CVPR 2022 论文列表

Geospatial semantic segmentation on remote sensing images suffers from large intra-class variance in both foreground and background classes. First, foreground objects are tiny in the remote sensing images and are represented by only a few pixels, which leads to large foreground intra-class variance and undermines the discrimination between foreground classes (issue firstly considered in this work). Second, background class contains complex context, which results in false alarms due to large background intra-class variance. To alleviate these two issues, we construct a sparse and complete latent structure via prototypes. In particular, to enhance the sparsity of the latent space, we design a prototypical contrastive learning to have prototypes of the same category clustering together and prototypes of different categories to be far away from each other. Also, we strengthen the completeness of the latent space by modeling all foreground categories and hardest (nearest) background objects. We further design a patch shuffle augmentation for remote sensing images with complicated contexts. Our augmentation encourages the semantic information of an object to be correlated only to the limited context within the patch that is specific to its category, which further reduces large intra-class variance. We conduct extensive evaluations on a large scale remote sensing dataset, showing our approach significantly outperforms state-of-the-art methods by a large margin.

Most state-of-the-art instance segmentation methods have to be trained on densely annotated images. While difficult in general, this requirement is especially daunting for biomedical images, where domain expertise is often required for annotation and no large public data collections are available for pre-training. We propose to address the dense annotation bottleneck by introducing a proposal-free segmentation approach based on non-spatial embeddings, which exploits the structure of the learned embedding space to extract individual instances in a differentiable way. The segmentation loss can then be applied directly to instances and the overall pipeline can be trained in a fully- or weakly supervised manner. We consider the challenging case of positive-unlabeled supervision, where a novel self-supervised consistency loss is introduced for the unlabeled parts of the training data. We evaluate the proposed method on 2D and 3D segmentation problems in different microscopy modalities as well as on the Cityscapes and CVPPP instance segmentation benchmarks, achieving state-of-the-art results on the latter.

CRF is a classical computer vision model which is also useful for deep learning. There are two common CRF types: sparse and dense. Sparse CRF connects only the nearby pixels, while dense CRF has global connectivity. Therefore dense CRF is a more general model, but it is much harder to optimize compared to sparse CRF. In fact, only a certain form of dense CRF is optimized in practice, and even then approximately. We propose a new sparse non-local CRF: it has a sparse number of connections, but it has both local and non-local ones. Like sparse CRF, the total number of connections is small, and our model is easy to optimize exactly. Like dense CRF, our model is more general than sparse CRF due to non-local connections. We show that our sparse non-local CRF can model properties similar to that of the popular Gaussian edge dense CRF. Besides efficiency, another advantage is that our edge weights are less restricted compared to Gaussian edge dense CRF. We design models that take advantage of this flexibility. We also discuss connection of our model to other CRF models. Finally, to prove the usefulness of our model, we evaluate it on the classical application of segmentation from a bounding box and for deep learning based salient object segmentation. We improve state of the art for both applications.

Heatmap regression methods have dominated face alignment area in recent years while they ignore the inherent relation between different landmarks. In this paper, we propose a Sparse Local Patch Transformer (SLPT) for learning the inherent relation. The SLPT generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism. The subpixel coordinate of each landmark is predicted independently based on the aggregated feature. Moreover, a coarse-to-fine framework is further introduced to incorporate with the SLPT, which enables the initial landmarks to gradually converge to the target facial landmarks using fine-grained features from dynamically resized local patches. Extensive experiments carried out on three popular benchmarks, including WFLW, 300W and COFW, demonstrate that the proposed method works at the state-of-the-art level with much less computational complexity by learning the inherent relation between facial landmarks. The code is available at the project website.

In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we propose a sparse set of instance activation maps, as a new object representation, to highlight informative regions for each foreground object. Then instance-level features are obtained by aggregating features according to the highlighted regions for recognition and segmentation. Moreover, based on bipartite matching, the instance activation maps can predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark, which significantly outperforms the counterparts in terms of speed and accuracy. Code and models are available at https://github.com/hustvl/SparseInst.

