The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN-based methods can achieve good performance but are computationally intensive. In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency and high performance. The key idea of TSM is to shift part of the channels along the temporal dimension, thus facilitate information exchanged among neighboring frames. It can be inserted into 2D CNNs to achieve temporal modeling at zero computation and zero parameters. TSM offers several unique advantages. Firstly, TSM has high performance; it ranks the first on the Something-Something leaderboard upon submission. Secondly, TSM has high efficiency; it achieves a high frame rate of 74fps and 29fps for online video recognition on Jetson Nano and Galaxy Note8. Thirdly, TSM has higher scalability compared to 3D networks, enabling large-scale Kinetics training on 1,536 GPUs in 15 minutes. Lastly, TSM enables action concepts learning, which 2D networks cannot model; we visualize the category attention map and find that spatial-temporal action detector emerges during the training of classification tasks. The code is publicly available at https://github.com/mit-han-lab/temporal-shift-module.
Many current deep learning approaches make extensive use of backbone networks pre-trained on large datasets like ImageNet, which are then fine-tuned to perform a certain task. In remote sensing, the lack of comparable large annotated datasets and the wide diversity of sensing platforms impedes similar developments. In order to contribute towards the availability of pre-trained backbone networks in remote sensing, we devise a self-supervised approach for pre-training deep neural networks. By exploiting the correspondence between geo-tagged audio recordings and remote sensing imagery, this is done in a completely label-free manner, eliminating the need for laborious manual annotation. For this purpose, we introduce the SoundingEarth dataset, which consists of co-located aerial imagery and audio samples all around the world. Using this dataset, we then pre-train ResNet models to map samples from both modalities into a common embedding space, which encourages the models to understand key properties of a scene that influence both visual and auditory appearance. To validate the usefulness of the proposed approach, we evaluate the transfer learning performance of pre-trained weights obtained against weights obtained through other means. By fine-tuning the models on a number of commonly used remote sensing datasets, we show that our approach outperforms existing pre-training strategies for remote sensing imagery. The dataset, code and pre-trained model weights will be available at https://github.com/khdlr/SoundingEarth.
Motivated by the recent discovery that the interpretation maps of CNNs could easily be manipulated by adversarial attacks against network interpretability, we study the problem of interpretation robustness from a new perspective of \Renyi differential privacy (RDP). The advantages of our Renyi-Robust-Smooth (RDP-based interpretation method) are three-folds. First, it can offer provable and certifiable top-$k$ robustness. That is, the top-$k$ important attributions of the interpretation map are provably robust under any input perturbation with bounded $\ell_d$-norm (for any $d\geq 1$, including $d = \infty$). Second, our proposed method offers $\sim10\%$ better experimental robustness than existing approaches in terms of the top-$k$ attributions. Remarkably, the accuracy of Renyi-Robust-Smooth also outperforms existing approaches. Third, our method can provide a smooth tradeoff between robustness and computational efficiency. Experimentally, its top-$k$ attributions are {\em twice} more robust than existing approaches when the computational resources are highly constrained.
Prosody plays an important role in characterizing the style of a speaker or an emotion, but most non-parallel voice or emotion style transfer algorithms do not convert any prosody information. Two major components of prosody are pitch and rhythm. Disentangling the prosody information, particularly the rhythm component, from the speech is challenging because it involves breaking the synchrony between the input speech and the disentangled speech representation. As a result, most existing prosody style transfer algorithms would need to rely on some form of text transcriptions to identify the content information, which confines their application to high-resource languages only. Recently, SpeechSplit has made sizeable progress towards unsupervised prosody style transfer, but it is unable to extract high-level global prosody style in an unsupervised manner. In this paper, we propose AutoPST, which can disentangle global prosody style from speech without relying on any text transcriptions. AutoPST is an Autoencoder-based Prosody Style Transfer framework with a thorough rhythm removal module guided by the self-expressive representation learning. Experiments on different style transfer tasks show that AutoPST can effectively convert prosody that correctly reflects the styles of the target domains.
