This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to 1 billion). Our main goal is to improve the performance for a given target architecture, like ResNet-50 or ResNext. We provide an extensive analysis of the success factors of our approach, which leads us to formulate some recommendations to produce high-accuracy models for image classification with semi-supervised learning. As a result, our approach brings important gains to standard architectures for image, video and fine-grained classification. For instance, by leveraging one billion unlabelled images, our learned vanilla ResNet-50 achieves 81.2% top-1 accuracy on the ImageNet benchmark.
Factor analysis or sometimes referred to as variable analysis has been extensively used in classification problems for identifying specific factors that are significant to particular classes. This type of analysis has been widely used in application such as customer segmentation, medical research, network traffic, image, and video classification. Today, factor analysis is prominently being used in fault diagnosis of machines to identify the significant factors and to study the root cause of a specific machine fault. The advantage of performing factor analysis in machine maintenance is to perform prescriptive analysis (helps answer what actions to take?) and preemptive analysis (helps answer how to eliminate the failure mode?). In this paper, a real case of an industrial rotating machine was considered where vibration and ambient temperature data was collected for monitoring the health of the machine. Gaussian mixture model-based clustering was used to cluster the data into significant groups, and spectrum analysis was used to diagnose each cluster to a specific state of the machine. The significant features that attribute to a particular mode of the machine were identified by using the random forest classification model. The significant features for specific modes of the machine were used to conclude that the clusters generated are distinct and have a unique set of significant features.
Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing on a highly specific video understanding task and thus leaving a significant gap towards describing the overall content of a video. We fill this gap by presenting a large-scale "Holistic Video Understanding Dataset"~(HVU). HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semantic aspects in the dynamic scene. HVU contains approx.~572k videos in total with 9 million annotations for training, validation, and test set spanning over 3142 labels. HVU encompasses semantic aspects defined on categories of scenes, objects, actions, events, attributes, and concepts which naturally captures the real-world scenarios. We demonstrate the generalization capability of HVU on three challenging tasks: 1.) Video classification, 2.) Video captioning and 3.) Video clustering tasks. In particular for video classification, we introduce a new spatio-temporal deep neural network architecture called "Holistic Appearance and Temporal Network"~(HATNet) that builds on fusing 2D and 3D architectures into one by combining intermediate representations of appearance and temporal cues. HATNet focuses on the multi-label and multi-task learning problem and is trained in an end-to-end manner. Via our experiments, we validate the idea that holistic representation learning is complementary, and can play a key role in enabling many real-world applications.
In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action recognition in particular. Thus far, the vision community has focused on spatio-temporal approaches using standard filters, rather we here propose dynamic filters that adaptively learn the video-specific internal motion representation by predicting the short-term future frames. We name this new motion representation, as dynamic motion representation (DMR) and is embedded inside of 3D convolutional network as a new layer, which captures the visual appearance and motion dynamics throughout entire video clip via end-to-end network learning. Simultaneously, we utilize these motion representation to enrich video classification. We have designed the frame prediction task as an auxiliary task to empower the classification problem. With these overall objectives, to this end, we introduce a novel unified spatio-temporal 3D-CNN architecture (DynamoNet) that jointly optimizes the video classification and learning motion representation by predicting future frames as a multi-task learning problem. We conduct experiments on challenging human action datasets: Kinetics 400, UCF101, HMDB51. The experiments using the proposed DynamoNet show promising results on all the datasets.
Higher-order data with high dimensionality arise in a diverse set of application areas such as computer vision, video analytics and medical imaging. Tensors provide a natural tool for representing these types of data. Although there has been a lot of work in the area of tensor decomposition and low-rank tensor approximation, extensions to supervised learning, feature extraction and classification are still limited. Moreover, most of the existing supervised tensor learning approaches are based on the orthogonal Tucker model. However, this model has some limitations for large tensors including high memory and computational costs. In this paper, we introduce a supervised learning approach for tensor classification based on the tensor-train model. In particular, we introduce a multi-branch tensor network structure for efficient implementation of tensor-train discriminant analysis (TTDA). The proposed approach takes advantage of the flexibility of the tensor train structure to implement various computationally efficient versions of TTDA. This approach is then evaluated on image and video classification tasks with respect to computation time, storage cost and classification accuracy and is compared to both vector and tensor based discriminant analysis methods.
