Multi-task learning in Convolutional Networks has displayed remarkable success in the field of recognition. This success can be largely attributed to learning shared representations from multiple supervisory tasks. However, existing multi-task approaches rely on enumerating multiple network architectures specific to the tasks at hand, that do not generalize. In this paper, we propose a principled approach to learn shared representations in ConvNets using multitask learning. Specifically, we propose a new sharing unit: "cross-stitch" unit. These units combine the activations from multiple networks and can be trained end-to-end. A network with cross-stitch units can learn an optimal combination of shared and task-specific representations. Our proposed method generalizes across multiple tasks and shows dramatically improved performance over baseline methods for categories with few training examples.

We propose a novel multi-task learning architecture, which allows learning of task-specific feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool, together with a soft-attention module for each task. These modules allow for learning of taskspecific features from the global features, whilst simultaneously allowing for features to be shared across different tasks. The architecture can be trained end-to-end and can be built upon any feed-forward neural network, is simple to implement, and is parameter efficient. We evaluate our approach on a variety of datasets, across both image-toimage predictions and image classification tasks. We show that our architecture is state-of-the-art in multi-task learning compared to existing methods, and is also less sensitive to various weighting schemes in the multi-task loss function. Code is available at https://github.com/ lorenmt/mtan.

The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10× or 100×? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between 'enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pretraining) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-theart results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.

We investigate methods for combining multiple selfsupervised tasks-i.e., supervised tasks where data can be collected without manual labeling-in order to train a single visual representation. First, we provide an apples-toapples comparison of four different self-supervised tasks using the very deep ResNet-101 architecture. We then combine tasks to jointly train a network. We also explore lasso regularization to encourage the network to factorize the information in its representation, and methods for "harmonizing" network inputs in order to learn a more unified representation. We evaluate all methods on ImageNet classification, PASCAL VOC detection, and NYU depth prediction. Our results show that deeper networks work better, and that combining tasks-even via a naïve multihead architecture-always improves performance. Our best joint network nearly matches the PASCAL performance of a model pre-trained on ImageNet classification, and matches the ImageNet network on NYU depth prediction.

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixelsto-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves stateof-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3× faster, tests 10× faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https: //github.com/rbgirshick/fast-rcnn.

In this paper we address three different computer vision tasks using a single multiscale convolutional network architecture: depth prediction, surface normal estimation, and semantic labeling. The network that we develop is able to adapt naturally to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.

Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful approach for unsupervised learning of CNN. Specifically, we use hundreds of thousands of unlabeled videos from the web to learn visual representations.Our key idea is that visual tracking provides the supervision. That is, two patches connected by a track should have similar visual representation in deep feature space since they probably belong to the same object or object part. We design a Siamese-triplet network with a ranking loss function to train this CNN representation. Without using a single image from ImageNet, just using 100K unlabeled videos and the VOC 2012 dataset, we train an ensemble of unsupervised networks that achieves 52% mAP (no bounding box regression). This performance comes tantalizingly close to its ImageNet-supervised counterpart, an ensemble which achieves a mAP of 54.4%. We also show that our unsupervised network can perform competitively in other tasks such as surface-normal estimation.

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012-achieving a mAP of 53.3%. Our approach combines two key insights:(1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at http://www.cs.berkeley.edu/ ˜rbg/rcnn.

转移学习可以在源任务上重新使用知识来帮助学习目标任务。一种简单的转移学习形式在当前的最先进的计算机视觉模型中是常见的，即预先训练ILSVRC数据集上的图像分类模型，然后在任何目标任务上进行微调。然而，先前对转移学习的系统研究已经有限，并且预计工作的情况并不完全明白。在本文中，我们对跨越不同的图像域进行了广泛的转移学习实验探索（消费者照片，自主驾驶，空中图像，水下，室内场景，合成，特写镜头）和任务类型（语义分割，物体检测，深度估计，关键点检测）。重要的是，这些都是与现代计算机视觉应用相关的复杂的结构化的输出任务类型。总共执行超过2000年的转移学习实验，包括许多来源和目标来自不同的图像域，任务类型或两者。我们系统地分析了这些实验，了解图像域，任务类型和数据集大小对传输学习性能的影响。我们的研究导致了几个见解和具体建议：（1）对于大多数任务，存在一个显着优于ILSVRC'12预培训的来源; （2）图像领域是实现阳性转移的最重要因素; （3）源数据集应该\ \ emph {include}目标数据集的图像域以获得最佳结果; （4）与此同时，当源任务的图像域比目标的图像域时，我们只观察小的负面影响; （5）跨任务类型的转移可能是有益的，但其成功严重依赖于源和目标任务类型。

We investigate and improve self-supervision as a dropin replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On VOC segmentation and classification tasks, we present results that are state-of-the-art among methods not using Im-ageNet labels for pretraining representations.Moreover, we present the first in-depth analysis of selfsupervision via colorization, concluding that formulation of the loss, training details and network architecture play important roles in its effectiveness. This investigation is further expanded by revisiting the ImageNet pretraining paradigm, asking questions such as: How much training data is needed? How many labels are needed? How much do features change when fine-tuned? We relate these questions back to self-supervision by showing that colorization provides a similarly powerful supervisory signal as various flavors of ImageNet pretraining.

