2023-03-17 更新
Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation
Authors:Mattia Litrico, Alessio Del Bue, Pietro Morerio
Standard Unsupervised Domain Adaptation (UDA) methods assume the availability of both source and target data during the adaptation. In this work, we investigate Source-free Unsupervised Domain Adaptation (SF-UDA), a specific case of UDA where a model is adapted to a target domain without access to source data. We propose a novel approach for the SF-UDA setting based on a loss reweighting strategy that brings robustness against the noise that inevitably affects the pseudo-labels. The classification loss is reweighted based on the reliability of the pseudo-labels that is measured by estimating their uncertainty. Guided by such reweighting strategy, the pseudo-labels are progressively refined by aggregating knowledge from neighbouring samples. Furthermore, a self-supervised contrastive framework is leveraged as a target space regulariser to enhance such knowledge aggregation. A novel negative pairs exclusion strategy is proposed to identify and exclude negative pairs made of samples sharing the same class, even in presence of some noise in the pseudo-labels. Our method outperforms previous methods on three major benchmarks by a large margin. We set the new SF-UDA state-of-the-art on VisDA-C and DomainNet with a performance gain of +1.8% on both benchmarks and on PACS with +12.3% in the single-source setting and +6.6% in multi-target adaptation. Additional analyses demonstrate that the proposed approach is robust to the noise, which results in significantly more accurate pseudo-labels compared to state-of-the-art approaches.
PDF To be published in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023
点此查看论文截图
You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos
Authors:Xiang Fang, Daizong Liu, Pan Zhou, Guoshun Nan
Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual features extracted from the consecutive decoded frames and fail to handle the compressed videos for query modelling, suffering from insufficient representation capability and significant computational complexity during training and testing. In this paper, we pose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input. To handle the raw video bit-stream input, we propose a novel Three-branch Compressed-domain Spatial-temporal Fusion (TCSF) framework, which extracts and aggregates three kinds of low-level visual features (I-frame, motion vector and residual features) for effective and efficient grounding. Particularly, instead of encoding the whole decoded frames like previous works, we capture the appearance representation by only learning the I-frame feature to reduce delay or latency. Besides, we explore the motion information not only by learning the motion vector feature, but also by exploring the relations of neighboring frames via the residual feature. In this way, a three-branch spatial-temporal attention layer with an adaptive motion-appearance fusion module is further designed to extract and aggregate both appearance and motion information for the final grounding. Experiments on three challenging datasets shows that our TCSF achieves better performance than other state-of-the-art methods with lower complexity.
PDF Accepted by CVPR-23
点此查看论文截图
ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution
Authors:Shuyao Shang, Zhengyang Shan, Guangxing Liu, Jinglin Zhang
Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN-predicted image. In contrast to the common diffusion-based methods that directly use LR images to guide the noise towards HR space, ResDiff utilizes the CNN’s initial prediction to direct the noise towards the residual space between HR space and CNN-predicted space, which not only accelerates the generation process but also acquires superior sample quality. Additionally, a frequency-domain-based loss function for CNN is introduced to facilitate its restoration, and a frequency-domain guided diffusion is designed for DPM on behalf of predicting high-frequency details. The extensive experiments on multiple benchmark datasets demonstrate that ResDiff outperforms previous diffusion-based methods in terms of shorter model convergence time, superior generation quality, and more diverse samples.
PDF 18 pages, 13 figures
点此查看论文截图
Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation
Authors:Xinyue Huo, Lingxi Xie, Wengang Zhou, Houqiang Li, Qi Tian
We study unsupervised domain adaptation (UDA) for semantic segmentation. Currently, a popular UDA framework lies in self-training which endows the model with two-fold abilities: (i) learning reliable semantics from the labeled images in the source domain, and (ii) adapting to the target domain via generating pseudo labels on the unlabeled images. We find that, by decreasing/increasing the proportion of training samples from the target domain, the ‘learning ability’ is strengthened/weakened while the ‘adapting ability’ goes in the opposite direction, implying a conflict between these two abilities, especially for a single model. To alleviate the issue, we propose a novel dual teacher-student (DTS) framework and equip it with a bidirectional learning strategy. By increasing the proportion of target-domain data, the second teacher-student model learns to ‘Focus on Your Target’ while the first model is not affected. DTS is easily plugged into existing self-training approaches. In a standard UDA scenario (training on synthetic, labeled data and real, unlabeled data), DTS shows consistent gains over the baselines and sets new state-of-the-art results of 76.5\% and 75.1\% mIoUs on GTAv$\rightarrow$Cityscapes and SYNTHIA$\rightarrow$Cityscapes, respectively.
