We explore the plain, non-hierarchical Vision Transformer (ViT) as a backbone network for object detection. This design enables the original ViT architecture to be fine-tuned for object detection without needing to redesign a hierarchical backbone for pre-training. With minimal adaptations for fine-tuning, our plain-backbone detector can achieve competitive results. Surprisingly, we observe: (i) it is sufficient to build a simple feature pyramid from a single-scale feature map (without the common FPN design) and (ii) it is sufficient to use window attention (without shifting) aided with very few cross-window propagation blocks. With plain ViT backbones pre-trained as Masked Autoencoders (MAE), our detector, named ViTDet, can compete with the previous leading methods that were all based on hierarchical backbones, reaching up to 61.3 AP_box on the COCO dataset using only ImageNet-1K pre-training. We hope our study will draw attention to research on plain-backbone detectors. Code for ViTDet is available in Detectron2.
论文检索
输入标题、作者或关键词，从 3,199 篇学术成果中精准定位
Predicting pedestrian movement is critical for human behavior analysis and also for safe and efficient human-agent interactions. However, despite significant advancements, it is still challenging for existing approaches to capture the uncertainty and multimodality of human navigation decision making. In this paper, we propose SocialVAE, a novel approach for human trajectory prediction. The core of SocialVAE is a timewise variational autoencoder architecture that exploits stochastic recurrent neural networks to perform prediction, combined with a social attention mechanism and a backward posterior approximation to allow for better extraction of pedestrian navigation strategies. We show that SocialVAE improves current state-of-the-art performance on several pedestrian trajectory prediction benchmarks, including the ETH/UCY benchmark, Stanford Drone Dataset, and SportVU NBA movement dataset.
Existing methods for anomaly detection based on memory-augmented autoencoder (AE) have the following drawbacks: (1) Establishing a memory bank requires additional memory space. (2) The fixed number of prototypes from subjective assumptions ignores the data feature differences and diversity. To overcome these drawbacks, we introduce DLAN-AC, a Dynamic Local Aggregation Network with Adaptive Clusterer, for anomaly detection. First, The proposed DLAN can automatically learn and aggregate high-level features from the AE to obtain more representative prototypes, while freeing up extra memory space. Second, The proposed AC can adaptively cluster video data to derive initial prototypes with prior information. In addition, we also propose a dynamic redundant clustering strategy (DRCS) to enable DLAN for automatically eliminating feature clusters that do not contribute to the construction of prototypes. Extensive experiments on benchmarks demonstrate that DLAN-AC outperforms most existing methods, validating the effectiveness of our method. Our code is publicly available at https://github.com/Beyond-Zw/DLAN-AC.
Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we explore this learning paradigm for 3D mesh data analysis based on Transformers. Since applying Transformer architectures to new modalities is usually non-trivial, we first adapt Vision Transformer to 3D mesh data processing, i.e., Mesh Transformer. In specific, we divide a mesh into several non-overlapping local patches with each containing the same number of faces and use the 3D position of each patch’s center point to form positional embeddings. Inspired by MAE, we explore how pre-training on 3D mesh data with the Transformer-based structure benefits downstream 3D mesh analysis tasks. We first randomly mask some patches of the mesh and feed the corrupted mesh into Mesh Transformers. Then, through reconstructing the information of masked patches, the network is capable of learning discriminative representations for mesh data. Therefore, we name our method MeshMAE, which can yield state-of-the-art or comparable performance on mesh analysis tasks, i.e., classification and segmentation. In addition, we also conduct comprehensive ablation studies to show the effectiveness of key designs in our method.
Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like PointNet being unable to properly handle the training versus testing distribution mismatch introduced by masking during training. In this paper, we bridge this gap by proposing a discriminative mask pretraining Transformer framework, MaskPoint, for point clouds. Our key idea is to represent the point cloud as discrete occupancy values (1 if part of the point cloud; 0 if not), and perform simple binary classification between masked object points and sampled noise points as the proxy task. In this way, our approach is robust to the point sampling variance in point clouds, and facilitates learning rich representations. We evaluate our pretrained models across several downstream tasks, including 3D shape classification, segmentation, and real-word object detection, and demonstrate state-of-the-art results while achieving a significant pretraining speedup (e.g., 4.1x on ScanNet) compared to the prior state-of-the-art Transformer baseline. Code is available at https://github.com/haotian-liu/MaskPoint.
