Open-World实例细分（OWIS）旨在从图像中分割类不足的实例，该图像具有广泛的现实应用程序，例如自主驾驶。大多数现有方法遵循两阶段的管道：首先执行类不足的检测，然后再进行特定于类的掩模分段。相比之下，本文提出了一个单阶段框架，以直接为每个实例生成掩码。另外，实例掩码注释在现有数据集中可能很吵。为了克服这个问题，我们引入了新的正规化损失。具体而言，我们首先训练一个额外的分支来执行预测前景区域的辅助任务（即属于任何对象实例的区域），然后鼓励辅助分支的预测与实例掩码的预测一致。关键的见解是，这种交叉任务一致性损失可以充当误差校正机制，以打击注释中的错误。此外，我们发现所提出的跨任务一致性损失可以应用于图像，而无需任何注释，将自己借给了半监督的学习方法。通过广泛的实验，我们证明了所提出的方法可以在完全监督和半监督的设置中获得令人印象深刻的结果。与SOTA方法相比，所提出的方法将$ ap_ {100} $得分提高了4.75 \％\％\％\ rightarrow $ uvo设置和4.05 \％\％\％\％\％\％\ rightarrow $ uvo设置。在半监督学习的情况下，我们的模型仅使用30 \％标记的数据学习，甚至超过了其完全监督的数据，并具有5​​0 \％标记的数据。该代码将很快发布。

跳舞视频retargeting旨在综合传输从源视频到目标人物的舞蹈移动的视频。以前的工作需要收集有几分钟的目标人物，以训练个性化模型的数千帧。但是，训练有素的模型只能生成同一个人的视频。为了解决限制，最近的工作解决了几次跳舞的视频retargeting，这将通过利用其中几帧来综合看不见的人的视频。在实践中，给出了一个人的几个框架，这些工作只是将它们视为一批没有时间相关性的单个图像，从而产生了低视觉质量的时间上不连贯的跳舞视频。在这项工作中，我们将一个人的一些框架模拟了一系列跳舞的移动，其中每个移动包含两个连续帧，以提取这个人的外观模式和时间动态。我们提出了通过跳舞移动的合成优化模型的初始化，从而利用时间感知的元学习，使得元训练模型可以朝着增强的视觉质量和加强不良人员的时间稳定性地调整。很少的框架。广泛的评估显示了我们的方法的大量优势。

DataSet Shift在信用评分场景中很常见，并且培训数据分发与实际需要预测的数据之间的不一致可能导致模型性能不佳。但是，大多数当前研究都没有考虑到这一点，并且当培训模型时，它们直接在不同时间段中混合数据。这带来了大约两个问题。首先，存在数据泄漏的风险，即，使用未来的数据来预测过去。这可能导致离线验证的导致膨胀，但在实际应用中会导致不令人满意的结果。其次，在不同的时间段中，宏观经济环境和风险控制策略可能是不同的，借款人的行为模式也可能发生变化。具有过去数据培训的模型可能不适用于最近的阶段。因此，我们提出了一种基于对抗性验证的方法来缓解信用评分场景中的数据集转变问题。在该方法中，选择具有最接近预测数据的分布的部分训练设置样本用于通过对抗验证进行交叉验证，以确保训练模型对预测样本的泛化性能。另外，通过简单的拼接方法，与测试数据分发不一致的训练数据中的样本也也涉及交叉验证的培训过程，这充分利用了所有数据并进一步提高了模型性能。为了验证所提出的方法的有效性，通过贷款俱乐部提供的数据进行了具有若干其他数据分离方法的比较实验。实验结果表明，数据集转变在信用评分领域的重要性以及所提出的方法的优势。

多目标跟踪（MOT）的典型管道是使用探测器进行对象本地化，并在重新识别（RE-ID）之后进行对象关联。该管道通过对象检测和重新ID的最近进展部分而部分地激励，并且部分地通过现有的跟踪数据集中的偏差激励，其中大多数物体倾向于具有区分外观和RE-ID模型足以建立关联。为了响应这种偏见，我们希望重新强调多目标跟踪的方法也应该在对象外观不充分辨别时起作用。为此，我们提出了一个大型数据集，用于多人跟踪，人类具有相似的外观，多样化的运动和极端关节。由于数据集包含主要组跳舞视频，我们将其命名为“DanceTrack”。我们预计DanceTrack可以提供更好的平台，以开发更多的MOT算法，这些算法依赖于视觉识别并更依赖于运动分析。在我们的数据集上，我们在数据集上基准测试了几个最先进的追踪器，并在与现有基准测试中遵守DanceTrack的显着性能下降。 DataSet，项目代码和竞争服务器播放：\ url {https://github.com/danceTrack}。

