimodal learning because it usually benefits downstream tasks. However, the existing methods often directly estimate missed modalities from the observed ones by deep neural networks, lacking consideration of the distribution gap between modalities, resulting in the inconsistency of distributions between the recovered data and true data. To mitigate this issue, in this work, we propose a novel recovery paradigm, Distribution-Consistent Modal Recovering (DiCMoR), to transfer the distributions from available modalities to missed modalities, which thus maintains the distribution consistency of recovered data. In particular, we design a class-specific flow based modality recovery method to transform cross-modal distributions on the condition of sample class, which could well predict a distribution-consistent space for missing modality by virtue of the invertibility and exact density estimation of normalizing flow. The generated data from the predicted distribution is jointly integrated with available modalities for the task of classification. Experiments demonstrate that DiCMoR gains superior performances and is more robust than existing state-of-the-art methods under various missing patterns. Visualization results show that the distribution gaps between recovered modalities and missing modalities are mitigated.

Zhibin Dong, Siwei Wang, Jiaqi Jin, Xinwang Liu, En Zhu

Multi-view clustering aims to extract valuable information from different sources or perspectives. Over the years, the deep neural network has demonstrated its superior representation learning capability in multi-view clustering and achieved impressive performance. However, most existing deep clustering approaches are dedicated to merging and exploring the consistent latent representation across multiple views while overlooking the abundant complementary information in each view. Furthermore, finding correlations between multiple views in an unsupervised setting is a significant challenge. To tackle these issues, we present a novel Cross-view Topology based Consistent and Complementary information extraction framework, termed CTCC. In detail, deep embedding can be obtained from the bipartite graph learning module for each view individually. CTCC then constructs the cross-view topological graph based on the OT distance between the bipartite graph of each view. Utilizing the above graph, we maximize the mutual information across views to learn consistent information and enhance the complementarity of each view by selectively isolating distributions from each other. Extensive experiments on five challenging datasets verify that CTCC outperforms existing methods significantly.

Chengxu Liu, Xuan Wang, Shuai Li, Yuzhi Wang, Xueming Qian

Under-display camera (UDC) systems remove the screen notch for bezel-free displays and provide a better interactive experience. The main challenge is that the pixel array of light-emitting diodes used for display diffracts and attenuates the incident light, leading to complex degradation. Existing models eliminate spatial diffraction by maximizing model capacity through complex design and ignore the periodic distribution of diffraction in the frequency domain, which prevents these approaches from satisfactory results. In this paper, we introduce a new perspective to handle various diffraction in UDC images by jointly exploring the feature restoration in the frequency and spatial domains, and present a Frequency and Spatial Interactive Learning Network (FSI). It consists of a series of well-designed Frequency-Spatial Joint (FSJ) modules for feature learning and a color transform module for color enhancement. In particular, in the FSJ module, a frequency learning block uses the Fourier transform to eliminate spectral bias, a spatial learning block uses a multi-distillation structure to supplement the absence of local details, and a dual transfer unit to facilitate the interactive learning between features of different domains. Experimental results demonstrate the superiority of the proposed FSI over state-of-the-art models, through extensive quantitative and qualitative evaluations in three widely-used UDC benchmarks.

Yidong Cai, Jie Liu, Jie Tang, Gangshan Wu

Object modeling has become a core part of recent tracking frameworks. Current popular tackers use Transformer attention to extract the template feature separately or interactively with the search region. However, separate template learning lacks communication between the template and search regions, which brings difficulty in extracting discriminative target-oriented features. On the other hand, interactive template learning produces hybrid template features, which may introduce potential distractors to the template via the cluttered search regions. To enjoy the merits of both methods, we propose a robust object modeling framework for visual tracking (ROMTrack), which simultaneously models the inherent template and the hybrid template features. As a result, harmful distractors can be suppressed by combining the inherent features of target objects with search regions' guidance. Target-related features can also be extracted using the hybrid template, thus resulting in a more robust object modeling framework. To further enhance robustness, we present novel variation tokens to depict the ever-changing appearance of target objects. Variation tokens are adaptable to object deformation and appearance variations, which can boost overall performance with negligible computation. Experiments show that our ROMTrack sets a new state-of-the-art on multiple benchmarks.

