Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for 3D object detection given only a monocular image. While there exist different alternatives for tackling this problem, it is found that they are either equipped with heavy networks to fuse RGB and depth information or empirically ineffective to process millions of pseudo-LiDAR points. With in-depth examination, we realize that these limitations are rooted in inaccurate object localization. In this paper, we propose a novel and lightweight approach, dubbed {\em Progressive Coordinate Transforms} (PCT) to facilitate learning coordinate representations. Specifically, a localization boosting mechanism with confidence-aware loss is introduced to progressively refine the localization prediction. In addition, semantic image representation is also exploited to compensate for the usage of patch proposals. Despite being lightweight and simple, our strategy leads to superior improvements on the KITTI and Waymo Open Dataset monocular 3D detection benchmarks. At the same time, our proposed PCT shows great generalization to most coordinate-based 3D detection frameworks. The code is available at: https://github.com/amazon-research/progressive-coordinate-transforms .
Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful loss objectives as long as we can find a reasonable way to formulate positive and negative samples to contrast. However, existing approaches rely heavily on the short-range spatiotemporal salience to form clip-level contrastive signals, thus limit themselves from using global context. In this paper, we propose a new video-level contrastive learning method based on segments to formulate positive pairs. Our formulation is able to capture global context in a video, thus robust to temporal content change. We also incorporate a temporal order regularization term to enforce the inherent sequential structure of videos. Extensive experiments show that our video-level contrastive learning framework (VCLR) is able to outperform previous state-of-the-arts on five video datasets for downstream action classification, action localization and video retrieval. Code is available at https://github.com/amazon-research/video-contrastive-learning.
In this paper, we give a systematic description of the 1st Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AI Work Group. Firstly, the framework of full channel state information (F-CSI) feedback problem and its corresponding channel dataset are provided. Then the enhancing schemes for DL-based F-CSI feedback including i) channel data analysis and preprocessing, ii) neural network design and iii) quantization enhancement are elaborated. The final competition results composed of different enhancing schemes are presented. Based on the valuable experience of 1st WAIC, we also list some challenges and potential study areas for the design of AI-based wireless communication systems.
Though deep neural network models exhibit outstanding performance for various applications, their large model size and extensive floating-point operations render deployment on mobile computing platforms a major challenge, and, in particular, on Internet of Things devices. One appealing solution is model quantization that reduces the model size and uses integer operations commonly supported by microcontrollers . To this end, a 1-bit quantized DNN model or deep binary neural network maximizes the memory efficiency, where each parameter in a BNN model has only 1-bit. In this paper, we propose a reconfigurable BNN (RBNN) to further amplify the memory efficiency for resource-constrained IoT devices. Generally, the RBNN can be reconfigured on demand to achieve any one of M (M>1) distinct tasks with the same parameter set, thus only a single task determines the memory requirements. In other words, the memory utilization is improved by times M. Our extensive experiments corroborate that up to seven commonly used tasks can co-exist (the value of M can be larger). These tasks with a varying number of classes have no or negligible accuracy drop-off on three binarized popular DNN architectures including VGG, ResNet, and ReActNet. The tasks span across different domains, e.g., computer vision and audio domains validated herein, with the prerequisite that the model architecture can serve those cross-domain tasks. To protect the intellectual property of an RBNN model, the reconfiguration can be controlled by both a user key and a device-unique root key generated by the intrinsic hardware fingerprint. By doing so, an RBNN model can only be used per paid user per authorized device, thus benefiting both the user and the model provider.
Convolutional neural networks have allowed remarkable advances in single image super-resolution (SISR) over the last decade. Among recent advances in SISR, attention mechanisms are crucial for high performance SR models. However, few works really discuss why attention works and how it works. In this work, we attempt to quantify and visualize the static attention mechanisms and show that not all attention modules are equally beneficial. We then propose attention in attention network (A$^2$N) for highly accurate image SR. Specifically, our A$^2$N consists of a non-attention branch and a coupling attention branch. Attention dropout module is proposed to generate dynamic attention weights for these two branches based on input features that can suppress unwanted attention adjustments. This allows attention modules to specialize to beneficial examples without otherwise penalties and thus greatly improve the capacity of the attention network with little parameter overhead. Experiments have demonstrated that our model could achieve superior trade-off performances comparing with state-of-the-art lightweight networks. Experiments on local attribution maps also prove attention in attention (A$^2$) structure can extract features from a wider range.
