Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
Hong Kong University of Science and Technology（香港科技大学）；Singapore University of Technology and Design（新加坡科技设计大学）；The University of Tokyo（东京大学）；Deakin University（迪肯大学）
Deep learning techniques for point cloud data have demonstrated great potentials in solving classical problems in 3D computer vision such as 3D object classification and segmentation. Several recent 3D object classification methods have reported state-of-the-art performance on CAD model datasets such as ModelNet40 with high accuracy (~92%). Despite such impressive results, in this paper, we argue that object classification is still a challenging task when objects are framed with real-world settings. To prove this, we introduce ScanObjectNN, a new real-world point cloud object dataset based on scanned indoor scene data. From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial due to occlusions. We identify three key open problems for point cloud object classification, and propose new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background. Our dataset and code are publicly available in our project page https://hkust-vgd.github.io/scanobjectnn/.
Xidian University（西安电子科技大学）；Northwestern Polytechnical University（西北工业大学）；China University of Mining Technology-Beijing（中国矿业大学（北京））；Zhejiang Lab（之江实验室）
Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are devised to address the data imbalance problem by biasing the training process towards less frequent classes. However, they usually evaluate the performance on a balanced testing set or multiple independent testing sets having distinct distributions with the training data. Considering the testing data may have arbitrary distributions, existing evaluation strategies are unable to reflect the actual classification perform…
This paper describes our solution for the video recognition task of ActivityNet Kinetics challenge that ranked the 1st place. Most of existing state-of-the-art video recognition approaches are in favor of an end-to-end pipeline. One exception is the framework of DevNet. The merit of DevNet is that they first use the video data to learn a network (i.e. fine-tuning or training from scratch). Instead of directly using the end-to-end classification scores (e.g. softmax scores), they extract the features from the learned network and then fed them into the off-the-shelf machine learning models to co…
Hefei University of Technology（合肥工业大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；Zhengzhou University（郑州大学）；Singapore Management University（新加坡管理大学）
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts have been aimed at designing more and more complex classifiers that measure similarities between query and support images, but left the importance of feature embeddings seldom explored. We show that the reliance on sophisticated classifiers is not necessary, and a simple classifier applied directly to improved feature embeddings can instead outperform most of the leading methods in the literature. To this end, we pre…
Facebook AI Research（Facebook人工智能研究院）；Univ Rennes（雷恩大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；IRISA（IRISA研究所）
In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather than its weights. The principle of our approach is that it minimizes the loss reconstruction error for in-domain inputs. Our method only requires a set of unlabelled data at quantization time and allows for efficient inference on CPU by using byte-aligned codebooks to store the compressed weights. We validate our approach by quantizing a high performing Res…
WTA (Winner Take All) hashing has been successfully applied in many large scale vision applications. This hashing scheme was tailored to take advantage of the comparative reasoning (or order based information), which showed significant accuracy improvements. In this paper, we identify a subtle issue with WTA, which grows with the sparsity of the datasets. This issue limits the discriminative power of WTA. We then propose a solution for this problem based on the idea of Densification which provably fixes the issue. Our experiments show that Densified WTA Hashing outperforms Vanilla WTA both in …
The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. However, increased detail usually comes at the expense of high storage, as well as computational costs in terms of processing and visualization operations. Mesh and Point Cloud simplification methods aim to reduce the complexity of 3D models while retaining visual quality and relevant salient features. Traditional simplification techniques usually rely on solving a time-consuming optimization problem, hence they are impractical for large-scale datasets. In an attempt to…
Cornell University（康奈尔大学）；Ohio State University（俄亥俄州立大学）；Facebook AI Research（脸书人工智能研究院）
Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization …
The prevalent perspectives of scene text recognition are from sequence to sequence (seq2seq) and segmentation. Nevertheless, the former is composed of many components which makes implementation and deployment complicated, while the latter requires character level annotations that is expensive. In this paper, we revisit classification perspective that models scene text recognition as an image classification problem. Classification perspective has a simple pipeline and only needs word level annotations. We revive classification perspective by devising a scene text recognition model named as CSTR…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM T.J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Recent region-based object detectors are usually built with separate classification and localization branches on top of shared feature extraction networks. In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization. We conjecture that: (1) Shared feature representation is not optimal due to the mismatched goals of feature learning for classification and localization; (2) multi-task learning helps, yet optimization of the multi-task loss may result in sub-optimal for individual tasks; (3) la…
Revisiting Point Cloud Completion: Are We Ready For The Real-World?