Recently, large pretrained models (e.g., BERT, StyleGAN, CLIP) show great knowledge transfer and generalization capability on various downstream tasks within their domains. Inspired by these efforts, in this paper we propose a unified model for open-domain image editing focusing on color and tone adjustment of open-domain images while keeping their original content and structure. Our model learns a unified editing space that is more semantic, intuitive, and easy to manipulate than the operation space (e.g., contrast, brightness, color curve) used in many existing photo editing softwares. Our model belongs to the image-to-image translation framework which consists of an image encoder and decoder, and is trained on pairs of before-and-after edited images to produce multimodal outputs. We show that by inverting image pairs into latent codes of the learned editing space, our model can be leveraged for various downstream editing tasks such as language-guided image editing, personalized editing, editing-style clustering, retrieval, etc. We extensively study the unique properties of the editing space in experiments and demonstrate superior performance on the aforementioned tasks.

Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. However, the training data in source domain required by most of the existing methods is usually unavailable in real-world applications due to privacy preserving policies. Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data. In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation. Firstly, we produce robust pseudo-labels for target data with spherical k-means clustering, whose initial class centers are the weight vectors (anchors) learned by the classifier of pretrained model. Furthermore, we propose to estimate the class-conditioned feature distribution of source domain by exploiting target data and corresponding anchors. Finally, we sample surrogate features from the estimated distribution, which are then utilized to align two domains by minimizing a contrastive adaptation loss function. Extensive experiments show that the proposed method achieves state-of-the-art performance on multiple DA benchmarks, and even outperforms traditional DA methods which require plenty of source data.

The recent success of the generative model shows that leveraging the multi-modal embedding space can manipulate an image using text information. However, manipulating an image with other sources rather than text, such as sound, is not easy due to the dynamic characteristics of the sources. Especially, sound can convey vivid emotions and dynamic expressions of the real world. Here, we propose a framework that directly encodes sound into the multi-modal (image-text) embedding space and manipulates an image from the space. Our audio encoder is trained to produce a latent representation from an audio input, which is forced to be aligned with image and text representations in the multi-modal embedding space. We use a direct latent optimization method based on aligned embeddings for sound-guided image manipulation. We also show that our method can mix different modalities, i.e., text and audio, which enrich the variety of the image modification. The experiments on zero-shot audio classification and semantic-level image classification show that our proposed model outperforms other text and sound-guided state-of-the-art methods.

Different self-supervised tasks (SSL) reveal different features from the data. The learned feature representations can exhibit different performance for each downstream task. In this light, this work aims to combine Multiple SSL tasks (Multi-SSL) that generalizes well for all downstream tasks. For this study, we investigate binaural sounds and image data. For binaural sounds, we propose three SSL tasks namely, spatial alignment, temporal synchronization of foreground objects and binaural audio and temporal gap prediction. We investigate several approaches of Multi-SSL and give insights into the downstream task performance on video retrieval, spatial sound super resolution, and semantic prediction on the OmniAudio dataset. Our experiments on binaural sound representations demonstrate that Multi-SSL via incremental learning (IL) of SSL tasks outperforms single SSL task models and fully supervised models in the downstream task performance. As a check of applicability on other modality, we also formulate our Multi-SSL models for image representation learning and we use the recently proposed SSL tasks, MoCov2 and DenseCL. Here, Multi-SSL surpasses recent methods such as MoCov2, DenseCL and DetCo by 2.06%, 3.27% and 1.19% on VOC07 classification and +2.83, +1.56 and +1.61 AP on COCO detection.

Image collage task aims to create an informative and visual-aesthetic visual summarization for an image collection. While several recent works exploit tree-based algorithm to preserve image content better, all of them resort to hand-crafted adjustment rules to optimize the collage tree structure, leading to the failure of fully exploring the structure space of collage tree. Our key idea is to soften the discrete tree structure space into a continuous probability space. We propose SoftCollage, a novel method that employs a neural-based differentiable probabilistic tree generator to produce the probability distribution of correlation-preserving collage tree conditioned on deep image feature, aspect ratio and canvas size. The differentiable characteristic allows us to formulate the tree-based collage generation as a differentiable process and directly exploit gradient to optimize the collage layout in the level of probability space in an end-to-end manner. To facilitate image collage research, we propose AIC, a large-scale public-available annotated dataset for image collage evaluation. Extensive experiments on the introduced dataset demonstrate the superior performance of the proposed method. Data and codes are available at https://github.com/ChineseYjh/SoftCollage.

