当NLP模型从一个时间段进行文本数据培训并从另一个时间进行测试或部署或部署时，产生的时间未对准可能会降低结束任务性能。在这项工作中，我们在不同域名（社交媒体，科学论文，新闻和评论和评论）和时间（跨越五年或更长时间）的时间内建立了八个不同的任务套件，以量化时间未对准的影响。我们的研究专注于普遍存在的环境，其中佩戴的模型可选择通过持续的域特异性预测来改编，然后是特定于任务的FineTuning。我们在多个域中建立了一套任务，以研究现代NLP系统中的时间错位。我们发现对任务性能的时间不对准而不是先前报告的更强烈影响。我们还发现，虽然通过续预先训练的时间适应可以帮助，但与目标时间段中的数据上的任务特定的FineTuning相比，这些收益很小。我们的研究结果激励了提高NLP模型的时间稳健性的持续研究。

Complex and contact-rich robotic manipulation tasks, particularly those that involve multi-fingered hands and underactuated object manipulation, present a significant challenge to any control method. Methods based on reinforcement learning offer an appealing choice for such settings, as they can enable robots to learn to delicately balance contact forces and dexterously reposition objects without strong modeling assumptions. However, running reinforcement learning on real-world dexterous manipulation systems often requires significant manual engineering. This negates the benefits of autonomous data collection and ease of use that reinforcement learning should in principle provide. In this paper, we describe a system for vision-based dexterous manipulation that provides a "programming-free" approach for users to define new tasks and enable robots with complex multi-fingered hands to learn to perform them through interaction. The core principle underlying our system is that, in a vision-based setting, users should be able to provide high-level intermediate supervision that circumvents challenges in teleoperation or kinesthetic teaching which allow a robot to not only learn a task efficiently but also to autonomously practice. Our system includes a framework for users to define a final task and intermediate sub-tasks with image examples, a reinforcement learning procedure that learns the task autonomously without interventions, and experimental results with a four-finger robotic hand learning multi-stage object manipulation tasks directly in the real world, without simulation, manual modeling, or reward engineering.

Reference-based Super-Resolution (Ref-SR) has recently emerged as a promising paradigm to enhance a low-resolution (LR) input image or video by introducing an additional high-resolution (HR) reference image. Existing Ref-SR methods mostly rely on implicit correspondence matching to borrow HR textures from reference images to compensate for the information loss in input images. However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e.g., scale and rotation) and the resolution gap (e.g., HR and LR). To tackle these challenges, we propose C2-Matching in this work, which performs explicit robust matching crossing transformation and resolution. 1) To bridge the transformation gap, we propose a contrastive correspondence network, which learns transformation-robust correspondences using augmented views of the input image. 2) To address the resolution gap, we adopt teacher-student correlation distillation, which distills knowledge from the easier HR-HR matching to guide the more ambiguous LR-HR matching. 3) Finally, we design a dynamic aggregation module to address the potential misalignment issue between input images and reference images. In addition, to faithfully evaluate the performance of Reference-based Image Super-Resolution under a realistic setting, we contribute the Webly-Referenced SR (WR-SR) dataset, mimicking the practical usage scenario. We also extend C2-Matching to Reference-based Video Super-Resolution task, where an image taken in a similar scene serves as the HR reference image. Extensive experiments demonstrate that our proposed C2-Matching significantly outperforms state of the arts on the standard CUFED5 benchmark and also boosts the performance of video SR by incorporating the C2-Matching component into Video SR pipelines.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal information, e.g., action detection, action recognition, video captioning, video retrieval. One of the most challenging problems in video understanding is dealing with feature extraction, i.e. extract contextual visual representation from given untrimmed video due to the long and complicated temporal structure of unconstrained videos. Different from existing approaches, which apply a pre-trained backbone network as a black-box to extract visual representation, our approach aims to extract the most contextual information with an explainable mechanism. As we observed, humans typically perceive a video through the interactions between three main factors, i.e., the actors, the relevant objects, and the surrounding environment. Therefore, it is very crucial to design a contextual explainable video representation extraction that can capture each of such factors and model the relationships between them. In this paper, we discuss approaches, that incorporate the human perception process into modeling actors, objects, and the environment. We choose video paragraph captioning and temporal action detection to illustrate the effectiveness of human perception based-contextual representation in video understanding. Source code is publicly available at https://github.com/UARK-AICV/Video_Representation.

Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks. Over the years, the research community expands mix-up methods into two directions, with extensive efforts to improve saliency-guided procedures but minimal focus on the arbitrary path, leaving the randomization domain unexplored. In this paper, inspired by the superior qualities of each direction over one another, we introduce a novel method that lies at the junction of the two routes. By combining the best elements of randomness and saliency utilization, our method balances speed, simplicity, and accuracy. We name our method R-Mix following the concept of "Random Mix-up". We demonstrate its effectiveness in generalization, weakly supervised object localization, calibration, and robustness to adversarial attacks. Finally, in order to address the question of whether there exists a better decision protocol, we train a Reinforcement Learning agent that decides the mix-up policies based on the classifier's performance, reducing dependency on human-designed objectives and hyperparameter tuning. Extensive experiments further show that the agent is capable of performing at the cutting-edge level, laying the foundation for a fully automatic mix-up. Our code is released at [https://github.com/minhlong94/Random-Mixup].

The biomedical imaging world is notorious for working with small amounts of data, frustrating state-of-the-art efforts in the computer vision and deep learning worlds. With large datasets, it is easier to make progress we have seen from the natural image distribution. It is the same with microscopy videos of neuron cells moving in a culture. This problem presents several challenges as it can be difficult to grow and maintain the culture for days, and it is expensive to acquire the materials and equipment. In this work, we explore how to alleviate this data scarcity problem by synthesizing the videos. We, therefore, take the recent work of the video diffusion model to synthesize videos of cells from our training dataset. We then analyze the model's strengths and consistent shortcomings to guide us on improving video generation to be as high-quality as possible. To improve on such a task, we propose modifying the denoising function and adding motion information (dense optical flow) so that the model has more context regarding how video frames transition over time and how each pixel changes over time.

Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference. We present Fast Weight Layers (FWLs), a neural component that provides the benefits of dynamic evaluation much more efficiently by expressing gradient updates as linear attention. A key improvement over dynamic evaluation is that FWLs can also be applied at training time so the model learns to make good use of gradient updates. FWLs can easily be added on top of existing transformer models, require relatively little extra compute or memory to run, and significantly improve language modeling perplexity.

Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases. In practice, the segmentation models may encounter new data that have not been seen yet. Also, the previous data training of segmentation models may be inaccessible due to privacy problems. Therefore, to address these problems, in this work, we propose a Continual Unsupervised Domain Adaptation (CONDA) approach that allows the model to continuously learn and adapt with respect to the presence of the new data. Moreover, our proposed approach is designed without the requirement of accessing previous training data. To avoid the catastrophic forgetting problem and maintain the performance of the segmentation models, we present a novel Bijective Maximum Likelihood loss to impose the constraint of predicted segmentation distribution shifts. The experimental results on the benchmark of continual unsupervised domain adaptation have shown the advanced performance of the proposed CONDA method.

Gait has been used in clinical and healthcare applications to assess the physical and cognitive health of older adults. Acoustic based gait detection is a promising approach to collect gait data of older adults passively and non-intrusively. However, there has been limited work in developing acoustic based gait detectors that can operate in noisy polyphonic acoustic scenes of homes and care homes. We attribute this to the lack of good quality gait datasets from the real-world to train a gait detector on. In this paper, we put forward a novel machine learning based filter which can triage gait audio samples suitable for training machine learning models for gait detection. The filter achieves this by eliminating noisy samples at an f(1) score of 0.85 and prioritising gait samples with distinct spectral features and minimal noise. To demonstrate the effectiveness of the filter, we train and evaluate a deep learning model on gait datasets collected from older adults with and without applying the filter. The model registers an increase of 25 points in its f(1) score on unseen real-word gait data when trained with the filtered gait samples. The proposed filter will help automate the task of manual annotation of gait samples for training acoustic based gait detection models for older adults in indoor environments.