Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching property fundamentally suffers from the intermediate interruptions in a video, such as object occlusions, fast camera movements, and abrupt light changes. Moreover, it typically overlooks temporal information beyond the two frames for matching. In this paper, we investigate an alternative by treating object association as clip-wise matching. Our new perspective views a single long video sequence as multiple short clips, and then the tracking is performed both within and between the clips. The benefits of this new approach are two folds. First, our method is robust to tracking error accumulation or propagation, as the video chunking allows bypassing the interrupted frames, and the short clip tracking avoids the conventional error-prone long-term track memory management. Second, the multiple frame information is aggregated during the clip-wise matching, resulting in a more accurate long-range track association than the current frame-wise matching. Given the state-of-the-art tracking-by-detection tracker, QDTrack, we showcase how the tracking performance improves with our new tracking formulation. We evaluate our proposals on two tracking benchmarks, TAO and MOT17 that have complementary characteristics and challenges each other.

Scaling object taxonomies is one of the important steps toward a robust real-world deployment of recognition systems. We have faced remarkable progress in images since the introduction of the LVIS benchmark. To continue this success in videos, a new video benchmark, TAO, was recently presented. Given the recent encouraging results from both detection and tracking communities, we are interested in marrying those two advances and building a strong large vocabulary video tracker. However, supervisions in LVIS and TAO are inherently sparse or even missing, posing two new challenges for training the large vocabulary trackers. First, no tracking supervisions are in LVIS, which leads to inconsistent learning of detection (with LVIS and TAO) and tracking (only with TAO). Second, the detection supervisions in TAO are partial, which results in catastrophic forgetting of absent LVIS categories during video fine-tuning. To resolve these challenges, we present a simple but effective learning framework that takes full advantage of all available training data to learn detection and tracking while not losing any LVIS categories to recognize. With this new learning scheme, we show that consistent improvements of various large vocabulary trackers are capable, setting strong baseline results on the challenging TAO benchmarks.

Test-time adaptation (TTA) has attracted significant attention due to its practical properties which enable the adaptation of a pre-trained model to a new domain with only target dataset during the inference stage. Prior works on TTA assume that the target dataset comes from the same distribution and thus constitutes a single homogeneous domain. In practice, however, the target domain can contain multiple homogeneous domains which are sufficiently distinctive from each other and those multiple domains might occur cyclically. Our preliminary investigation shows that domain-specific TTA outperforms vanilla TTA treating compound domain (CD) as a single one. However, domain labels are not available for CD, which makes domain-specific TTA not practicable. To this end, we propose an online clustering algorithm for finding pseudo-domain labels to obtain similar benefits as domain-specific configuration and accumulating knowledge of cyclic domains effectively. Moreover, we observe that there is a significant discrepancy in terms of prediction quality among samples, especially in the CD context. This further motivates us to boost its performance with gradient denoising by considering the image-wise similarity with the source distribution. Overall, the key contribution of our work lies in proposing a highly significant new task compound domain test-time adaptation (CD-TTA) on semantic segmentation as well as providing a strong baseline to facilitate future works to benchmark.

Universal Domain Adaptation aims to transfer the knowledge between the datasets by handling two shifts: domain-shift and category-shift. The main challenge is correctly distinguishing the unknown target samples while adapting the distribution of known class knowledge from source to target. Most existing methods approach this problem by first training the target adapted known classifier and then relying on the single threshold to distinguish unknown target samples. However, this simple threshold-based approach prevents the model from considering the underlying complexities existing between the known and unknown samples in the high-dimensional feature space. In this paper, we propose a new approach in which we use two sets of feature points, namely dual Classifiers for Prototypes and Reciprocals (CPR). Our key idea is to associate each prototype with corresponding known class features while pushing the reciprocals apart from these prototypes to locate them in the potential unknown feature space. The target samples are then classified as unknown if they fall near any reciprocals at test time. To successfully train our framework, we collect the partial, confident target samples that are classified as known or unknown through on our proposed multi-criteria selection. We then additionally apply the entropy loss regularization to them. For further adaptation, we also apply standard consistency regularization that matches the predictions of two different views of the input to make more compact target feature space. We evaluate our proposal, CPR, on three standard benchmarks and achieve comparable or new state-of-the-art results. We also provide extensive ablation experiments to verify our main design choices in our framework.