Deep learning researchers have a keen interest in proposing new novel activation functions that can boost neural network performance. A good choice of activation function can have a significant effect on improving network performance and training dynamics. Rectified Linear Unit (ReLU) is a popular hand-designed activation function and is the most common choice in the deep learning community due to its simplicity though ReLU has some drawbacks. In this paper, we have proposed two new novel activation functions based on approximation of the maximum function, and we call these functions Smooth Maximum Unit (SMU and SMU-1). We show that SMU and SMU-1 can smoothly approximate ReLU, Leaky ReLU, or more general Maxout family, and GELU is a particular case of SMU. Replacing ReLU by SMU, Top-1 classification accuracy improves by 6.22%, 3.39%, 3.51%, and 3.08% on the CIFAR100 dataset with ShuffleNet V2, PreActResNet-50, ResNet-50, and SeNet-50 models respectively. Also, our experimental evaluation shows that SMU and SMU-1 improve network performance in a variety of deep learning tasks like image classification, object detection, semantic segmentation, and machine translation compared to widely used activation functions.

We present a dataset of 1000 video sequences of human portraits recorded in real and uncontrolled conditions by using a handheld smartphone accompanied by an external high-quality depth camera. The collected dataset contains 200 people captured in different poses and locations and its main purpose is to bridge the gap between raw measurements obtained from a smartphone and downstream applications, such as state estimation, 3D reconstruction, view synthesis, etc. The sensors employed in data collection are the smartphone's camera and Inertial Measurement Unit (IMU), and an external Azure Kinect DK depth camera software synchronized with sub-millisecond precision to the smartphone system. During the recording, the smartphone flash is used to provide a periodic secondary source of lightning. Accurate mask of the foremost person is provided as well as its impact on camera alignment accuracy. For evaluation purposes, we compare multiple state-of-the-art camera alignment methods by using a Motion Capture system. We provide a smartphone visual-inertial benchmark for portrait capturing, where we report results for multiple methods and motivate further use of the provided trajectories, available in the dataset, in view synthesis and 3D reconstruction tasks.

Several recent works seek to create lightweight deep networks for video object detection on mobiles. We observe that many existing detectors, previously deemed computationally costly for mobiles, intrinsically support adaptive inference, and offer a multi-branch object detection framework (MBODF). Here, an MBODF is referred to as a solution that has many execution branches and one can dynamically choose from among them at inference time to satisfy varying latency requirements (e.g. by varying resolution of an input frame). In this paper, we ask, and answer, the wide-ranging question across all MBODFs: How to expose the right set of execution branches and then how to schedule the optimal one at inference time? In addition, we uncover the importance of making a content-aware decision on which branch to run, as the optimal one is conditioned on the video content. Finally, we explore a content-aware scheduler, an Oracle one, and then a practical one, leveraging various lightweight feature extractors. Our evaluation shows that layered on Faster R-CNN-based MBODF, compared to 7 baselines, our SMARTADAPT achieves a higher Pareto optimal curve in the accuracy-vs-latency space for the ILSVRC VID dataset.

Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several sub-tasks and utilize multiple surrogates (e.g. boxes and masks, centers and offsets) to represent objects. However, this divide-and-conquer strategy requires complex post-processing in both spatial and temporal domains and is vulnerable to failures from surrogate tasks. In this paper, inspired by object-centric learning which learns compact and robust object representations, we present Slot-VPS, the first end-to-end framework for this task. We encode all panoptic entities in a video, including both foreground instances and background semantics, in a unified representation called panoptic slots. The coherent spatio-temporal object's information is retrieved and encoded into the panoptic slots by the proposed Video Panoptic Retriever, enabling to localize, segment, differentiate, and associate objects in a unified manner. Finally, the output panoptic slots can be directly converted into the class, mask, and object ID of panoptic objects in the video. We conduct extensive ablation studies and demonstrate the effectiveness of our approach on two benchmark datasets, Cityscapes-VPS (val and test sets) and VIPER (val set), achieving new state-of-the-art performance of 63.7, 63.3 and 56.2 VPQ, respectively.

