Video semantic segmentation is an essential task for the analysis and understanding of videos. Recent efforts largely focus on supervised video segmentation by learning from fully annotated data, but the learnt models often experience clear performance drop while applied to videos of a different domain. This paper presents DA-VSN, a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos. DA-VSN consists of two novel and complementary designs. The first is cross-domain TCR that guides the prediction of target frames to have similar temporal consistency as that of source frames (learnt from annotated source data) via adversarial learning. The second is intra-domain TCR that guides unconfident predictions of target frames to have similar temporal consistency as confident predictions of target frames. Extensive experiments demonstrate the superiority of our proposed domain adaptive video segmentation network which outperforms multiple baselines consistently by large margins.
论文检索
输入标题、作者或关键词，从 1,612 篇学术成果中精准定位
Increasing demands for understanding the internal behavior of convolutional neural networks (CNNs) have led to remarkable improvements in explanation methods. Particularly, several class activation mapping (CAM) based methods, which generate visual explanation maps by a linear combination of activation maps from CNNs, have been proposed. However, the majority of the methods lack a clear theoretical basis on how they assign the coefficients of the linear combination. In this paper, we revisit the intrinsic linearity of CAM with respect to the activation maps; we construct an explanation model of CNN as a linear function of binary variables that denote the existence of the corresponding activation maps. With this approach, the explanation model can be determined by additive feature attribution methods in an analytic manner. We then demonstrate the adequacy of SHAP values, which is a unique solution for the explanation model with a set of desirable properties, as the coefficients of CAM. Since the exact SHAP values are unattainable, we introduce an efficient approximation method, LIFT-CAM, based on DeepLIFT. Our proposed LIFT-CAM can estimate the SHAP values of the activation maps with high speed and accuracy. Furthermore, it greatly outperforms other previous CAM-based methods in both qualitative and quantitative aspects.
Point cloud completion is an interesting and challenging task in 3D vision, aiming to recover complete shapes from sparse and incomplete point clouds. Existing learning-based methods often require vast computation cost to achieve excellent performance, which limits their practical applications. In this paper, we propose a novel Recurrent Forward Network (RFNet), which is composed of three modules: Recurrent Feature Extraction (RFE), Forward Dense Completion (FDC) and Raw Shape Protection (RSP). The RFE extracts multiple global features from the incomplete point clouds for different recurrent levels, and the FDC generates point clouds in a coarse-to-fine pipeline. The RSP introduces details from the original incomplete models to refine the completion results. Besides, we propose a Sampling Chamfer Distance to better capture the shapes of models and a new Balanced Expansion Constraint to restrict the expansion distances from coarse to fine. According to the experiments on ShapeNet and KITTI, our network can achieve the state-of-the-art with lower memory cost and faster convergence.
In this paper, given a small bag of images, each containing a common but latent predicate, we are interested in localizing visual subject-object pairs connected via the common predicate in each of the images. We refer to this novel problem as visual relationship co-localization or VRC as an abbreviation. VRC is a challenging task, even more so than the well-studied object co-localization task. This becomes further challenging when using just a few images, the model has to learn to co-localize visual subject-object pairs connected via unseen predicates. To solve VRC, we propose an optimization framework to select a common visual relationship in each image of the bag. The goal of the optimization framework is to find the optimal solution by learning visual relationship similarity across images in a few-shot setting. To obtain robust visual relationship representation, we utilize a simple yet effective technique that learns relationship embedding as a translation vector from visual subject to visual object in a shared space. Further, to learn visual relationship similarity, we utilize a proven meta-learning technique commonly used for few-shot classification tasks. Finally, to tackle the combinatorial complexity challenge arising from an exponential number of feasible solutions, we use a greedy approximation inference algorithm that selects approximately the best solution. We extensively evaluate our proposed framework on variations of bag sizes obtained from two challenging public datasets, namely VrR-VG and VG-150, and achieve impressive visual co-localization performance.
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
PDF ↗Recent research has shown that it is possible to find interpretable directions in the latent spaces of pre-trained Generative Adversarial Networks (GANs). These directions enable controllable image generation and support a wide range of semantic editing operations, such as zoom or rotation. The discovery of such directions is often done in a supervised or semi-supervised manner and requires manual annotations which limits their use in practice. In comparison, unsupervised discovery allows finding subtle directions that are difficult to detect a priori. In this work, we propose a contrastive learning-based approach to discover semantic directions in the latent space of pre-trained GANs in a self-supervised manner. Our approach finds semantically meaningful dimensions compatible with state-of-the-art methods.