Cross-modal correlation provides an inherent supervision for video unsupervised representation learning. Existing methods focus on distinguishing different video clips by visual and audio representations. We human visual perception could attend to regions where sounds are made, and our auditory perception could also ground their frequencies of sounding objects, which we call bidirectional local correspondence. Such supervision is intuitive but not well explored in the contrastive learning framework. This paper introduces a pretext task, Cross-Modal Attention Consistency (CMAC), for exploring the bidirectional local correspondence property. The CMAC approach aims to align the regional attention generated purely from the visual signal with the target attention generated under the guidance of acoustic signal, and do a similar alignment for frequency grounding on the acoustic attention. Accompanied by a remoulded cross-modal contrastive loss where we consider additional within-modal interactions, the CMAC approach works effectively for enforcing the bidirectional alignment. Extensive experiments on six downstream benchmarks demonstrate that CMAC can improve the state-of-the-art performance on both visual and audio modalities.
It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to compounding errors or suboptimal solutions. In this paper, we propose Option-GAIL, a novel method to learn skills at long horizon. The key idea of Option-GAIL is modeling the task hierarchy by options and train the policy via generative adversarial optimization. In particular, we propose an Expectation-Maximization(EM)-style algorithm: an E-step that samples the options of expert conditioned on the current learned policy, and an M-step that updates the low- and high-level policies of agent simultaneously to minimize the newly proposed option-occupancy measurement between the expert and the agent. We theoretically prove the convergence of the proposed algorithm. Experiments show that Option-GAIL outperforms other counterparts consistently across a variety of tasks.
We present Temporal and Object Quantification Networks (TOQ-Nets), a new class of neuro-symbolic networks with a structural bias that enables them to learn to recognize complex relational-temporal events. This is done by including reasoning layers that implement finite-domain quantification over objects and time. The structure allows them to generalize directly to input instances with varying numbers of objects in temporal sequences of varying lengths. We evaluate TOQ-Nets on input domains that require recognizing event-types in terms of complex temporal relational patterns. We demonstrate that TOQ-Nets can generalize from small amounts of data to scenarios containing more objects than were present during training and to temporal warpings of input sequences.
The problem of grounding VQA tasks has seen an increased attention in the research community recently, with most attempts usually focusing on solving this task by using pretrained object detectors. However, pre-trained object detectors require bounding box annotations for detecting relevant objects in the vocabulary, which may not always be feasible for real-life large-scale applications. In this paper, we focus on a more relaxed setting: the grounding of relevant visual entities in a weakly supervised manner by training on the VQA task alone. To address this problem, we propose a visual capsule module with a query-based selection mechanism of capsule features, that allows the model to focus on relevant regions based on the textual cues about visual information in the question. We show that integrating the proposed capsule module in existing VQA systems significantly improves their performance on the weakly supervised grounding task. Overall, we demonstrate the effectiveness of our approach on two state-of-the-art VQA systems, stacked NMN and MAC, on the CLEVR-Answers benchmark, our new evaluation set based on CLEVR scenes with ground truth bounding boxes for objects that are relevant for the correct answer, as well as on GQA, a real world VQA dataset with compositional questions. We show that the systems with the proposed capsule module consistently outperform the respective baseline systems in terms of answer grounding, while achieving comparable performance on VQA task.
Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in photographic datasets. Yet to build truly intelligent agents, we must construct representation learning algorithms that can learn not only from datasets but also learn from environments. An agent in a natural environment will not typically be fed curated data. Instead, it must explore its environment to acquire the data it will learn from. We propose a framework, curious representation learning (CRL), which jointly learns a reinforcement learning policy and a visual representation model. The policy is trained to maximize the error of the representation learner, and in doing so is incentivized to explore its environment. At the same time, the learned representation becomes stronger and stronger as the policy feeds it ever harder data to learn from. Our learned representations enable promising transfer to downstream navigation tasks, performing better than or comparably to ImageNet pretraining without using any supervision at all. In addition, despite being trained in simulation, our learned representations can obtain interpretable results on real images.