We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutional networks with the efficiency of standard convolutional layers in two and three-dimensional dense grids. The new block operates via multiple parallel heads, whereas each head differentiably rasterizes feature representations of individual points into a low-dimensional space, and then uses dense convolution to propagate information across points. The results of the processing of individual heads are then combined together resulting in the update of point features. Using the new block, we build architectures for both discriminative (point cloud segmentation, point cloud classification) and generative (point cloud inpainting and image-based point cloud reconstruction) tasks. The resulting architectures achieve state-of-the-art performance for these tasks, demonstrating the versatility of the new block for point cloud processing.
论文检索
输入标题、作者或关键词，从 7,876 篇学术成果中精准定位
This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextual information within individual images. Though impressive, these methods neglect the significance of the representations of the pixels of the corresponding class beyond the input image. To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations. We first set up a feature memory module, which is updated dynamically during training, to store the dataset-level representations of various categories. Then, we learn class probability distribution of each pixel representation under the supervision of the ground-truth segmentation. At last, the representation of each pixel is augmented by aggregating the dataset-level representations based on the corresponding class probability distribution. Furthermore, by utilizing the stored dataset-level representations, we also propose a representation consistent learning strategy to make the classification head better address intra-class compactness and inter-class dispersion. The proposed method could be effortlessly incorporated into existing segmentation frameworks (e.g., FCN, PSPNet, OCRNet and DeepLabV3) and brings consistent performance improvements. Mining contextual information beyond image allows us to report state-of-the-art performance on various benchmarks: ADE20K, LIP, Cityscapes and COCO-Stuff.
Real-world machine learning systems need to analyze novel testing data that differs from the training data. In K-way classification, this is crisply formulated as open-set recognition, core to which is the ability to discriminate open-set data outside the K closed-set classes. Two conceptually elegant ideas for open-set discrimination are: 1) discriminatively learning an open-vs-closed binary discriminator by exploiting some outlier data as the open-set, and 2) unsupervised learning the closed-set data distribution with a GAN and using its discriminator as the open-set likelihood function. However, the former generalizes poorly to diverse open test data due to overfitting to the training outliers, which unlikely exhaustively span the open-world. The latter does not work well, presumably due to the instable training of GANs. Motivated by the above, we propose OpenGAN, which addresses the limitation of each approach by combining them with several technical insights. First, we show that a carefully selected GAN-discriminator on some real outlier data already achieves the state-of-the-art. Second, we augment the available set of real open training examples with adversarially synthesized ""fake"" data. Third and most importantly, we build the discriminator over the features computed by the closed-world K-way networks. Extensive experiments show that OpenGAN significantly outperforms prior open-set methods.
The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still growing number of evidences showing that these models suffer over-fitting especially when the training data is limited. This paper offers an empirical study by performing step-by-step operations to gradually transit a Transformer-based model to a convolution-based model. The results we obtain during the transition process deliver useful messages for improving visual recognition. Based on these observations, we propose a new architecture named Visformer, which is abbreviated from the 'Vision-friendly Transformer'. With the same computational complexity, Visformer outperforms both the Transformer-based and convolution-based models in terms of ImageNet classification accuracy, and the advantage becomes more significant when the model complexity is lower or the training set is smaller. The code is available at https://github.com/danczs/Visformer.
For all the ways convolutional neural nets have revolutionized computer vision in recent years, one important aspect has received surprisingly little attention: the effect of image size on the accuracy of tasks being trained for. Typically, to be efficient, the input images are resized to a relatively small spatial resolution (e.g. 224x224), and both training and inference are carried out at this resolution. The actual mechanism for this re-scaling has been an afterthought: Namely, off-the-shelf image resizers such as bilinear and bicubic are commonly used in most machine learning software frameworks. But do these resizers limit the on task performance of the trained networks? The answer is yes. Indeed, we show that the typical linear resizer can be replaced with learned resizers that can substantially improve performance. Importantly, while the classical resizers typically result in better perceptual quality of the downscaled images, our proposed learned resizers do not necessarily give better visual quality, but instead improve task performance. Our learned image resizer is jointly trained with a baseline vision model. This learned CNN-based resizer creates machine friendly visual manipulations that lead to a consistent improvement of the end task metric over the baseline model. Specifically, here we focus on the classification task with the ImageNet dataset, and experiment with four different models to learn resizers adapted to each model. Moreover, we show that the proposed resizer can also be useful for fine-tuning the classification baselines for other vision tasks. To this end, we experiment with three different baselines to develop image quality assessment (IQA) models on the AVA dataset.