As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud self-supervised learning, addressing the challenges posed by point cloud’s properties, including leakage of location information and uneven information density. Concretely, we divide the input point cloud into irregular point patches and randomly mask them at a high ratio. Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches. Extensive experiments show that our approach is efficient during pre-training and generalizes well on various downstream tasks. The pre-trained models achieve 85.18% accuracy on ScanObjectNN and 94.04% accuracy on ModelNet40, outperforming all the other self-supervised learning methods. We show with our scheme, a simple architecture entirely based on standard Transformers can surpass dedicated Transformer models from supervised learning. Our approach also advances state-of-the-art accuracies by 1.5%-2.3% in the few-shot classification. Furthermore, our work inspires the feasibility of applying unified architectures from languages and images to the point cloud. Codes are available at https://github.com/Pang-Yatian/Point-MAE.
In this paper, we formulate a potentially valuable panoramic depth completion (PDC) task as panoramic 3D cameras often produce 360° depth with missing data in complex scenes. Its goal is to recover dense panoramic depths from raw sparse ones and panoramic RGB images. To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery. However, it needs to face a challenging optimization problem of the network parameters due to its non-convex objective function. To address this problem, we propose a simple yet effective approach termed M³PT: multi-modal masked pre-training. Specifically, during pre-training, we simultaneously cover up patches of the panoramic RGB image and sparse depth by shared random mask, then reconstruct the sparse depth in the masked regions. To our best knowledge, it is the first time that we show the effectiveness of masked pre-training in a multi-modal vision task, instead of the single-modal task resolved by masked autoencoders (MAE). Different from MAE where fine-tuning completely discards the decoder part of pre-training, there is no architectural difference between the pre-training and fine-tuning stages in our M³PT as they only differ in the prediction density, which potentially makes the transfer learning more convenient and effective. Extensive experiments verify the effectiveness of M³PT on three panoramic datasets. Notably, we improve the state-of-the-art baselines by averagely 29.2% in RMSE, 51.7% in MRE, 49.7% in MAE, and 37.5% in RMSElog on three benchmark datasets.
Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry. We avoid all such supervision and assumptions by explicitly leveraging the consistency between images of different object instances. As a result, our method can learn from large collections of unlabelled images depicting the same object category. Our main contributions are two ways for leveraging cross-instance consistency: (i) progressive conditioning, a training strategy to gradually specialize the model from category to instances in a curriculum learning fashion; and (ii) neighbor reconstruction, a loss enforcing consistency between instances having similar shape or texture. Also critical to the success of our method are: our structured autoencoding architecture decomposing an image into explicit shape, texture, pose, and background; an adapted formulation of differential rendering; and a new optimization scheme alternating between 3D and pose learning. We compare our approach, UNICORN, both on the diverse synthetic ShapeNet dataset - the classical benchmark for methods requiring multiple views as supervision - and on standard real-image benchmarks (Pascal3D+ Car, CUB) for which most methods require known templates and silhouette annotations. We also showcase applicability to more challenging real-world collections (CompCars, LSUN), where silhouettes are not available and images are not cropped around the object.
Forecasting complex vehicle and pedestrian multi-modal distributions requires powerful probabilistic approaches. Normalizing flows (NF) have recently emerged as an attractive tool to model such distributions. However, a key drawback is that independent samples drawn from a flow model often do not adequately capture all the modes in the underlying distribution. We propose Likelihood-Based Diverse Sampling (LDS), a method for improving the quality and the diversity of trajectory samples from a pre-trained flow model. Rather than producing individual samples, LDS produces a set of trajectories in one shot. Given a pre-trained forecasting flow model, we train LDS using gradients from the model, to optimize an objective function that rewards high likelihood for individual trajectories in the predicted set, together with high spatial separation among trajectories. LDS outperforms state-of-art post-hoc neural diverse forecasting methods for various pre-trained flow models as well as conditional variational autoencoder (CVAE) models. Crucially, it can also be used for transductive trajectory forecasting, where the diverse forecasts are trained on-the-fly on unlabeled test examples. LDS is easy to implement, and we show that it offers a simple plug-in improvement over baselines on two challenging benchmarks. Code is at: https://github.com/JasonMa2016/LDS
Few-shot class incremental learning (FSCIL) aims to incrementally add sets of novel classes to a well-trained base model in multiple training sessions with the restriction that only a few novel instances are available per class. While learning novel classes, FSCIL methods gradually forget base (old) class training and overfit to a few novel class samples. Existing approaches have addressed this problem by computing the class prototypes from the visual or semantic word vector domain. In this paper, we propose addressing this problem using a mixture of subspaces. Subspaces define the cluster structure of the visual domain and help to describe the visual and semantic domain considering the overall distribution of the data. Additionally, we propose to employ a variational autoencoder (VAE) to generate synthesized visual samples for augmenting pseudo-feature while learning novel classes incrementally. The combined effect of the mixture of subspaces and synthesized features reduces the forgetting and overfitting problem of FSCIL. Extensive experiments on three image classification datasets show that our proposed method achieves competitive results compared to state-of-the-art methods.
