The focal point of egocentric video understanding is modelling hand-object interactions. Standard models, e.g. CNNs or Vision Transformers, which receive RGB frames as input perform well. However, their performance improves further by employing additional input modalities that provide complementary cues, such as object detections, optical flow, audio, etc. The added complexity of the modality-specific modules, on the other hand, makes these models impractical for deployment. The goal of this work is to retain the performance of such a multimodal approach, while using only the RGB frames as input at inference time. We demonstrate that for egocentric action recognition on the Epic-Kitchens and the Something-Something datasets, students which are taught by multimodal teachers tend to be more accurate and better calibrated than architecturally equivalent models trained on ground truth labels in a unimodal or multimodal fashion. We further adopt a principled multimodal knowledge distillation framework, allowing us to deal with issues which occur when applying multimodal knowledge distillation in a naive manner. Lastly, we demonstrate the achieved reduction in computational complexity, and show that our approach maintains higher performance with the reduction of the number of input views. We release our code at https://github.com/gorjanradevski/multimodal-distillation.
We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins, and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain evaluation setups that more accurately simulate real-world situations where powerful generalization and adaptation under low-resource settings are desired. DUDE aims to set a new standard as a more practical, long-standing benchmark for the community, and we hope that it will lead to future extensions and contributions that address real-world challenges. Finally, our work illustrates the importance of finding more efficient ways to model language, images, and layout in DocAI.
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.
The focal point of egocentric video understanding is modelling hand-object interactions. Standard models -- CNNs, Vision Transformers, etc. -- which receive RGB frames as input perform well, however, their performance improves further by employing additional modalities such as object detections, optical flow, audio, etc. as input. The added complexity of the required modality-specific modules, on the other hand, makes these models impractical for deployment. The goal of this work is to retain the performance of such multimodal approaches, while using only the RGB images as input at inference time. Our approach is based on multimodal knowledge distillation, featuring a multimodal teacher (in the current experiments trained only using object detections, optical flow and RGB frames) and a unimodal student (using only RGB frames as input). We present preliminary results which demonstrate that the resulting model -- distilled from a multimodal teacher -- significantly outperforms the baseline RGB model (trained without knowledge distillation), as well as an omnivorous version of itself (trained on all modalities jointly), in both standard and compositional action recognition.
In recent years, we have seen significant steps taken in the development of self-driving cars. Multiple companies are starting to roll out impressive systems that work in a variety of settings. These systems can sometimes give the impression that full self-driving is just around the corner and that we would soon build cars without even a steering wheel. The increase in the level of autonomy and control given to an AI provides an opportunity for new modes of human-vehicle interaction. However, surveys have shown that giving more control to an AI in self-driving cars is accompanied by a degree of uneasiness by passengers. In an attempt to alleviate this issue, recent works have taken a natural language-oriented approach by allowing the passenger to give commands that refer to specific objects in the visual scene. Nevertheless, this is only half the task as the car should also understand the physical destination of the command, which is what we focus on in this paper. We propose an extension in which we annotate the 3D destination that the car needs to reach after executing the given command and evaluate multiple different baselines on predicting this destination location. Additionally, we introduce a model that outperforms the prior works adapted for this particular setting.
To protect sensitive training data, differentially private stochastic gradient descent (DP-SGD) has been adopted in deep learning to provide rigorously defined privacy. However, DP-SGD requires the injection of an amount of noise that scales with the number of gradient dimensions, resulting in large performance drops compared to non-private training. In this work, we propose random freeze which randomly freezes a progressively increasing subset of parameters and results in sparse gradient updates while maintaining or increasing accuracy. We theoretically prove the convergence of random freeze and find that random freeze exhibits a signal loss and perturbation moderation trade-off in DP-SGD. Applying random freeze across various DP-SGD frameworks, we maintain accuracy within the same number of iterations while achieving up to 70% representation sparsity, which demonstrates that the trade-off exists in a variety of DP-SGD methods. We further note that random freeze significantly improves accuracy, in particular for large networks. Additionally, axis-aligned sparsity induced by random freeze leads to various advantages for projected DP-SGD or federated learning in terms of computational cost, memory footprint and communication overhead.
Federated learning frameworks have been regarded as a promising approach to break the dilemma between demands on privacy and the promise of learning from large collections of distributed data. Many such frameworks only ask collaborators to share their local update of a common model, i.e. gradients with respect to locally stored data, instead of exposing their raw data to other collaborators. However, recent optimization-based gradient attacks show that raw data can often be accurately recovered from gradients. It has been shown that minimizing the Euclidean distance between true gradients and those calculated from estimated data is often effective in fully recovering private data. However, there is a fundamental lack of theoretical understanding of how and when gradients can lead to unique recovery of original data. Our research fills this gap by providing a closed-form recursive procedure to recover data from gradients in deep neural networks. We demonstrate that gradient attacks consist of recursively solving a sequence of systems of linear equations. Furthermore, our closed-form approach works as well as or even better than optimization-based approaches at a fraction of the computation, we name it Recursive Gradient Attack on Privacy (R-GAP). Additionally, we propose a rank analysis method, which can be used to estimate a network architecture's risk of a gradient attack. Experimental results demonstrate the validity of the closed-form attack and rank analysis, while demonstrating its superior computational properties and lack of susceptibility to local optima vis a vis optimization-based attacks. Source code is available for download from https://github.com/JunyiZhu-AI/R-GAP.
The task of visual grounding requires locating the most relevant region or object in an image, given a natural language query. So far, progress on this task was mostly measured on curated datasets, which are not always representative of human spoken language. In this work, we deviate from recent, popular task settings and consider the problem under an autonomous vehicle scenario. In particular, we consider a situation where passengers can give free-form natural language commands to a vehicle which can be associated with an object in the street scene. To stimulate research on this topic, we have organized the \emph{Commands for Autonomous Vehicles} (C4AV) challenge based on the recent \emph{Talk2Car} dataset (URL: https://www.aicrowd.com/challenges/eccv-2020-commands-4-autonomous-vehicles). This paper presents the results of the challenge. First, we compare the used benchmark against existing datasets for visual grounding. Second, we identify the aspects that render top-performing models successful, and relate them to existing state-of-the-art models for visual grounding, in addition to detecting potential failure cases by evaluating on carefully selected subsets. Finally, we discuss several possibilities for future work.