Deep features have been proven powerful in building accurate dense semantic correspondences in various previous works. However, the multi-scale and pyramidal hierarchy of convolutional neural networks has not been well studied to learn discriminative pixel-level features for semantic correspondence. In this paper, we propose a multiscale matching network that is sensitive to tiny semantic differences between neighboring pixels. We follow the coarse-to-fine matching strategy, and build a top-down feature and matching enhancement scheme that is coupled with the multi-scale hierarchy of deep convolutional neural networks. During feature enhancement, intra-scale enhancement fuses same-resolution feature maps from multiple layers together via local self-attention, and cross-scale enhancement hallucinates higher resolution feature maps along the top-down hierarchy. Besides, we learn complementary matching details at different scales, and thus the overall matching score is refined by features at different semantic levels gradually. Our multi-scale matching network can be trained end-to-end easily with few additional learnable parameters. Experimental results demonstrate the proposed method achieves state-of-the-art performance on three popular benchmarks with high computational efficiency.
Understanding complex social interactions among agents is a key challenge for trajectory prediction. Most existing methods consider the interactions between pairwise traffic agents or in a local area, while the nature of interactions is unlimited, involving an uncertain number of agents and non-local areas simultaneously. Besides, they treat heterogeneous traffic agents the same, namely those among agents of different categories, while neglecting people's diverse reaction patterns toward traffic agents in different categories. To address these problems, we propose a simple yet effective Unlimited Neighborhood Interaction Network (UNIN), which predicts trajectories of heterogeneous agents in multiple categories. Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area. Meanwhile, a hierarchical graph attention module is proposed to obtain category-to-category interaction and agent-to-agent interaction. Finally, parameters of a Gaussian Mixture Model are estimated for generating the future trajectories. Extensive experimental results on benchmark datasets demonstrate a significant performance improvement of our method over the state-of-the-art methods.
Crowd counting is a difficult task because of the diversity of scenes. Most of the existing crowd counting methods adopt complex structures with massive backbones to enhance the generalization ability. Unfortunately, the performance of existing methods on large-scale data sets is not satisfactory. In order to handle various scenarios with less complex network, we explored how to efficiently use the multi-expert model for crowd counting tasks. We mainly focus on how to train more efficient expert networks and how to choose the most suitable expert. Specifically, we propose a task-driven similarity metric based on sample's mutual enhancement, referred as co-fine-tune similarity, which can find a more efficient subset of data for training the expert network. Similar samples are considered as a cluster which is used to obtain parameters of an expert. Besides, to make better use of the proposed method, we design a simple network called FPN with Deconvolution Counting Network, which is a more suitable base model for the multi-expert counting network. Experimental results show that multiple experts FDC (MFDC) achieves the best performance on four public data sets, including the large scale NWPU-Crowd data set. Furthermore, the MFDC trained on an extensive dense crowd data set can generalize well on the other data sets without extra training or fine-tuning.
We present a general learning-based solution for restoring images suffering from spatially-varying degradations. Prior approaches are typically degradation-specific and employ the same processing across different images and different pixels within. However, we hypothesize that such spatially rigid processing is suboptimal for simultaneously restoring the degraded pixels as well as reconstructing the clean regions of the image. To overcome this limitation, we propose SPAIR, a network design that harnesses distortion-localization information and dynamically adjusts computation to difficult regions in the image. SPAIR comprises of two components, (1) a localization network that identifies degraded pixels, and (2) a restoration network that exploits knowledge from the localization network in filter and feature domain to selectively and adaptively restore degraded pixels. Our key idea is to exploit the non-uniformity of heavy degradations in spatial-domain and suitably embed this knowledge within distortion-guided modules performing sparse normalization, feature extraction and attention. Our architecture is agnostic to physical formation model and generalizes across several types of spatially-varying degradations. We demonstrate the efficacy of SPAIR individually on four restoration tasks- removal of rain-streaks, raindrops, shadows and motion blur. Extensive qualitative and quantitative comparisons with prior art on 11 benchmark datasets demonstrate that our degradation-agnostic network design offers significant performance gains over state-of-the-art degradation-specific architectures. Code available at https://github.com/human-analysis/spatially-adaptive-image-restoration.