We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tasks where spatio-temporal features are prevailing. In this paper we propose a novel self-supervised approach to learn spatio-temporal features for video representation. Inspired by the success of two-stream approaches in video classification, we propose to learn visual features by regressing both motion and appearance statistics along spatial and temporal dimensions, given only the input video data. Specifically, we extract statistical concepts (fast-motion region and the corresponding dominant direction, spatio-temporal color diversity, dominant color, etc.) from simple patterns in both spatial and temporal domains. Unlike prior puzzles that are even hard for humans to solve, the proposed approach is consistent with human inherent visual habits and therefore easy to answer. We conduct extensive experiments with C3D to validate the effectiveness of our proposed approach. The experiments show that our approach can significantly improve the performance of C3D when applied to video classification tasks. Code is available at https://github.com/laura-wang/video_repres_mas.
Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good computation/accuracy trade-offs with 3D group convolutional networks. This paper studies the effects of different design choices in 3D group convolutional networks for video classification. We empirically demonstrate that the amount of channel interactions plays an important role in the accuracy of 3D group convolutional networks. Our experiments suggest two main findings. First, it is a good practice to factorize 3D convolutions by separating channel interactions and spatiotemporal interactions as this leads to improved accuracy and lower computational cost. Second, 3D channel-separated convolutions provide a form of regularization, yielding lower training accuracy but higher test accuracy compared to 3D convolutions. These two empirical findings lead us to design an architecture -- Channel-Separated Convolutional Network (CSN) -- which is simple, efficient, yet accurate. On Sports1M, Kinetics, and Something-Something, our CSNs are comparable with or better than the state-of-the-art while being 2-3 times more efficient.
Two-stream architecture have shown strong performance in video classification task. The key idea is to learn spatio-temporal features by fusing convolutional networks spatially and temporally. However, there are some problems within such architecture. First, it relies on optical flow to model temporal information, which are often expensive to compute and store. Second, it has limited ability to capture details and local context information for video data. Third, it lacks explicit semantic guidance that greatly decrease the classification performance. In this paper, we proposed a new two-stream based deep framework for video classification to discover spatial and temporal information only from RGB frames, moreover, the multi-scale pyramid attention (MPA) layer and the semantic adversarial learning (SAL) module is introduced and integrated in our framework. The MPA enables the network capturing global and local feature to generate a comprehensive representation for video, and the SAL can make this representation gradually approximate to the real video semantics in an adversarial manner. Experimental results on two public benchmarks demonstrate our proposed methods achieves state-of-the-art results on standard video datasets.
Purpose: A profound education of novice surgeons is crucial to ensure that surgical interventions are effective and safe. One important aspect is the teaching of technical skills for minimally invasive or robot-assisted procedures. This includes the objective and preferably automatic assessment of surgical skill. Recent studies presented good results for automatic, objective skill evaluation by collecting and analyzing motion data such as trajectories of surgical instruments. However, obtaining the motion data generally requires additional equipment for instrument tracking or the availability of a robotic surgery system to capture kinematic data. In contrast, we investigate a method for automatic, objective skill assessment that requires video data only. This has the advantage that video can be collected effortlessly during minimally invasive and robot-assisted training scenarios. Methods: Our method builds on recent advances in deep learning-based video classification. Specifically, we propose to use an inflated 3D ConvNet to classify snippets, i.e., stacks of a few consecutive frames, extracted from surgical video. The network is extended into a Temporal Segment Network during training. Results: We evaluate the method on the publicly available JIGSAWS dataset, which consists of recordings of basic robot-assisted surgery tasks performed on a dry lab bench-top model. Our approach achieves high skill classification accuracies ranging from 95.1% to 100.0%. Conclusions: Our results demonstrate the feasibility of deep learning-based assessment of technical skill from surgical video. Notably, the 3D ConvNet is able to learn meaningful patterns directly from the data, alleviating the need for manual feature engineering. Further evaluation will require more annotated data for training and testing.
Recently,there has been a lot of interest in building compact models for video classification which have a small memory footprint (<1 GB). While these models are compact, they typically operate by repeated application of a small weight matrix to all the frames in a video. E.g. recurrent neural network based methods compute a hidden state for every frame of the video using a recurrent weight matrix. Similarly, cluster-and-aggregate based methods such as NetVLAD, have a learnable clustering matrix which is used to assign soft-clusters to every frame in the video. Since these models look at every frame in the video, the number of floating point operations (FLOPs) is still large even though the memory footprint is small. We focus on building compute-efficient video classification models which process fewer frames and hence have less number of FLOPs. Similar to memory efficient models, we use the idea of distillation albeit in a different setting. Specifically, in our case, a compute-heavy teacher which looks at all the frames in the video is used to train a compute-efficient student which looks at only a small fraction of frames in the video. This is in contrast to a typical memory efficient Teacher-Student setting, wherein both the teacher and the student look at all the frames in the video but the student has fewer parameters. Our work thus complements the research on memory efficient video classification. We do an extensive evaluation with three types of models for video classification,viz.(i) recurrent models (ii) cluster-and-aggregate models and (iii) memory-efficient cluster-and-aggregate models and show that in each of these cases, a see-it-all teacher can be used to train a compute efficient see-very-little student. We show that the proposed student network can reduce the inference time by 30% and the number of FLOPs by approximately 90% with a negligible drop in the performance.
Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve state-of-the-art performance in many challenging video datasets. Because of the high level of complexity of these methods, as the convolution operations are also extended to additional dimension in order to extract features from them as well, providing a visualization for the signals that the network interpret as informative, is a challenging task. An effective notion of understanding the network's inner-workings would be to isolate the spatio-temporal regions on the video that the network finds most informative. We propose a method called Saliency Tubes which demonstrate the foremost points and regions in both frame level and over time that are found to be the main focus points of the network. We demonstrate our findings on widely used datasets for third-person and egocentric action classification and enhance the set of methods and visualizations that improve 3D Convolutional Neural Networks (CNNs) intelligibility.
In this paper, we study deep diagonal circulant neural networks, that is deep neural networks in which weight matrices are the product of diagonal and circulant ones. Besides making a theoretical analysis of their expressivity, we introduced principled techniques for training these models: we devise an initialization scheme and proposed a smart use of non-linearity functions in order to train deep diagonal circulant networks. Furthermore, we show that these networks outperform recently introduced deep networks with other types of structured layers. We conduct a thorough experimental study to compare the performance of deep diagonal circulant networks with state of the art models based on structured matrices and with dense models. We show that our models achieve better accuracy than other structured approaches while required 2x fewer weights as the next best approach. Finally we train deep diagonal circulant networks to build a compact and accurate models on a real world video classification dataset with over 3.8 million training examples.
Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs). However, when considering visual Internet-of-Things applications, surveillance systems and semantic crawlers of large video repositories, the video capture and the CNN-based semantic analysis parts do not tend to be co-located. This necessitates the transport of compressed video over networks and incurs significant overhead in bandwidth and energy consumption, thereby significantly undermining the deployment potential of such systems. In this paper, we investigate the trade-off between the encoding bitrate and the achievable accuracy of CNN-based video classification models that directly ingest AVC/H.264 and HEVC encoded videos. Instead of retaining entire compressed video bitstreams and applying complex optical flow calculations prior to CNN processing, we only retain motion vector and select texture information at significantly-reduced bitrates and apply no additional processing prior to CNN ingestion. Based on three CNN architectures and two action recognition datasets, we achieve 11%-94% saving in bitrate with marginal effect on classification accuracy. A model-based selection between multiple CNNs increases these savings further, to the point where, if up to 7% loss of accuracy can be tolerated, video classification can take place with as little as 3 kbps for the transport of the required compressed video information to the system implementing the CNN models.
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps the image unchanged and only adds an adversarial framing on the border of the image. We show empirically that our method is able to successfully attack state-of-the-art methods on both image and video classification problems. Notably, the proposed method results in a universal attack which is very fast at test time. Source code can be found at https://github.com/zajaczajac/adv_framing .
This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex Action: a set of one-actions with a weak temporal pattern that serves a specific purpose. Related works use spatiotemporal 3D convolutions with fixed kernel size, too rigid to capture the varieties in temporal extents of complex actions, and too short for long-range temporal modeling. In contrast, we use multi-scale temporal convolutions, and we reduce the complexity of 3D convolutions. The outcome is Timeception convolution layers, which reasons about minute-long temporal patterns, a factor of 8 longer than best related works. As a result, Timeception achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions, and MultiTHUMOS. Further, we demonstrate that Timeception learns long-range temporal dependencies and tolerate temporal extents of complex actions.
Sign language recognition is a challenging and often underestimated problem comprising multi-modal articulators (handshape, orientation, movement, upper body and face) that integrate asynchronously on multiple streams. Learning powerful statistical models in such a scenario requires much data, particularly to apply recent advances of the field. However, labeled data is a scarce resource for sign language due to the enormous cost of transcribing these unwritten languages. We propose the first real-life large-scale sign language data set comprising over 25,000 annotated videos, which we thoroughly evaluate with state-of-the-art methods from sign and related action recognition. Unlike the current state-of-the-art, the data set allows to investigate the generalization to unseen individuals (signer-independent test) in a realistic setting with over 200 signers. Previous work mostly deals with limited vocabulary tasks, while here, we cover a large class count of 1000 signs in challenging and unconstrained real-life recording conditions. We further propose I3D, known from video classifications, as a powerful and suitable architecture for sign language recognition, outperforming the current state-of-the-art by a large margin. The data set is publicly available to the community.