Weilai Xiang, Hongyu Yang, Di Huang, Yunhong Wang

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that the networks in diffusion models, namely denoising diffusion autoencoders (DDAE), are unified self-supervised learners: by pre-training on unconditional image generation, DDAE has already learned strongly linear-separable representations within its intermediate layers without auxiliary encoders, thus making diffusion pre-training emerge as a general approach for generative-and-discriminative dual learning. To validate this, we conduct linear probe and fine-tuning evaluations. Our diffusion-based approach achieves 95.9% and 50.0% linear evaluation accuracies on CIFAR-10 and Tiny-ImageNet, respectively, and is comparable to contrastive learning and masked autoencoders for the first time. Transfer learning from ImageNet also confirms the suitability of DDAE for Vision Transformers, suggesting the potential to scale DDAEs as unified foundation models. Code is available at github.com/FutureXiang/ddae.

Yunhao Zou, Chenggang Yan, Ying Fu

High dynamic range (HDR) images can record much more intensity levels than usual ones. Existing methods mainly reconstruct HDR images from the 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing pipeline. However, recovering extremely high dynamic range scenes from such low bit-depth data is challenging. Unlike existing methods, the core idea of this work is to incorporate more informative Raw sensor data to generate HDR images, aiming to recover scene information in hard regions (the darkest and brightest areas of an HDR scene). We propose a model customized for Raw images, considering the unique feature of Raw data to learn the Raw-to-HDR mapping. Specifically, we learn exposure masks to separate the hard and easy regions of a high dynamic scene. Then, we introduce two important guidances, dual intensity guidance, which guides less informative channels with more informative ones, and global spatial guidance which hallucinates scene details from a longer spatial range. To verify our Raw-to-HDR approach, we collect a large and high-quality Raw/HDR paired dataset for both training and testing, which will be made available publicly. We verify the superiority of the proposed Raw-to-HDR reconstruction model, as well as our newly captured dataset in the experiments.

Ruopeng Gao, Limin Wang

As a video task, Multiple Object Tracking (MOT) is expected to capture temporal information of targets effectively. Unfortunately, most existing methods only explicitly exploit the object features between adjacent frames, while lacking the capacity to model long-term temporal information. In this paper, we propose MeMOTR, a long-term memory-augmented Transformer for multi-object tracking. Our method is able to make the same object's track embedding more stable and distinguishable by leveraging long-term memory injection with a customized memory-attention layer. This significantly improves the target association ability of our model. Experimental results on DanceTrack show that MeMOTR impressively surpasses the state-of-the-art method by 7.9% and 13.0% on HOTA and AssA metrics, respectively. Furthermore, our model also outperforms other Transformer-based methods on association performance on MOT17 and generalizes well on BDD100K. Code is available at https://github.com/MCG-NJU/MeMOTR.

Xin Wen, Bingchen Zhao, Xiaojuan Qi

Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. Previous studies argued that parametric classifiers are prone to overfitting to seen categories, and endorsed using a non-parametric classifier formed with semi-supervised k-means. However, in this study, we investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We demonstrate that two prediction biases exist: the classifier tends to predict seen classes more often, and produces an imbalanced distribution across seen and novel categories. Based on these findings, we propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers. We hope the investigation and proposed simple framework can serve as a strong baseline to facilitate future studies in this field. Our code is available at: https://github.com/CVMI-Lab/SimGCD.