PDF 12 pages, 7 figures, 10 tables
点此查看论文截图
A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation
Authors:Hui Tang, Kui Jia
Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. However, exhaustive data annotation is impracticable for each task of all domains of interest, due to high labor costs and unguaranteed labeling accuracy. Besides, the uncontrollable data collection process produces non-IID training and test data, where undesired duplication may exist. All these nuisances may hinder the verification of typical theories and exposure to new findings. To circumvent them, an alternative is to generate synthetic data via 3D rendering with domain randomization. We in this work push forward along this line by doing profound and extensive research on bare supervised learning and downstream domain adaptation. Specifically, under the well-controlled, IID data setting enabled by 3D rendering, we systematically verify the typical, important learning insights, e.g., shortcut learning, and discover the new laws of various data regimes and network architectures in generalization. We further investigate the effect of image formation factors on generalization, e.g., object scale, material texture, illumination, camera viewpoint, and background in a 3D scene. Moreover, we use the simulation-to-reality adaptation as a downstream task for comparing the transferability between synthetic and real data when used for pre-training, which demonstrates that synthetic data pre-training is also promising to improve real test results. Lastly, to promote future research, we develop a new large-scale synthetic-to-real benchmark for image classification, termed S2RDA, which provides more significant challenges for transfer from simulation to reality. The code and datasets are available at https://github.com/huitangtang/On_the_Utility_of_Synthetic_Data.
PDF 24 pages, 14 figures, 5 tables, accepted by the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. The proposed new synthetic-to-real benchmark S2RDA is available at https://pan.baidu.com/s/17C5lRDf7cpGR1kAVS2jS-Q?pwd=61tt
点此查看论文截图
3D Masked Autoencoding and Pseudo-labeling for Domain Adaptive Segmentation of Heterogeneous Infant Brain MRI
Authors:Xuzhe Zhang, Yuhao Wu, Jia Guo, Jerod M. Rasmussen, Thomas G. O’Connor, Hyagriv N. Simhan, Sonja Entringer, Pathik D. Wadhwa, Claudia Buss, Cristiane S. Duarte, Andrea Jackowski, Hai Li, Jonathan Posner, Andrew F. Laine, Yun Wang
Robust segmentation of infant brain MRI across multiple ages, modalities, and sites remains challenging due to the intrinsic heterogeneity caused by different MRI scanners, vendors, or acquisition sequences, as well as varying stages of neurodevelopment. To address this challenge, previous studies have explored domain adaptation (DA) algorithms from various perspectives, including feature alignment, entropy minimization, contrast synthesis (style transfer), and pseudo-labeling. This paper introduces a novel framework called MAPSeg (Masked Autoencoding and Pseudo-labelling Segmentation) to address the challenges of cross-age, cross-modality, and cross-site segmentation of subcortical regions in infant brain MRI. Utilizing 3D masked autoencoding as well as masked pseudo-labeling, the model is able to jointly learn from labeled source domain data and unlabeled target domain data. We evaluated our framework on expert-annotated datasets acquired from different ages and sites. MAPSeg consistently outperformed other methods, including previous state-of-the-art supervised baselines, domain generalization, and domain adaptation frameworks in segmenting subcortical regions regardless of age, modality, or acquisition site. The code and pretrained encoder will be publicly available at https://github.com/XuzheZ/MAPSeg
PDF
点此查看论文截图