Federated learning (FL) and split learning (SL) are state-of-the-art distributed machine learning techniques to enable machine learning training without accessing raw data on clients or end devices. However, their \emph{comparative training performance} under real-world resource-restricted Internet of Things (IoT) device settings, e.g., Raspberry Pi, remains barely studied, which, to our knowledge, have not yet been evaluated and compared, rendering inconvenient reference for practitioners. This work firstly provides empirical comparisons of FL and SL in real-world IoT settings regarding (i) learning performance with heterogeneous data distributions and (ii) on-device execution overhead. Our analyses in this work demonstrate that the learning performance of SL is better than FL under an imbalanced data distribution but worse than FL under an extreme non-IID data distribution. Recently, FL and SL are combined to form splitfed learning (SFL) to leverage each of their benefits (e.g., parallel training of FL and lightweight on-device computation requirement of SL). This work then considers FL, SL, and SFL, and mount them on Raspberry Pi devices to evaluate their performance, including training time, communication overhead, power consumption, and memory usage. Besides evaluations, we apply two optimizations. Firstly, we generalize SFL by carefully examining the possibility of a hybrid type of model training at the server-side. The generalized SFL merges sequential (dependent) and parallel (independent) processes of model training and is thus beneficial for a system with large-scaled IoT devices, specifically at the server-side operations. Secondly, we propose pragmatic techniques to substantially reduce the communication overhead by up to four times for the SL and (generalized) SFL.
Normalization techniques are crucial in stabilizing and accelerating the training of deep neural networks. However, they are mainly designed for the independent and identically distributed (IID) data, not satisfying many real-world out-of-distribution (OOD) situations. Unlike most previous works, this paper presents two normalization methods, SelfNorm and CrossNorm, to promote OOD generalization. SelfNorm uses attention to recalibrate statistics (channel-wise mean and variance), while CrossNorm exchanges the statistics between feature maps. SelfNorm and CrossNorm can complement each other in OOD generalization, though exploring different directions in statistics usage. Extensive experiments on different domains (vision and language), tasks (classification and segmentation), and settings (supervised and semi-supervised) show their effectiveness.
Video action recognition is one of the representative tasks for video understanding. Over the last decade, we have witnessed great advancements in video action recognition thanks to the emergence of deep learning. But we also encountered new challenges, including modeling long-range temporal information in videos, high computation costs, and incomparable results due to datasets and evaluation protocol variances. In this paper, we provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition. We first introduce the 17 video action recognition datasets that influenced the design of models. Then we present video action recognition models in chronological order: starting with early attempts at adapting deep learning, then to the two-stream networks, followed by the adoption of 3D convolutional kernels, and finally to the recent compute-efficient models. In addition, we benchmark popular methods on several representative datasets and release code for reproducibility. In the end, we discuss open problems and shed light on opportunities for video action recognition to facilitate new research ideas.
This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020. Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details. The task in this challenge is to upscale videos with an extreme factor of 16, which results in more serious degradations that also affect the structural integrity of the videos. A single pixel in the low-resolution (LR) domain corresponds to 256 pixels in the high-resolution (HR) domain. Due to this massive information loss, it is hard to accurately restore the missing information. Track 1 is set up to gauge the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM. Perceptually higher quality can be achieved in trade-off for fidelity by generating plausible high-frequency content. Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study. In contrast to single image super-resolution (SISR), VSR can benefit from additional information in the temporal domain. However, this also imposes an additional requirement, as the generated frames need to be consistent along time.
This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected stage of the machine learning pipeline, the attack surfaces are recognized to be wide and then formalized into six categorizations: code poisoning, outsourcing, pretrained, data collection, collaborative learning and post-deployment. Accordingly, attacks under each categorization are combed. The countermeasures are categorized into four general classes: blind backdoor removal, offline backdoor inspection, online backdoor inspection, and post backdoor removal. Accordingly, we review countermeasures, and compare and analyze their advantages and disadvantages. We have also reviewed the flip side of backdoor attacks, which are explored for i) protecting intellectual property of deep learning models, ii) acting as a honeypot to catch adversarial example attacks, and iii) verifying data deletion requested by the data contributor.Overall, the research on defense is far behind the attack, and there is no single defense that can prevent all types of backdoor attacks. In some cases, an attacker can intelligently bypass existing defenses with an adaptive attack. Drawing the insights from the systematic review, we also present key areas for future research on the backdoor, such as empirical security evaluations from physical trigger attacks, and in particular, more efficient and practical countermeasures are solicited.