Tianyu Huang, Bowen Dong, Yunhan Yang, Xiaoshui Huang, Rynson W.H. Lau, Wanli Ouyang, Wangmeng Zuo

Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language (V-L) pre-training methods to 3D vision. However, the domain gap between 3D and images is unsolved, so that V-L pre-trained models are restricted in 3D downstream tasks. To address this issue, we propose CLIP2Point, an image-depth pre-training method by contrastive learning to transfer CLIP to the 3D domain, and adapt it to point cloud classification. We introduce a new depth rendering setting that forms a better visual effect, and then render 52,460 pairs of images and depth maps from ShapeNet for pre-training. The pre-training scheme of CLIP2Point combines cross-modality learning to enforce the depth features for capturing expressive visual and textual features and intra-modality learning to enhance the invariance of depth aggregation. Additionally, we propose a novel Gated Dual-Path Adapter (GDPA), i.e., a dual-path structure with global-view aggregators and gated fusion for downstream representative learning. It allows the ensemble of CLIP and CLIP2Point, tuning pre-training knowledge to downstream tasks in an efficient adaptation. Experimental results show that CLIP2Point is effective in transferring CLIP knowledge to 3D vision. Our CLIP2Point outperforms other 3D transfer learning and pre-training networks, achieving state-of-the-art results on zero-shot, few-shot, and fully-supervised classification.

Runyi Yu, Zhennan Wang, Yinhuai Wang, Kehan Li, Chang Liu, Haoyi Duan, Xiangyang Ji, Jie Chen

Position information is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operations. A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs. However, this approach operates the same Layer Normalization (LN) to token embedding and PE, and delivers the same PE to each layer. This results in restricted and monotonic PE across layers, as the shared LN affine parameters are not dedicated to PE, and the PE cannot be adjusted on a per-layer basis. To overcome these limitations, we propose using two independent LNs for token embeddings and PE in each layer, and progressively delivering PE across layers. By implementing this approach, VTs will receive layer-adaptive and hierarchical PE. We name our method as Layer-adaptive Position Embedding, abbreviated as LaPE, which is simple, effective, and robust. Extensive experiments on image classification, object detection, and semantic segmentation demonstrate that LaPE significantly outperforms the default PE method. For example, LaPE improves +1.06% for CCT on CIFAR100, +1.57% for DeiT-Ti on ImageNet-1K, +0.7 box AP and +0.5 mask AP for ViT-Adapter-Ti on COCO, and +1.37 mIoU for tiny Segmenter on ADE20K. This is remarkable considering LaPE only increases negligible parameters, memory, and computational cost.

Siyu Ren, Junhui Hou, Xiaodong Chen, Ying He, Wenping Wang

We present a learning-based method, namely GeoUDF, to tackle the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation that explicitly formulates the unsigned distance of a query point as the learnable affine averaging of its distances to the tangent planes of neighboring points on the surface. Besides, we model the local geometric structure of the input point clouds by explicitly learning a quadratic polynomial for each point. This not only facilitates upsampling the input sparse point cloud but also naturally induces unoriented normal, which further augments UDF estimation. Finally, to extract triangle meshes from the predicted UDF, we propose a customized edge-based marching cube module. We conduct extensive experiments and ablation studies to demonstrate the significant advantages of our method over state-of-the-art methods in terms of reconstruction accuracy, efficiency, and generality. The source code is publicly available at https://github.com/rsy6318/GeoUDF.

Kaicheng Yang, Jiankang Deng, Xiang An, Jiawei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. To address this issue, we first utilize the OFA model to generate synthetic captions that focus on the image content. The generated captions contain complementary information that is beneficial for pre-training. Then, we propose an Adaptive Language-Image Pre-training (ALIP), a bi-path model that integrates supervision from both raw text and synthetic caption. As the core components of ALIP, the Language Consistency Gate (LCG) and Description Consistency Gate (DCG) dynamically adjust the weights of samples and image-text/caption pairs during the training process. Meanwhile, the adaptive contrastive loss can effectively reduce the impact of noise data and enhances the efficiency of pre-training data. We validate ALIP with experiments on different scales of models and pre-training datasets. Experiments results show that ALIP achieves state-of-the-art performance on multiple downstream tasks including zero-shot image-text retrieval and linear probe. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/ALIP.