Vanilla unsupervised domain adaptation methods tend to optimize the model with fixed neural architecture, which is not very practical in real-world scenarios since the target data is usually processed by different resource-limited devices. It is therefore of great necessity to facilitate architecture adaptation across various devices. In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs. The main challenge in this framework lies in simultaneously boosting the adaptation performance of numerous models in the model bank. To tackle this problem, we develop a Stochastic EnsEmble Distillation method to fully exploit the complementary knowledge in the model bank for inter-model interaction. Nevertheless, considering the optimization conflict between inter-model interaction and intra-model adaptation, we augment the existing bi-classifier domain confusion architecture into an Optimization-Separated Tri-Classifier counterpart. After optimizing the model bank, architecture adaptation is leveraged via our proposed Unsupervised Performance Evaluation Metric. Under various resource constraints, our framework surpasses other competing approaches by a very large margin on multiple benchmarks. It is also worth emphasizing that our framework can preserve the performance improvement against the source-only model even when the computing complexity is reduced to 1/64. Code will be available at https://github.com/HIK-LAB/SlimDA.

This work presents SkinningNet, an end-to-end Two-Stream Graph Neural Network architecture that computes skinning weights from an input mesh and its associated skeleton, without making any assumptions on shape class and structure of the provided mesh. Whereas previous methods pre-compute handcrafted features that relate the mesh and the skeleton or assume a fixed topology of the skeleton, the proposed method extracts this information in an end-to-end learnable fashion by jointly learning the best relationship between mesh vertices and skeleton joints. The proposed method exploits the benefits of the novel Multi-Aggregator Graph Convolution that combines the results of different aggregators during the summarizing step of the Message-Passing scheme, helping the operation to generalize for unseen topologies. Experimental results demonstrate the effectiveness of the contributions of our novel architecture, with SkinningNet outperforming current state-of-the-art alternatives.

Sketching enables many exciting applications, notably, image retrieval. The fear-to-sketch problem (i.e., "I can't sketch") has however proven to be fatal for its widespread adoption. This paper tackles this "fear" head on, and for the first time, proposes an auxiliary module for existing retrieval models that predominantly lets the users sketch without having to worry. We first conducted a pilot study that revealed the secret lies in the existence of noisy strokes, but not so much of the "I can't sketch". We consequently design a stroke subset selector that detects noisy strokes, leaving only those which make a positive contribution towards successful retrieval. Our Reinforcement Learning based formulation quantifies the importance of each stroke present in a given subset, based on the extent to which that stroke contributes to retrieval. When combined with pre-trained retrieval models as a pre-processing module, we achieve a significant gain of 8%-10% over standard baselines and in turn report new state-of-the-art performance. Last but not least, we demonstrate the selector once trained, can also be used in a plug-and-play manner to empower various sketch applications in ways that were not previously possible.

Sketch-based image manipulation is an interactive image editing task to modify an image based on input sketches from users. Existing methods typically convert this task into a conditional inpainting problem, which requires an additional mask from users indicating the region to modify. Then the masked regions are regarded as missing and filled by an inpainting model conditioned on the sketch. With this formulation, paired training data can be easily obtained by randomly creating masks and extracting edges or contours. Although this setup simplifies data preparation and model design, it complicates user interaction and discards useful information in masked regions. To this end, we propose a new framework for sketch-based image manipulation that only requires sketch inputs from users and utilizes the entire original image. Given an image and sketch, our model automatically predicts the target modification region and encodes it into a structure agnostic style vector. A generator then synthesizes the new image content based on the style vector and sketch. The manipulated image is finally produced by blending the generator output into the modification region of the original image. Our model can be trained in a self-supervised fashion by learning the reconstruction of an image region from the style vector and sketch. The proposed framework offers simpler and more intuitive user workflows for sketch-based image manipulation and provides better results than previous approaches. The code and interactive demo can be found in the supplementary material.

Zero-shot sketch-based image retrieval typically asks for a trained model to be applied as is to unseen categories. In this paper, we question to argue that this setup by definition is not compatible with the inherent abstract and subjective nature of sketches -- the model might transfer well to new categories, but will not understand sketches existing in different test-time distribution as a result. We thus extend ZS-SBIR asking it to transfer to both categories and sketch distributions. Our key contribution is a test-time training paradigm that can adapt using just one sketch. Since there is no paired photo, we make use of a sketch raster-vector reconstruction module as a self-supervised auxiliary task. To maintain the fidelity of the trained cross-modal joint embedding during test-time update, we design a novel meta-learning based training paradigm to learn a separation between model updates incurred by this auxiliary task from those off the primary objective of discriminative learning. Extensive experiments show our model to outperform state-of-the-arts, thanks to the proposed test-time adaption that not only transfers to new categories but also accommodates to new sketching styles.