University of Antwerp（安特卫普大学）；Indian Institute of Technology Delhi（印度理工学院德里分校）；Birla Institute of Technology and Science Pilani（贝拉理工科学学院皮拉尼分校）；Geographic Information Management（地理信息管理机构）
Processing point cloud data is an important component of many real-world systems. As such, a wide variety of point-based approaches have been proposed, reporting steady benchmark improvements over time. We study the key ingredients of this progress and uncover two critical results. First, we find that auxiliary factors like different evaluation schemes, data augmentation strategies, and loss functions, which are independent of the model architecture, make a large difference in performance. The differences are large enough that they obscure the effect of architecture. When these factors are con…
In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to update this knowledge, then they need to fine-tune the model parameters. Moreover, users cannot verify the validity of inference results or evaluate the contribution of knowledge to the results. In this paper, we investigate a system that stores knowledge for image classification, such as image feature maps, labels, and original images, not in model parameters but in external high-capacity storage. Our system refers to …
Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone. This requires a remarkable degree of invariance to pose, articulation and background. A solution is to use pose-normalized representations: first localize semantic parts in each image, and then describe images by characterizing the appearance of each part. While such representations are out of favor for fully supervised classification, we show that they are extremely effective for few-shot fine-grained classification. With a mini…
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Tencent AI Lab（腾讯人工智能实验室）
The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison between query and support examples. However, the importance of feature embedding, i.e., exploring the relationship among training samples, is neglected. In this work, we present a simple yet powerful baseline for few-shot classification by emphasizing the importance of feature embedding. Specifically, we revisit the classical triplet network from deep metric le…
Georgia Tech（佐治亚理工学院）；University of Kentucky（肯塔基大学）
Image geolocalization, inferring the geographic location of an image, is a challenging computer vision problem with many potential applications. The recent state-of-the-art approach to this problem is a deep image classification approach in which the world is spatially divided into cells and a deep network is trained to predict the correct cell for a given image. We propose to combine this approach with the original Im2GPS approach in which a query image is matched against a database of geotagged images and the location is inferred from the retrieved set. We estimate the geographic location of…
Istituto Italiano di Tecnologia（意大利技术研究院）；Università degli Studi di Genova（热那亚大学）；Università di Verona（维罗纳大学）
By thoroughly revisiting the classic human action recognition paradigm, this paper aims at proposing a new approach for the design of effective action classification systems. Taking as testbed publicly available three-dimensional (MoCap) action/activity datasets, we analyzed and validated different training/testing strategies. In particular, considering that each human action in the datasets is performed several times by different subjects, we were able to precisely quantify the effect of inter- and intra-subject variability, so as to figure out the impact of several learning approaches in ter…
Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large. The impact of particular forms of normalization, however, has so far been investigated in limited domain-specific classification tasks and not in a general fashion. Motivated by the lack of such a comprehensive study, in this paper we investigate the performance of lp-constrained softmax loss classifiers across different norm orders, magnitudes, and data dimensions in both proof-of-concept classification problems and real-world popular image classificatio…
Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent and balanced optimization of the tasks. In this paper, we find that shifting the bounding boxes can change the division of positive and negative samples in classification, meaning classification depends on regression. Moreover, we summarize three important conclusions about fine-tuning loss weights, considering different datasets, optimizers and regression …
Harbin Institute of Technology（哈尔滨工业大学）；Australian National University（澳大利亚国立大学）
Monocular depth estimation is a fundamental task in computer vision and has drawn increasing attention. Recently, some methods reformulate it as a classification-regression task to boost the model performance, where continuous depth is estimated via a linear combination of predicted probability distributions and discrete bins. In this paper, we present a novel framework called BinsFormer, tailored for the classification-regression-based depth estimation. It mainly focuses on two crucial components in the specific task: 1) proper generation of adaptive bins and 2) sufficient interaction between…
SenseTime X-Lab（商汤科技X实验室）；The Chinese University of Hong Kong（香港中文大学）
The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~\cite{girshick2015fast}, has been leading the fashion of the object detection community in the past five years. This paper provides the observation that the spatial misalignment between the two object functions in the sibling head can considerably hurt the training process, but this misalignment can be resolved by a very simple operator called task-aware spatial disentanglement (TSD). Considering the classification and regression, TSD decouples them from the spatial dimension by generating …
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
The University of Sydney（悉尼大学）；Baidu Inc.（百度公司）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained models in large scales of the model architecture and amount of data. In this study, we focus on transferring knowledge for video classification tasks. Conventional methods randomly initialize the linear classifier head for vision classification, but they leave the usage of the text encoder for downstream visual recognition tasks undiscovered. In this paper, w…
Technische Universität Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence GmbH (DFKI)（德国人工智能研究中心）
It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. This assumption has led to a growing body of work aiming to align deep models' decision-making processes with the fundamental properties of human vision. The reliance on shape features is primarily expected to improve the robustness of these models under covariate shift. In this paper, we revisit the significance of shape-biases for the classification of skin lesion images. Our analysis shows that different skin lesion datasets exhibit varying biases towards individual image …