Song Park, Sanghyuk Chun, Byeongho Heo, Wonjae Kim, Sangdoo Yun

We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e.g., the LAION-4B dataset needs 240TB storage space). However, it has become challenging to deal with unlimited dataset storage with limited storage infrastructure. A number of storage-efficient training methods have been proposed to tackle the problem, but they are rarely scalable or suffer from severe damage to performance. In this paper, we propose a storage-efficient training strategy for vision classifiers for large-scale datasets (e.g., ImageNet) that only uses 1024 tokens per instance without using the raw level pixels; our token storage only needs <1% of the original JPEG-compressed raw pixels. We also propose token augmentations and a Stem-adaptor module to make our approach able to use the same architecture as pixel-based approaches with only minimal modifications on the stem layer and the carefully tuned optimization settings. Our experimental results on ImageNet-1K show that our method significantly outperforms other storage-efficient training methods with a large gap. We further show the effectiveness of our method in other practical scenarios, storage-efficient pre-training, and continual learning. We will make our implementation and tokenized dataset publicly after the acceptance.

Luozhou Wang, Shuai Yang, Shu Liu, Ying-cong Chen

Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off problem: adding too much noise affects the fidelity of the image while adding too little affects its editability. This largely limits their practical applicability. In this paper, we propose a novel framework, Selective Diffusion Distillation (SDD), that ensures both the fidelity and editability of images. Instead of directly editing images with a diffusion model, we train a feedforward image manipulation network under the guidance of the diffusion model. Besides, we propose an effective indicator to select the semantic-related timestep to obtain the correct semantic guidance from the diffusion model. This approach successfully avoids the dilemma caused by the diffusion process. Our extensive experiments demonstrate the advantages of our framework.

Ruofan Liang, Huiting Chen, Chunlin Li, Fan Chen, Selvakumar Panneer, Nandita Vijaykumar

Recent advances in neural rendering have shown great potential for reconstructing scenes from multiview images. However, accurately representing objects with glossy surfaces remains a challenge for existing methods. In this work, we introduce ENVIDR, a rendering and modeling framework for high-quality rendering and reconstruction of surfaces with challenging specular reflections. To achieve this, we first propose a novel neural renderer with decomposed rendering components to learn the interaction between surface and environment lighting. This renderer is trained using existing physically based renderers and is decoupled from actual scene representations. We then propose an SDF-based neural surface model that leverages this learned neural renderer to represent general scenes. Our model additionally synthesizes indirect illuminations caused by inter-reflections from shiny surfaces by marching surface-reflected rays. We demonstrate that our method outperforms state-of-art methods on challenging shiny scenes, providing high-quality rendering of specular reflections while also enabling material editing and scene relighting.

Mischa Dombrowski, Hadrien Reynaud, Matthew Baugh, Bernhard Kainz

Curating datasets for object segmentation is a difficult task. With the advent of large-scale pre-trained generative models, conditional image generation has been given a significant boost in result quality and ease of use. In this paper, we present a novel method that enables the generation of general foreground-background segmentation models from simple textual descriptions, without requiring segmentation labels. We leverage and explore pre-trained latent diffusion models, to automatically generate weak segmentation masks for concepts and objects. The masks are then used to fine-tune the diffusion model on an inpainting task, which enables fine-grained removal of the object, while at the same time providing a synthetic foreground and background dataset. We demonstrate that using this method beats previous methods in both discriminative and generative performance and closes the gap with fully supervised training while requiring no pixel-wise object labels. We show results on the task of segmenting four different objects (humans, dogs, cars, birds) and a use case scenario in medical image analysis. The code is available at https://github.com/MischaD/fobadiffusion.