Recent strategies achieved ensembling ""for free"" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork learns to classify only one of the multiple inputs simultaneously provided. However, the question of how to best mix these multiple inputs has not been studied so far. In this paper, we introduce MixMo, a new generalized framework for learning multi-input multi-output deep subnetworks. Our key motivation is to replace the suboptimal summing operation hidden in previous approaches by a more appropriate mixing mechanism. For that purpose, we draw inspiration from successful mixed sample data augmentations. We show that binary mixing in features - particularly with rectangular patches from CutMix - enhances results by making subnetworks stronger and more diverse. We improve state of the art for image classification on CIFAR-100 and Tiny ImageNet datasets. Our easy to implement models notably outperform data augmented deep ensembles, without the inference and memory overheads. As we operate in features and simply better leverage the expressiveness of large networks, we open a new line of research complementary to previous works.
As a challenging task of high-level video understanding, weakly supervised temporal action localization has been attracting increasing attention. With only video annotations, most existing methods seek to handle this task with a localization-by-classification framework, which generally adopts a selector to select snippets of high probabilities of actions or namely the foreground. Nevertheless, the existing foreground selection strategies have a major limitation of only considering the unilateral relation from foreground to actions, which cannot guarantee the foreground-action consistency. In this paper, we present a framework named FAC-Net based on the I3D backbone, on which three branches are appended, named class-wise foreground classification branch, class-agnostic attention branch and multiple instance learning branch. First, our class-wise foreground classification branch regularizes the relation between actions and foreground to maximize the foreground-background separation. Besides, the class-agnostic attention branch and multiple instance learning branch are adopted to regularize the foreground-action consistency and help to learn a meaningful foreground classifier. Within each branch, we introduce a hybrid attention mechanism, which calculates multiple attention scores for each snippet, to focus on both discriminative and less-discriminative snippets to capture the full action boundaries. Experimental results on THUMOS14 and ActivityNet1.3 demonstrate the superior performance over state-of-the-art approaches.
In this paper, we seek reasons for the two major failure cases in Semantic Segmentation (SS): 1) missing small objects or minor object parts, and 2) mislabeling minor parts of large objects as wrong classes. We have an interesting finding that Failure-1 is due to the underuse of detailed features and Failure-2 is due to the underuse of visual contexts. To help the model learn a better trade-off, we introduce several Self-Regulation (SR) losses for training SS neural networks. By "self", we mean that the losses are from the model per se without using any additional data or supervision. By applying the SR losses, the deep layer features are regulated by the shallow ones to preserve more details; meanwhile, shallow layer classification logits are regulated by the deep ones to capture more semantics. We conduct extensive experiments on both weakly and fully supervised SS tasks, and the results show that our approach consistently surpasses the baselines. We also validate that SR losses are easy to implement in various state-of-the-art SS models, e.g., SPGNet and OCRNet, incurring little computational overhead during training and none for testing
Aggregating features from different depths of a network is widely adopted to improve the network capability. Lots of modern architectures are equipped with skip connections, which actually makes the feature aggregation happen in all these networks. Since different features tell different semantic meanings, there are inconsistencies and incompatibilities to be solved. However, existing works naively blend deep features via element-wise summation or concatenation with a convolution behind. Better feature aggregation method beyond summation or concatenation is rarely explored. In this paper, given two layers of features to be aggregated together, we first detect and identify where and what needs to be updated in one layer, then replace the feature at the identified location with the information of the other layer. This process, which we call DEtect-rePLAce (DEPLA), enables us to avoid inconsistent patterns while keeping useful information in the merged outputs. Experimental results demonstrate our method largely boosts multiple baselines e.g. ResNet, FishNet and FPN on three major vision tasks including ImageNet classification, MS COCO object detection and instance segmentation.