Videos have become ubiquitous on the Internet. And video analysis can provide lots of information for detecting and recognizing objects as well as help people understand human actions and interactions with the real world. However, facing data as huge as TB level, effective methods should be applied. Recurrent neural network (RNN) architecture has wildly been used on many sequential learning problems such as Language Model, Time-Series Analysis, etc. In this paper, we propose some variations of RNN such as stacked bidirectional LSTM/GRU network with attention mechanism to categorize large-scale video data. We also explore different multimodal fusion methods. Our model combines both visual and audio information on both video and frame level and received great result. Ensemble methods are also applied. Because of its multimodal characteristics, we decide to call this method Deep Multimodal Learning(DML). Our DML-based model was trained on Google Cloud and our own server and was tested in a well-known video classification competition on Kaggle held by Google.
Few-shot or one-shot learning of classifiers requires a significant inductive bias towards the type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the target task. In this paper, we propose UMTRA, an algorithm that performs unsupervised, model-agnostic meta-learning for classification tasks. The meta-learning step of UMTRA is performed on a flat collection of unlabeled images. While we assume that these images can be grouped into a diverse set of classes and are relevant to the target task, no explicit information about the classes or any labels are needed. UMTRA uses random sampling and augmentation to create synthetic training tasks for meta-learning phase. Labels are only needed at the final target task learning step, and they can be as little as one sample per class. On the Omniglot and Mini-Imagenet few-shot learning benchmarks, UMTRA outperforms every tested approach based on unsupervised learning of representations, while alternating for the best performance with the recent CACTUs algorithm. Compared to supervised model-agnostic meta-learning approaches, UMTRA trades off some classification accuracy for a reduction in the required labels of several orders of magnitude.
Extracting temporal and representation features efficiently plays a pivotal role in understanding visual sequence information. To deal with this, we propose a new recurrent neural framework that can be stacked deep effectively. There are mainly two novel designs in our deep RNN framework: one is a new RNN module called Context Bridge Module (CBM) which splits the information flowing along the sequence (temporal direction) and along depth (spatial representation direction), making it easier to train when building deep by balancing these two directions; the other is the Overlap Coherence Training Scheme that reduces the training complexity for long visual sequential tasks on account of the limitation of computing resources. We provide empirical evidence to show that our deep RNN framework is easy to optimize and can gain accuracy from the increased depth on several visual sequence problems. On these tasks, we evaluate our deep RNN framework with 15 layers, 7* than conventional RNN networks, but it is still easy to train. Our deep framework achieves more than 11% relative improvements over shallow RNN models on Kinetics, UCF-101, and HMDB-51 for video classification. For auxiliary annotation, after replacing the shallow RNN part of Polygon-RNN with our 15-layer deep CBM, the performance improves by 14.7%. For video future prediction, our deep RNN improves the state-of-the-art shallow model's performance by 2.4% on PSNR and SSIM. The code and trained models are published accompanied by this paper: https://github.com/BoPang1996/Deep-RNN-Framework.
In classic video action recognition, labels may not contain enough information about the diverse video appearance and dynamics, thus, existing models that are trained under the standard supervised learning paradigm may extract less generalizable features. We evaluate these models under a cross-dataset experiment setting, as the above label bias problem in video analysis is even more prominent across different data sources. We find that using the optical flows as model inputs harms the generalization ability of most video recognition models. Based on these findings, we present a multi-task learning paradigm for video classification. Our key idea is to avoid label bias and improve the generalization ability by taking data as its own supervision or supervising constraints on the data. First, we take the optical flows and the RGB frames by taking them as auxiliary supervisions, and thus naming our model as Reversed Two-Stream Networks (Rev2Net). Further, we collaborate the auxiliary flow prediction task and the frame reconstruction task by introducing a new training objective to Rev2Net, named Decoding Discrepancy Penalty (DDP), which constraints the discrepancy of the multi-task features in a self-supervised manner. Rev2Net is shown to be effective on the classic action recognition task. It specifically shows a strong generalization ability in the cross-dataset experiments.