Zhixuan Li, Weining Ye, Juan Terven, Zachary Bennett, Ying Zheng, Tingting Jiang, Tiejun Huang

Amodal Instance Segmentation (AIS) endeavors to accurately deduce complete object shapes that are partially or fully occluded. However, the inherent ill-posed nature of single-view datasets poses challenges in determining occluded shapes. A multi-view framework may help alleviate this problem, as humans often adjust their perspective when encountering occluded objects. At present, this approach has not yet been explored by existing methods and datasets. To bridge this gap, we propose a new task called Multi-view Amodal Instance Segmentation (MAIS) and introduce the MUVA dataset, the first MUlti-View AIS dataset that takes the shopping scenario as instantiation. MUVA provides comprehensive annotations, including multi-view amodal/visible segmentation masks, 3D models, and depth maps, making it the largest image-level AIS dataset in terms of both the number of images and instances. Additionally, we propose a new method for aggregating representative features across different instances and views, which demonstrates promising results in accurately predicting occluded objects from one viewpoint by leveraging information from other viewpoints. Besides, we also demonstrate that MUVA can benefit the AIS task in real-world scenarios.

Dave Zhenyu Chen, Yawar Siddiqui, Hsin-Ying Lee, Sergey Tulyakov, Matthias Nießner

We present Text2Tex, a novel method for generating high-quality textures for 3D meshes from the given text prompts. Our method incorporates inpainting into a pre-trained depth-aware image diffusion model to progressively synthesize high resolution partial textures from multiple viewpoints. To avoid accumulating inconsistent and stretched artifacts across views, we dynamically segment the rendered view into a generation mask, which represents the generation status of each visible texel. This partitioned view representation guides the depth-aware inpainting model to generate and update partial textures for the corresponding regions. Furthermore, we propose an automatic view sequence generation scheme to determine the next best view for updating the partial texture. Extensive experiments demonstrate that our method significantly outperforms the existing text-driven approaches and GAN-based methods.

Artem Sevastopolskiy, Yury Malkov, Nikita Durasov, Luisa Verdoliva, Matthias Nießner

State-of-the-art face recognition systems require huge amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to celebrity web crawls, which have issues such as skewed distributions of ethnicities and limited numbers of identities. On the other hand, the self-supervised revolution in the industry motivates research on adaptation of the related techniques to facial recognition. One of the most popular practical tricks is to augment the dataset by the samples drawn from the high-resolution high-fidelity models (e.g. StyleGAN-like), while preserving the identity. We show that a simple approach based on fine-tuning an encoder for StyleGAN allows to improve upon the state-of-the-art facial recognition and performs better compared to training on synthetic face identities. We also collect large-scale unlabeled datasets with controllable ethnic constitution -- AfricanFaceSet-5M (5 million images of different people) and AsianFaceSet-3M (3 million images of different people) and we show that pretraining on each of them improves recognition of the respective ethnicities (as well as also others), while combining all unlabeled datasets results in the biggest performance increase. Our self-supervised strategy is the most useful with limited amounts of labeled training data, which can be beneficial for more tailored face recognition tasks and when facing privacy concerns. Evaluation is provided based on a standard RFW dataset and a new large-scale RB-WebFace benchmark.

Yaohua Zha, Jinpeng Wang, Tao Dai, Bin Chen, Zhi Wang, Shu-Tao Xia

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task storage overhead for model parameters, which limits the efficiency when applying large-scale pre-trained models. Inspired by the recent success of visual prompt tuning (VPT), this paper attempts to explore prompt tuning on pre-trained point cloud models, to pursue an elegant balance between performance and parameter efficiency. We find while instance-agnostic static prompting, e.g. VPT, shows some efficacy in downstream transfer, it is vulnerable to the distribution diversity caused by various types of noises in real-world point cloud data. To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models. The essence of IDPT is to develop a dynamic prompt generation module to perceive semantic prior features of each point cloud instance and generate adaptive prompt tokens to enhance the model's robustness. Notably, extensive experiments demonstrate that IDPT outperforms full fine-tuning in most tasks with a mere 7% of the trainable parameters, providing a promising solution to parameter-efficient learning for pre-trained point cloud models. Code is available at https://github.com/zyh16143998882/ICCV23-IDPT.