We contribute HAA500, a manually annotated human-centric atomic action dataset for action recognition on 500 classes with over 591K labeled frames. To minimize ambiguities in action classification, HAA500 consists of highly diversified classes of fine-grained atomic actions, where only consistent actions fall under the same label, e.g., ""Baseball Pitching"" vs ""Free Throw in Basketball"". Thus HAA500 is different from existing atomic action datasets, where coarse-grained atomic actions were labeled with coarse action-verbs such as ""Throw"". HAA500 has been carefully curated to capture the precise movement of human figures with little class-irrelevant motions or spatio-temporal label noises. The advantages of HAA500 are fourfold: 1) human-centric actions with a high average of 69.7% detectable joints for the relevant human poses; 2) high scalability since adding a new class can be done under 20-60 minutes; 3) curated videos capturing essential elements of an atomic action without irrelevant frames; 4) fine-grained atomic action classes. Our extensive experiments including cross-data validation using datasets collected in the wild demonstrate the clear benefits of human-centric and atomic characteristics of HAA500, which enable training even a baseline deep learning model to improve prediction by attending to atomic human poses. We detail the HAA500 dataset statistics and collection methodology and compare quantitatively with existing action recognition datasets.
Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets. In this paper, we propose LocTex that takes advantage of the low-cost localized textual annotations (i.e., captions and synchronized mouse-over gestures) to reduce the annotation effort. We introduce a contrastive pre-training framework between images and captions and propose to supervise the cross-modal attention map with rendered mouse traces to provide coarse localization signals. Our learned visual features capture rich semantics (from free-form captions) and accurate localization (from mouse traces), which are very effective when transferred to various downstream vision tasks. Compared with ImageNet supervised pre-training, LocTex can reduce the size of the pre-training dataset by 10x or the target dataset by 2x while achieving comparable or even improved performance on COCO instance segmentation. When provided with the same amount of annotations, LocTex achieves around 4% higher accuracy than the previous state-of-the-art "vision+language" pre-training approach on the task of PASCAL VOC image classification.
We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that the transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3xwhile keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention, which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirements, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.
Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task. The effect of this type of training on semantic segmentation, contrarily, just commences. We make the initial attempt to explore the defense strategy on semantic segmentation by formulating a general adversarial training procedure that can perform decently on both adversarial and clean samples. We propose a dynamic divide-and-conquer adversarial training (DDC-AT) strategy to enhance the defense effect, by setting additional branches in the target model during training, and dealing with pixels with diverse properties towards adversarial perturbation. Our dynamical division mechanism divides pixels into multiple branches automatically. Note all these additional branches can be abandoned during inference and thus leave no extra parameter and computation cost. Extensive experiments with various segmentation models are conducted on PASCAL VOC 2012 and Cityscapes datasets, in which DDC-AT yields satisfying performance under both white- and black-box attack. The code is available at https://github.com/dvlab-research/Robust-Semantic-Segmentation.
The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data scalability issue, while the existing works usually focus on classifying independently discrete labels. However, in many tasks (e.g., medical diagnosis), the labels are discrete and successively distributed. The UDA for ordinal classification requires inducing non-trivial ordinal distribution prior to the latent space. Target for this, the partially ordered set (poset) is defined for constraining the latent vector. Instead of the typically i.i.d. Gaussian latent prior, in this work, a recursively conditional Gaussian (RCG) set is adapted for ordered constraint modeling, which admits a tractable joint distribution prior. Furthermore, we are able to control the density of content vector that violates the poset constraints by a simple "three-sigma rule". We explicitly disentangle the cross-domain images into a shared ordinal prior induced ordinal content space and two separate source/target ordinal-unrelated spaces, and the self-training is worked on the shared space exclusively for ordinal-aware domain alignment. Extensive experiments on UDA medical diagnoses and facial age estimation demonstrate its effectiveness.
Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained models to produce coarse saliency maps to guide the generation of pseudo segmentation labels. However, the commonly used off-line heuristic generation process cannot fully exploit the benefits of these coarse saliency maps. Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels. Inspired by their similar structured semantics, we also propose to learn a cross-task global pixel-level affinity map from the saliency and segmentation representations. The learned cross-task affinity can be used to refine saliency predictions and propagate CAM maps to provide improved pseudo labels for both tasks. The mutual boost between pseudo label updating and cross-task affinity learning enables iterative improvements on segmentation performance. Extensive experiments demonstrate the effectiveness of the proposed auxiliary learning network structure and the cross-task affinity learning method. The proposed approach achieves state-of-the-art weakly supervised segmentation performance on the challenging PASCAL VOC 2012 and MS COCO benchmarks.