Due to the high human cost of annotation, it is non-trivial to curate a large-scale medical dataset that is fully labeled for all classes of interest. Instead, it would be convenient to collect multiple small partially labeled datasets from different matching sources, where the medical images may have only been annotated for a subset of classes of interest. This paper offers an empirical understanding of an under-explored problem, namely partially supervised multi-label classification (PSMLC), where a multi-label classifier is trained with only partially labeled medical images. In contrast to …
DeepGlint（深瞐科技）；China University of Mining and Technology（中国矿业大学）
Great progress has been made in point cloud classification with learning-based methods. However, complex scene and sensor inaccuracy in real-world application make point cloud data suffer from corruptions, such as occlusion, noise and outliers. In this work, we propose Point-Voxel based Adaptive (PV-Ada) feature abstraction for robust point cloud classification under various corruptions. Specifically, the proposed framework iteratively voxelize the point cloud and extract point-voxel feature with shared local encoding and Transformer. Then, adaptive max-pooling is proposed to robustly aggregat…
Although 3D point cloud classification neural network models have been widely used, the in-depth interpretation of the activation of the neurons and layers is still a challenge. We propose a novel approach, named Relevance Flow, to interpret the hidden semantics of 3D point cloud classification neural networks. It delivers the class Relevance to the activated neurons in the intermediate layers in a back-propagation manner, and associates the activation of neurons with the input points to visualize the hidden semantics of each layer. Specially, we reveal that the 3D point cloud classification n…
3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness a…
Shanghai Jiao Tong University（上海交通大学）；Foshan Woman and Children’s Hospital（佛山市妇幼保健院）
Understanding the implication of point cloud is still challenging to achieve the goal of classification or segmentation due to the irregular and sparse structure of point cloud. As we have known, PointNet architecture as a ground-breaking work for point cloud which can learn efficiently shape features directly on unordered 3D point cloud and have achieved favorable performance. However, this model fail to consider the fine-grained semantic information of local structure for point cloud. Afterwards, many valuable works are proposed to enhance the performance of PointNet by means of semantic fea…
Mines ParisTech（巴黎高等矿业学院）；PSL Research University（巴黎文理研究大学）；Centre for Robotics（机器人中心）
In this article we describe a new convolutional neural network (CNN) to classify 3D point clouds of urban or indoor scenes. Solutions are given to the problems encountered working on scene point clouds, and a network is described that allows for point classification using only the position of points in a multi-scale neighborhood. On the reduced-8 Semantic3D benchmark [Hackel et al., 2017], this network, ranked second, beats the state of the art of point classification methods (those not using a regularization step).
Australian National University（澳大利亚国立大学）；Data61-CSIRO（Data61-联邦科学与工业研究组织）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification. To this end, a novel triplet loss is developed that takes advantage of unlab…
School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）
In this paper, we propose a point cloud classification method based on graph neural network and manifold learning. Different from the conventional point cloud analysis methods, this paper uses manifold learning algorithms to embed point cloud features for better considering the geometric continuity on the surface. Then, the nature of point cloud can be acquired in low dimensional space, and after being concatenated with features in the original three-dimensional (3D)space, both the capability of feature representation and the classification network performance can be improved. We pro-pose two …
While adversarial training is generally used as a defense mechanism, recent works show that it can also act as a regularizer. By co-training a neural network on clean and adversarial inputs, it is possible to improve classification accuracy on the clean, non-adversarial inputs. We demonstrate that, contrary to previous findings, it is not necessary to separate batch statistics when co-training on clean and adversarial inputs, and that it is sufficient to use adapters with few domain-specific parameters for each type of input. We establish that using the classification token of a Vision Transfo…
Massachusetts Institute of Technology（麻省理工学院）；Stevens Institute of Technology（史蒂文斯理工学院）
We propose a methodology for robust, real-time place recognition using an imaging lidar, which yields image-quality high-resolution 3D point clouds. Utilizing the intensity readings of an imaging lidar, we project the point cloud and obtain an intensity image. ORB feature descriptors are extracted from the image and encoded into a bag-of-words vector. The vector, used to identify the point cloud, is inserted into a database that is maintained by DBoW for fast place recognition queries. The returned candidate is further validated by matching visual feature descriptors. To reject matching outlie…
We focus on better understanding the critical factors of augmentation-invariant representation learning. We revisit MoCo v2 and BYOL and try to prove the authenticity of the following assumption: different frameworks bring about representations of different characteristics even with the same pretext task. We establish the first benchmark for fair comparisons between MoCo v2 and BYOL, and observe: (i) sophisticated model configurations enable better adaptation to pre-training dataset; (ii) mismatched optimization strategies of pre-training and fine-tuning hinder model from achieving competitive…
Spinning LiDAR data are prevalent for 3D vision tasks. Since LiDAR data is presented in the form of point clouds, expensive 3D operations are usually required. This paper revisits spinning LiDAR scan formation and presents a cylindrical range image representation with a ray-wise projection/unprojection model. It is built upon raw scans and supports lossless conversion from 2D to 3D, allowing fast 2D operations, including 2D index-based neighbor search and downsampling. We then propose, to the best of our knowledge, the first multi-scale registration and dense signed distance function (SDF) rec…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Microsoft Research（微软研究院）
PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such as PointMLP and Point Transformer, we find that a large portion of the performance gain is due to improved training strategies, i.e. data augmentation and optimization techniques, and increased model sizes rather than architectural innovations. Thus, the full potential of PointNet++ has yet to be explored. In this work, we revisit the classical PointNet++ through a systematic study of model training and scaling stra…
The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning
School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou, China（先进技术学院 西安交通大学利物浦大学 苏州，中国）；Data Science Research Center Duke Kunshan University Suzhou, China（数据科学研究中心 狄尔克森大学 苏州，中国）