Transformer最近提出了令人鼓舞的计算机视觉进展。在这项工作中，我们通过添加三个设计，包括（1）线性复杂性注意层，（2）重叠的补丁嵌入和（3）卷积进料网络，通过添加三个设计来提高原始金字塔视觉变压器（PVT V1）来展示新的基线。通过这些修改，PVT V2将PVT V1的计算复杂性降低到线性，并在类别，检测和分割等基本视觉任务上取得了重大改进。值得注意的是，所提出的PVT V2比最近的作品（例如Swin Transformer）取得了可比或更好的性能。我们希望这项工作将促进计算机视觉中最新的变压器研究。代码可在https://github.com/whai362/pvt上找到。

ous vision tasks without convolutions, where it can be used as a direct replacement for CNN backbones. (3) We validate PVT through extensive experiments, showing that it boosts the performance of many downstream tasks, including object detection, instance and semantic segmentation. For example, with a comparable number of parameters, PVT+RetinaNet achieves 40.4 AP on the COCO dataset, surpassing ResNet50+RetinNet (36.3 AP) by 4.1 absolute AP (see Figure 2). We hope that PVT could serve as an alternative and useful backbone for pixel-level predictions and facilitate future research.

In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as predicting contour of instance through instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on the challenging COCO dataset.For the first time, we show that the complexity of instance segmentation, in terms of both design and computation complexity, can be the same as bounding box object detection and this much simpler and flexible instance segmentation framework can achieve competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation task. Code is available at: github.com/xieenze/PolarMask.

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a limited understanding of the performance trade-offs of different decisions made during the instruction-tuning process. These decisions include the scale and diversity of the instruction-tuning benchmark, different task sampling strategies, fine-tuning with and without demonstrations, training using specialized datasets for reasoning and dialogue, and finally, the fine-tuning objectives themselves. In this paper, we characterize the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks. Through the lens of this framework, we first present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT. OPT-IML demonstrates all three generalization abilities at both scales on four different evaluation benchmarks with diverse tasks and input formats -- PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG. Not only does it significantly outperform OPT on all benchmarks but is also highly competitive with existing models fine-tuned on each specific benchmark. We release OPT-IML at both scales, together with the OPT-IML Bench evaluation framework.

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of their training context, or are they simply memorizing their training corpus at finer granularity and have learnt to better understand their context? To tease apart these possibilities, we introduce ALERT, a benchmark and suite of analyses for assessing language models' reasoning ability comparing pre-trained and finetuned models on complex tasks that require reasoning skills to solve. ALERT provides a test bed to asses any language model on fine-grained reasoning skills, which spans over 20 datasets and covers 10 different reasoning skills. We leverage ALERT to further investigate the role of finetuning. With extensive empirical analysis we find that language models learn more reasoning skills such as textual entailment, abductive reasoning, and analogical reasoning during finetuning stage compared to pretraining state. We also find that when language models are finetuned they tend to overfit to the prompt template, which hurts the robustness of models causing generalization problems.

Recent progress on vision-language foundation models have brought significant advancement to building general-purpose robots. By using the pre-trained models to encode the scene and instructions as inputs for decision making, the instruction-conditioned policy can generalize across different objects and tasks. While this is encouraging, the policy still fails in most cases given an unseen task or environment. To adapt the policy to unseen tasks and environments, we explore a new paradigm on leveraging the pre-trained foundation models with Self-PLAY and Self-Describe (SPLAYD). When deploying the trained policy to a new task or a new environment, we first let the policy self-play with randomly generated instructions to record the demonstrations. While the execution could be wrong, we can use the pre-trained foundation models to accurately self-describe (i.e., re-label or classify) the demonstrations. This automatically provides new pairs of demonstration-instruction data for policy fine-tuning. We evaluate our method on a broad range of experiments with the focus on generalization on unseen objects, unseen tasks, unseen environments, and sim-to-real transfer. We show SPLAYD improves baselines by a large margin in all cases. Our project page is available at https://geyuying.github.io/SPLAYD/