Prior to Segment: Foreground Cues for Weakly Annotated Classes in Partially Supervised Instance Segmentation
PDF ↗Instance segmentation methods require large datasets with expensive and thus limited instance-level mask labels. Partially supervised instance segmentation aims to improve mask prediction with limited mask labels by utilizing the more abundant weak box labels. In this work, we show that a class agnostic mask head, commonly used in partially supervised instance segmentation, has difficulties learning a general concept of foreground for the weakly annotated classes using box supervision only. To resolve this problem, we introduce an object mask prior (OMP) that provides the mask head with the general concept of foreground implicitly learned by the box classification head under the supervision of all classes. This helps the class agnostic mask head to focus on the primary object in a region of interest (RoI) and improves generalization to the weakly annotated classes. We test our approach on the COCO dataset using different splits of strongly and weakly supervised classes. Our approach significantly improves over the Mask R-CNN baseline and obtains competitive performance with the state-of-the-art, while offering a much simpler architecture.
Human parsing and pose estimation are crucial for the understanding of human behaviors. Since these tasks are closely related, employing one unified model to perform two tasks simultaneously allows them to benefit from each other. However, since human parsing is a pixel-wise classification process while pose estimation is usually a regression task, it is non-trivial to extract discriminative features for both tasks while modeling their correlation in the joint learning fashion. Recent studies have shown that Neural Architecture Search (NAS) has the ability to allocate efficient feature connections for specific tasks automatically. With the spirit of NAS, we propose to search for an efficient network architecture (NPPNet) to tackle two tasks at the same time. On the one hand, to extract task-specific features for the two tasks and lay the foundation for the further searching of feature interaction, we propose to search their encoder-decoder architectures, respectively. On the other hand, to ensure two tasks fully communicate with each other, we propose to embed NAS units in both multi-scale feature interaction and high-level feature fusion to establish optimal connections between two tasks. Experimental results on both parsing and pose estimation benchmark datasets have demonstrated that the searched model achieves state-of-the-art performances on both tasks.
With a Little Help From My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
PDF ↗Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a contrastive loss, we are interested in using positives from other instances in the dataset. Our method, Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR), samples the nearest neighbors from the dataset in the latent space, and treats them as positives. This provides more semantic variations than pre-defined transformations. We find that using the nearest-neighbor as positive in contrastive losses improves performance significantly on ImageNet classification, from 71.7% to 75.6%, outperforming previous state-of-the-art methods. On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53.8% to 56.5%. On transfer learning benchmarks our method outperforms state-of-the-art methods (including supervised learning with ImageNet) on 8 out of 12 downstream datasets. Furthermore, we demonstrate empirically that our method is less reliant on complex data augmentations. We see a relative reduction of only 2.1% ImageNet Top-1 accuracy when we train using only random crops.
The generalization capability of deep neural networks has been substantially improved by applying a wide spectrum of regularization methods, e.g., restricting function space, injecting randomness during training, augmenting data, etc. In this work, we propose a simple yet effective regularization method named progressive self-knowledge distillation (PS-KD), which progressively distills a model's own knowledge to soften hard targets (i.e., one-hot vectors) during training. Hence, it can be interpreted within a framework of knowledge distillation as a student becomes a teacher itself. Specifically, targets are adjusted adaptively by combining the ground-truth and past predictions from the model itself. We show that PS-KD provides an effect of hard example mining by rescaling gradients according to difficulty in classifying examples. The proposed method is applicable to any supervised learning tasks with hard targets and can be easily combined with existing regularization methods to further enhance the generalization performance. Furthermore, it is confirmed that PS-KD achieves not only better accuracy, but also provides high quality of confidence estimates in terms of calibration as well as ordinal ranking. Extensive experimental results on three different tasks, image classification, object detection, and machine translation, demonstrate that our method consistently improves the performance of the state-of-the-art baselines.
We address the problem of domain generalizable object detection, which aims to learn a domain-invariant detector from multiple "seen" domains so that it can generalize well to other "unseen" domains. The generalization ability is crucial in practical scenarios especially when it is difficult to collect data. Compared to image classification, domain generalization in object detection has seldom been explored with more challenges brought by domain gaps on both image and instance levels. In this paper, we propose a novel generalizable object detection model, termed Domain-Invariant Disentangled Network (DIDN). In contrast to directly aligning multiple sources, we integrate a disentangled network into Faster R-CNN. By disentangling representations on both image and instance levels, DIDN is able to learn domain-invariant representations that are suitable for generalized object detection. Furthermore, we design a cross-level representation reconstruction to complement this two-level disentanglement so that informative object representations could be preserved. Extensive experiments are conducted on five benchmark datasets and the results demonstrate that our model achieves state-of-the-art performances on domain generalization for object detection.