We present a unified and compact representation for object rendering, 3D reconstruction, and grasp pose prediction that can be inferred from a single image within a few seconds. We achieve this by leveraging recent advances in the Neural Radiance Field (NeRF) literature that learn category-level priors and fine-tune on novel objects with minimal data and time. Our insight is that we can learn a compact shape representation and extract meaningful additional information from it, such as grasping poses. We believe this to be the first work to retrieve grasping poses directly from a NeRF-based representation using a single viewpoint (RGB-only), rather than going through a secondary network and/or representation. When compared to prior art, our method is two to three orders of magnitude smaller while achieving comparable performance at view reconstruction and grasping. Accompanying our method, we also propose a new dataset of rendered shoes for training a sim-2-real NeRF method with grasping poses for different widths of grippers.

来自磁共振成像（MRI）的体积图像在直肠癌的术前分期提供了宝贵的信息。最重要的是，T2和T3阶段之间的准确术前歧视可以说是直肠癌治疗的最具挑战性和临床意义的任务，因为通常建议对T3（或更大）阶段癌症患者进行化学疗法。在这项研究中，我们提出了一个体积卷积神经网络，可准确区分T2与直肠MR体积的T3阶段直肠癌。具体而言，我们提出1）基于自定义的基于重新连接的卷编码器，该编码器与晚期融合的固定间关系建模（即最后一层的3D卷积），2）双线性计算，该计算汇总了编码器所得的功能以创建一个创建一个的功能体积特征和3）三重损失和焦点损失的关节最小化。通过病理确认的T2/T3直肠癌的MR量，我们进行了广泛的实验，以比较残留学习框架内的各种设计。结果，我们的网络达到了0.831的AUC，高于专业放射科医生组的准确性。我们认为该方法可以扩展到其他卷分析任务

最近，基于内存的方法显示了半监督视频对象分割的有希望的结果。这些方法可以通过对先前掩码的经常更新的内存来预测对象蒙版逐帧。与这种人均推断不同，我们通过将视频对象分割视为夹子掩盖传播来研究替代角度。在此每次CLIP推断方案中，我们使用一个间隔更新内存，并同时处理内存更新之间的一组连续帧（即剪辑）。该方案提供了两个潜在的好处：通过剪辑级优化和效率增益的准确性增益，通过平行计算多个帧。为此，我们提出了一种针对人均推理量身定制的新方法。具体而言，我们首先引入夹具操作，以根据CLIP相关性来完善特征。此外，我们采用了一种渐进匹配机制来在剪辑中有效地通过信息通行。通过两个模块的协同作用和新提议的每盘培训，我们的网络在YouTube-Vos 2018/2019 Val（84.6％和84.6％）和Davis 2016/2017 Val（91.9 Val（91.9 ％和86.1％）。此外，我们的模型在不同的内存更新间隔内显示出巨大的速度准确性权衡取舍，从而带来了巨大的灵活性。

已知视觉问题答案（VQA）的任务受到VQA模型的问题的困扰，从而利用数据集中的偏见来做出最终预测。已经提出了许多先前基于合奏的偏数方法，其中有目的地训练了一个额外的模型以帮助训练强大的目标模型。但是，这些方法从训练数据的标签统计数据或直接从单局分支中计算出模型的偏差。相反，在这项工作中，为了更好地了解目标VQA模型的偏见，我们提出了一种生成方法来训练偏差模型\ emph {直接来自目标模型}，称为GenB。特别是，GENB采用生成网络来通过对抗目标和知识蒸馏的结合来学习偏见。然后，我们将目标模型以GENB作为偏置模型为单位，并通过广泛的实验显示了我们方法对包括VQA CP2，VQA-CP1，VQA-CP1，GQA-OOD和VQA-CE在内的各种VQA偏置数据集的影响。

蒙面的自动编码器是可扩展的视觉学习者，因为Mae \ Cite {He2022masked}的标题表明，视觉中的自我监督学习（SSL）可能会采用与NLP中类似的轨迹。具体而言，具有蒙版预测（例如BERT）的生成借口任务已成为NLP中的事实上的标准SSL实践。相比之下，他们的歧视性对应物（例如对比度学习）掩埋了视力中的生成方法的早期尝试；但是，蒙版图像建模的成功已恢复了屏蔽自动编码器（过去通常被称为DeNosing AutoCoder）。作为在NLP中与Bert弥合差距的一个里程碑，蒙面自动编码器吸引了对SSL在视觉及其他方面的前所未有的关注。这项工作对蒙面自动编码器进行了全面的调查，以洞悉SSL的有希望的方向。作为第一个使用蒙版自动编码器审查SSL的人，这项工作通过讨论其历史发展，最新进度以及对不同应用的影响，重点介绍其在视觉中的应用。