We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences in the presence of noise and occlusions remains a challenge. For this purpose, we propose an expressive generative model in the form of a conditional variational autoencoder, which learns a distribution of the change in pose at each step of a motion sequence. Furthermore, we introduce a flexible optimization-based approach that leverages HuMoR as a motion prior to robustly estimate plausible pose and shape from ambiguous observations. Through extensive evaluations, we demonstrate that our model generalizes to diverse motions and body shapes after training on a large motion capture dataset, and enables motion reconstruction from multiple input modalities including 3D keypoints and RGB(-D) videos.
Future segmentation prediction aims to predict the segmentation masks for unobserved future frames. Most existing works addressed it by directly predicting the intermediate features extracted by existing segmentation models. However, these segmentation features are learned to be local discriminative (with rich details) and are always of high resolution/dimension. Hence, the complicated spatio-temporal variations of these features are difficult to predict, which motivates us to learn a more predictive representation. In this work, we develop a novel framework called Predictive Feature Autoencoder. In the proposed framework, we construct an autoencoder which serves as a bridge between the segmentation features and the predictor. In the latent feature learned by the autoencoder, global structures are enhanced and local details are suppressed so that it is more predictive. In order to reduce the risk of vanishing the suppressed details during recurrent feature prediction, we further introduce a reconstruction constraint in the prediction module. Extensive experiments show the effectiveness of the proposed approach and our method outperforms state-of-the-arts by a considerable margin.
Boosting the Generalization Capability in Cross-Domain Few-Shot Learning via Noise-Enhanced Supervised Autoencoder
PDF ↗State of the art (SOTA) few-shot learning (FSL) methods suffer significant performance drop in the presence of domain differences between source and target datasets. The strong discrimination ability on the source dataset does not necessarily translate to high classification accuracy on the target dataset. In this work, we address this cross-domain few-shot learning (CDFSL) problem by boosting the generalization capability of the model. Specifically, we teach the model to capture broader variations of the feature distributions with a novel noise-enhanced supervised autoencoder (NSAE). NSAE trains the model by jointly reconstructing inputs and predicting the labels of inputs as well as their reconstructed pairs. Theoretical analysis based on intra-class correlation (ICC) shows that the feature embeddings learned from NSAE have stronger discrimination and generalization abilities in the target domain. We also take advantage of NSAE structure and propose a two-step fine-tuning procedure that achieves better adaption and improves classification performance in the target domain. Extensive experiments and ablation studies are conducted to demonstrate the effectiveness of the proposed method. Experimental results show that our proposed method consistently outperforms SOTA methods under various conditions.
Hierarchical Disentangled Representation Learning for Outdoor Illumination Estimation and Editing
PDF ↗Data-driven sky models have gained much attention in outdoor illumination prediction recently, showing superior performance against analytical models. However, naively compressing an outdoor panorama into a low-dimensional latent vector, as existing models have done, causes two major problems. One is the mutual interference between the HDR intensity of the sun and the complex textures of the surrounding sky, and the other is the lack of fine-grained control over independent lighting factors due to the entangled representation. To address these issues, we propose a hierarchical disentangled sky model (HDSky) for outdoor illumination prediction. With this model, any outdoor panorama can be hierarchically disentangled into several factors based on three well-designed autoencoders. The first autoencoder compresses each sunny panorama into a sky vector and a sun vector with some constraints. The second autoencoder and the third autoencoder further disentangle the sun intensity and the sky intensity from the sun vector and the sky vector with several customized loss functions respectively. Moreover, a unified framework is designed to predict all-weather sky information from a single outdoor image. Through extensive experiments, we demonstrate that the proposed model significantly improves the accuracy of outdoor illumination prediction. It also allows users to intuitively edit the predicted panorama (e.g., changing the position of the sun while preserving others), without sacrificing physical plausibility.
We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models. Contrary to recent approaches that model image layers with autoencoder networks, we represent them as explicit transformations of a small set of prototypical images. Our model has three main components: (i) a set of object prototypes in the form of learnable images with a transparency channel, which we refer to as sprites; (ii) differentiable parametric functions predicting occlusions and transformation parameters necessary to instantiate the sprites in a given image; (iii) a layered image formation model with occlusion for compositing these instances into complete images including background. By jointly learning the sprites and occlusion/transformation predictors to reconstruct images, our approach not only yields accurate layered image decompositions, but also identifies object categories and instance parameters. We first validate our approach by providing results on par with the state of the art on standard multi-object synthetic benchmarks (Tetrominoes, Multi-dSprites, CLEVR6). We then demonstrate the applicability of our model to real images in tasks that include clustering (SVHN, GTSRB), cosegmentation (Weizmann Horse) and object discovery from unfiltered social network images. To the best of our knowledge, our approach is the first layered image decomposition algorithm that learns an explicit and shared concept of object type, and is robust enough to be applied to real images.