我们提出了一个统一的查看，即通过通用表示，一个深层神经网络共同学习多个视觉任务和视觉域。同时学习多个问题涉及最大程度地减少具有不同幅度和特征的多个损失函数的加权总和，从而导致一个损失的不平衡状态，与学习每个问题的单独模型相比，一个损失的不平衡状态主导了优化和差的结果。为此，我们提出了通过小容量适配器将多个任务/特定于域网络的知识提炼到单个深神经网络中的知识。我们严格地表明，通用表示在学习NYU-V2和CityScapes中多个密集的预测问题方面实现了最新的表现，来自视觉Decathlon数据集中的不同域中的多个图像分类问题以及MetadataSet中的跨域中的几个域中学习。最后，我们还通过消融和定性研究进行多次分析。

Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224×224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement. The new network structure, called SPP-net, can generate a fixed-length representation regardless of image size/scale. Pyramid pooling is also robust to object deformations. With these advantages, SPP-net should in general improve all CNN-based image classification methods. On the ImageNet 2012 dataset, we demonstrate that SPP-net boosts the accuracy of a variety of CNN architectures despite their different designs. On the Pascal VOC 2007 and Caltech101 datasets, SPP-net achieves state-of-theart classification results using a single full-image representation and no fine-tuning.The power of SPP-net is also significant in object detection. Using SPP-net, we compute the feature maps from the entire image only once, and then pool features in arbitrary regions (sub-images) to generate fixed-length representations for training the detectors. This method avoids repeatedly computing the convolutional features. In processing test images, our method is 24-102× faster than the R-CNN method, while achieving better or comparable accuracy on Pascal VOC 2007.In ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2014, our methods rank #2 in object detection and #3 in image classification among all 38 teams. This manuscript also introduces the improvement made for this competition.

Semantic segmentation is a classic computer vision problem dedicated to labeling each pixel with its corresponding category. As a basic task for advanced tasks such as industrial quality inspection, remote sensing information extraction, medical diagnostic aid, and autonomous driving, semantic segmentation has been developed for a long time in combination with deep learning, and a lot of works have been accumulated. However, neither the classic FCN-based works nor the popular Transformer-based works have attained fine-grained localization of pixel labels, which remains the main challenge in this field. Recently, with the popularity of autonomous driving, the segmentation of road scenes has received increasing attention. Based on the cross-task consistency theory, we incorporate edge priors into semantic segmentation tasks to obtain better results. The main contribution is that we provide a model-agnostic method that improves the accuracy of semantic segmentation models with zero extra inference runtime overhead, verified on the datasets of road and non-road scenes. From our experimental results, our method can effectively improve semantic segmentation accuracy.

最近的工作表明，学习的图像压缩策略可以倾销标准的手工制作压缩算法，这些压缩算法已经开发了几十年的速率 - 失真折衷的研究。随着计算机视觉的不断增长的应用，来自可压缩表示的高质量图像重建通常是次要目标。压缩，可确保计算机视觉任务等高精度，例如图像分割，分类和检测，因此具有跨各种设置的显着影响的可能性。在这项工作中，我们开发了一个框架，它产生适合人类感知和机器感知的压缩格式。我们表明可以了解到表示，同时优化核心视觉任务的压缩和性能。我们的方法允许直接从压缩表示培训模型，并且这种方法会产生新任务和低拍学习设置的性能。我们呈现出与标准高质量JPG相比细分和检测性能提高的结果，但是在每像素的比特方面，表示表示的表示性比率为4至10倍。此外，与天真的压缩方法不同，在比标准JEPG的十倍小的级别，我们格式培训的分段和检测模型仅在性能下遭受轻微的降级。

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles which combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy and optimization function, etc. In this paper, we provide a review on deep learning based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely Convolutional Neural Network (CNN). Then we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network based learning systems.

This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning, to bring together the best of both worlds. In particular, it focuses simultaneous learning of multiple tasks, an element of MTL and promptly adapting to new tasks with fewer data, a quality of meta learning. It is important to highlight that we focus on heterogeneous tasks, which are of distinct kind, in contrast to typically considered homogeneous tasks (e.g., if all tasks are classification or if all tasks are regression tasks). The fundamental idea is to train a multi-task model, such that when an unseen task is introduced, it can learn in fewer steps whilst offering a performance at least as good as conventional single task learning on the new task or inclusion within the MTL. By conducting various experiments, we demonstrate this paradigm on two datasets and four tasks: NYU-v2 and the taskonomy dataset for which we perform semantic segmentation, depth estimation, surface normal estimation, and edge detection. MTML achieves state-of-the-art results for most of the tasks. Although semantic segmentation suffers quantitatively, our MTML method learns to identify segmentation classes absent in the pseudo labelled ground truth of the taskonomy dataset.

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with "attention" mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3], our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

尽管最近的密集预测问题的多任务学习的进步，但大多数方法都依赖于昂贵的标记数据集。在本文中，我们介绍了一个标签有效的方法，并在部分注释的数据上关注多密集预测任务，我们称之为多任务部分监督学习。我们提出了一种多任务培训程序，该程序成功利用任务关系在数据部分注释时监督其多任务学习。特别地，我们学会将每个任务对映射到联合成对任务空间，这使得通过在任务对上的另一个网络通过另一个网络以计算有效的方式共享信息，并通过保留高级信息来避免学习琐碎的交叉任务关系关于输入图像。我们严格证明，我们的提出方法有效利用了未标记的任务的图像，并且在三个标准基准测试中优于现有的半监督学习方法和相关方法。