We present DocFormer - a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU). VDU is a challenging problem which aims to understand documents in their varied formats(forms, receipts etc.) and layouts. In addition, DocFormer is pre-trained in an unsupervised fashion using carefully designed tasks which encourage multi-modal interaction. DocFormer uses text, vision and spatial features and combines them using a novel multi-modal self-attention layer. DocFormer also shares learned spatial embeddings across modalities which makes it easy for the model to correlate text to visual tokens and vice versa. DocFormer is evaluated on 4 different datasets each with strong baselines. DocFormer achieves state-of-the-art results on all of them, sometimes beating models 4x its size (in no. of parameters)
It is common practice to represent spoken languages at their phonetic level. However, for sign languages, this implies breaking motion into its constituent motion primitives. Avatar based Sign Language Production (SLP) has traditionally done just this, building up animation from sequences of hand motions, shapes and facial expressions. However, more recent deep learning based solutions to SLP have tackled the problem using a single network that estimates the full skeletal structure. We propose splitting the SLP task into two distinct jointly-trained sub-tasks. The first translation sub-task translates from spoken language to a latent sign language representation, with gloss supervision. Subsequently, the animation sub-task aims to produce expressive sign language sequences that closely resemble the learnt spatio-temporal representation. Using a progressive transformer for the translation sub-task, we propose a novel Mixture of Motion Primitives (MoMP) architecture for sign language animation. A set of distinct motion primitives are learnt during training, that can be temporally combined at inference to animate continuous sign language sequences. We evaluate on the challenging RWTH-PHOENIX-Weather-2014T(PHOENIX14T) dataset, presenting extensive ablation studies and showing that MoMP outperforms baselines in user evaluations. We achieve state-of-the-art back translation performance with an 11% improvement over competing results. Importantly, and for the first time, we showcase stronger performance for a full translation pipeline going from spoken language to sign, than from gloss to sign.
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature space with high similarity, which usually leads to wrong pairwise relationship for large neighborhoods because the Euclidean distance fails to depict the true semantic similarity on the feature manifold. On the contrary, our method mines the feature manifold in an unsupervised manner, through which the semantic similarity among instances is learned in order to obtain discriminative representations. Specifically, we employ the Generative Adversarial Networks (GAN) to mine the underlying feature manifold, where the generated features are applied as the proxies to progressively explore the feature manifold so that the semantic similarity among instances is acquired as reliable pseudo supervision. Extensive experiments on image classification demonstrate the superiority of our method compared with the state-of-the-art methods. The code is available at https://github.com/ZiweiWangTHU/ISL.git.
Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods via delicately designing various types of knowledge, they overlook the functional properties of neural networks, which makes the process of applying those techniques to new tasks unreliable and non-trivial. To alleviate such problem, in this paper, we initially leverage Lipschitz continuity to better represent the functional characteristic of neural networks and guide the knowledge distillation process. In particular, we propose a novel Lipschitz Continuity Guided Knowledge Distillation framework to faithfully distill knowledge by minimizing the distance between two neural networks' Lipschitz constants, which enables teacher networks to better regularize student networks and improve the corresponding performance. We derive an explainable approximation algorithm with an explicit theoretical derivation to address the NP-hard problem of calculating the Lipschitz constant. Experimental results have shown that our method outperforms other benchmarks over several knowledge distillation tasks (e.g., classification, segmentation and object detection) on CIFAR-100, ImageNet, and PASCAL VOC datasets.
We propose 3DETR, an end-to-end Transformer based object detection model for 3D point clouds. Compared to existing detection methods that employ a number of 3D-specific inductive biases, 3DETR requires minimal modifications to the vanilla Transformer block. Specifically, we find that a standard Transformer with non-parametric queries and Fourier positional embeddings is competitive with specialized architectures that employ libraries of 3D-specific operators with hand-tuned hyperparameters. Nevertheless, 3DETR is conceptually simple and easy to implement, enabling further improvements by incorporating 3D domain knowledge. Through extensive experiments, we show 3DETR outperforms the well-established and highly optimized VoteNet baselines on the challenging ScanNetV2 dataset by 9.5%. Furthermore, we show 3DETR is applicable to 3D tasks beyond detection, and can serve as a building block for future research.
Despite the success of self-supervised representation learning on planar data, to date it has not been studied on 360deg images. In this paper, we extend recent advances in contrastive learning to learn latent representations that are sufficiently invariant to be highly effective for spherical saliency prediction as a downstream task. We argue that omni-directional images are particularly suited to such an approach due to the geometry of the data domain. To verify this hypothesis, we design an unsupervised framework that effectively maximizes the mutual information between the different views from both the equator and the poles. We show that the decoder is able to learn good quality saliency distributions from the encoder embeddings. Our model compares favorably with fully-supervised learning methods on the Salient360!, VR-EyeTracking and Sitzman datasets. This performance is achieved using an encoder that is trained in a completely unsupervised way and a relatively lightweight supervised decoder (3.8 X fewer parameters in the case of the ResNet50 encoder). We believe that this combination of supervised and unsupervised learning is an important step toward flexible formulations of human visual attention.
Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learning offers excellent recognition results, its computational expense limits its impact for many real-world applications. In this paper, we propose an adaptive multi-modal learning framework, called AdaMML, that selects on-the-fly the optimal modalities for each segment conditioned on the input for efficient video recognition. Specifically, given a video segment, a multi-modal policy network is used to decide what modalities should be used for processing by the recognition model, with the goal of improving both accuracy and efficiency. We efficiently train the policy network jointly with the recognition model using standard back-propagation. Extensive experiments on four challenging diverse datasets demonstrate that our proposed adaptive approach yields 35%-55% reduction in computation when compared to the traditional baseline that simply uses all the modalities irrespective of the input, while also achieving consistent improvements in accuracy over the state-of-the-art methods. Project page: https://rpand002.github.io/adamml.html.
The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applications in the explanation of visual predictions and weakly-supervised localization tasks. However, CAM has its own shortcomings. The computation of attribution maps relies on ad-hoc calibration steps that are not part of the training computational graph, making it difficult for us to understand the real meaning of the attribution values. In this paper, we improve CAM by explicitly incorporating a latent variable encoding the location of the cue for recognition in the formulation, thereby subsuming the attribution map into the training computational graph. The resulting model, class activation latent mapping, or CALM, is trained with the expectation-maximization algorithm. Our experiments show that CALM identifies discriminative attributes for image classifiers more accurately than CAM and other visual attribution baselines. CALM also shows performance improvements over prior arts on the weakly-supervised object localization benchmarks. Our code is available at https://github.com/naver-ai/calm.
One of the most critical problems in weight-sharing neural architecture search is the evaluation of candidate models within a predefined search space. In practice, a one-shot supernet is trained to serve as an evaluator. A faithful ranking certainly leads to more accurate searching results. However, current methods are prone to making misjudgments. In this paper, we prove that their biased evaluation is due to inherent unfairness in the supernet training. In view of this, we propose two levels of constraints: expectation fairness and strict fairness. Particularly, strict fairness ensures equal optimization opportunities for all choice blocks throughout the training, which neither overestimates nor underestimates their capacity. We demonstrate that this is crucial for improving the confidence of models' ranking. Incorporating the one-shot supernet trained under the proposed fairness constraints with a multi-objective evolutionary search algorithm, we obtain various state-of-the-art models, e.g., FairNAS-A attains 77.5% top-1 validation accuracy on ImageNet.
Most unsupervised domain adaptation methods rely on rich prior knowledge about the source-target label set relationship, and they cannot recognize categories beyond the source classes, which limits their applicability in practical scenarios. This paper proposes a new paradigm for unsupervised domain adaptation, termed as Active Universal Domain Adaptation (AUDA), which removes all label set assumptions and aims for not only recognizing target samples from source classes but also inferring those from target-private classes by using active learning to annotate a small budget of target data. For AUDA, it is challenging to jointly adapt the model to the target domain and select informative target samples for annotations under a large domain gap and significant semantic shift. To address the problems, we propose an Active Universal Adaptation Network (AUAN). Specifically, we first introduce Adversarial and Diverse Curriculum Learning (ADCL), which progressively aligns source and target domains to classify whether target samples are from source classes. Then, we propose a Clustering Non-transferable Gradient Embedding (CNTGE) strategy, which utilizes the clues of transferability, diversity, and uncertainty to annotate target informative sample, making it possible to infer labels for target samples of target-private classes. Finally, we propose to jointly train ADCL and CNTGE with target supervision to promote domain adaptation and target-private class recognition. Extensive experiments demonstrate that the proposed AUDA model equipped with ADCL and CNTGE achieves significant results on four popular benchmarks.
We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps with decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers. As a result, we propose LeViT: a hybrid neural network for fast inference image classification. We consider different measures of efficiency on different hardware platforms, so as to best reflect a wide range of application scenarios. Our extensive experiments empirically validate our technical choices and show they are suitable to most architectures. Overall, LeViT significantly outperforms existing convnets and vision transformers with respect to the speed/accuracy tradeoff. For example, at 80% ImageNet top-1 accuracy, LeViT is 5 times faster than EfficientNet on CPU. We release the code at https://github.com/facebookresearch/LeViT.