We present Neural Articulated Radiance Field (NARF), a novel deformable 3D representation for articulated objects learned from images. While recent advances in 3D implicit representation have made it possible to learn models of complex objects, learning pose-controllable representations of articulated objects remains a challenge, as current methods require 3D shape supervision and are unable to render appearance. In formulating an implicit representation of 3D articulated objects, our method considers only the rigid transformation of the most relevant object part in solving for the radiance field at each 3D location. In this way, the proposed method represents pose-dependent changes without significantly increasing the computational complexity. NARF is fully differentiable and can be trained from images with pose annotations. Moreover, through the use of an autoencoder, it can learn appearance variations over multiple instances of an object class. Experiments show that the proposed method is efficient and can generalize well to novel poses. The code is available for research purposes at https://github.com/nogu-atsu/NARF
A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
PDF ↗In this paper, we propose HF2-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors. More importantly, conditioned on the reconstructed flows, we then employ a Conditional Variational Autoencoder (CVAE), which captures the high correlation between video frame and optical flow, to predict the next frame given several previous frames. By CVAE, the quality of flow reconstruction essentially influences that of frame prediction. Therefore, poorly reconstructed optical flows of abnormal events further deteriorate the quality of the final predicted future frame, making the anomalies more detectable. Experimental results demonstrate the effectiveness of the proposed method. Code is available at https://github.com/LiUzHiAn/hf2vad.
Learning an effective representation of 3D point clouds requires a good metric to measure the discrepancy between two 3D point sets, which is non-trivial due to their irregularity. Most of the previous works resort to using the Chamfer discrepancy or Earth Mover's distance, but those metrics are either ineffective in measuring the differences between point clouds or computationally expensive. In this paper, we conduct a systematic study with extensive experiments on distance metrics for 3D point clouds. From this study, we propose to use sliced Wasserstein distance and its variants for learning representations of 3D point clouds. In addition, we introduce a new algorithm to estimate sliced Wasserstein distance that guarantees that the estimated value is close enough to the true one. Experiments show that the sliced Wasserstein distance and its variants allow the neural network to learn a more efficient representation compared to the Chamfer discrepancy. We demonstrate the efficiency of the sliced Wasserstein metric and its variants on several tasks in 3D computer vision including training a point cloud autoencoder, generative modeling, transfer learning, and point cloud registration.
We present a domain- and user-preference-agnostic approach to detect highlightable excerpts from human-centric videos. Our method works on the graph-based representation of multiple observable human-centric modalities in the videos, such as poses and faces. We use an autoencoder network equipped with spatial-temporal graph convolutions to detect human activities and interactions based on these modalities. We train our network to map the activity- and interaction-based latent structural representations of the different modalities to per-frame highlight scores based on the representativeness of the frames. We use these scores to compute which frames to highlight and stitch contiguous frames to produce the excerpts. We train our network on the large-scale AVA-Kinetics action dataset and evaluate it on four benchmark video highlight datasets: DSH, TVSum, PHD^2, and SumMe. We observe a 4-12% improvement in the mean average precision of matching the human-annotated highlights over state-of-the-art methods in these datasets, without requiring any user-provided preferences or dataset-specific fine-tuning.
In open set recognition, a classifier has to detect unknown classes that are not known at training time. In order to recognize new categories, the classifier has to project the input samples of known classes in very compact and separated regions of the features space for discriminating samples of unknown classes. Recently proposed Capsule Networks have shown to outperform alternatives in many fields, particularly in image recognition, however they have not been fully applied yet to open-set recognition. In capsule networks, scalar neurons are replaced by capsule vectors or matrices, whose entries represent different properties of objects. In our proposal, during training, capsules features of the same known class are encouraged to match a pre-defined gaussian, one for each class. To this end, we use the variational autoencoder framework, with a set of gaussian priors as the approximation for the posterior distribution. In this way, we are able to control the compactness of the features of the same class around the center of the gaussians, thus controlling the ability of the classifier in detecting samples from unknown classes. We conducted several experiments and ablation of our model, obtaining state of the art results on different datasets in the open set recognition and unknown detection tasks.