Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

/pdf/imagenet-classification-with-deep-convolutional-neural-1190x9a6b9.pdf

ImageNet Classification with Deep Convolutional Neural Networks

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

/pdf/imagenet-a-large-scale-hierarchical-image-database-1e8f663s1h.pdf

ImageNet: A large-scale hierarchical image database

Over the last decade, Computer Vision, the branch of Artificial Intelligence aimed at understanding the visual world, has evolved from simply recognizing objects in images to describing pictures, answering questions about images, aiding robots maneuver around physical spaces, and even generating novel visual content. As these tasks and applications have modernized, so too has the reliance on more data, either for model training or for evaluation. In this chapter, we demonstrate that novel interaction strategies can enable new forms of data collection and evaluation for Computer Vision. First, we present a crowdsourcing interface for speeding up paid data collection by an order of magnitude, feeding the data-hungry nature of modern vision models. Second, we explore a method to increase volunteer contributions using automated social interventions. Third, we develop a system to ensure human evaluation of generative vision models are reliable, affordable, and grounded in psychophysics theory. We conclude with future opportunities for Human–Computer Interaction to aid Computer Vision.

Visual Intelligence through Human Interaction

Solvent-exfoliated Cu-TCPP nanosheets: electrochemistry and sensing application in simultaneous determination of 4-aminophenol and acetaminophen

References Fei-Fei, L., & Perona, P. (2005). A Bayesian Hierarchical Model for Learning Natural Scene Categories. IEEE Comp. Vis. Patt. Recog. Fei-Fei, L., VanRullen, R., Koch, C., & Perona, P. (2002). Rapid natural scene categorization in the near absence of attention. Proc. Natl. Acad. Sci, 99, 8378-8383. Hoiem, D., Efros, A. A., & Hebert, M. (2005). Geometric Context from a Single Image. ICCV. Lazebnik, S., Schmid, C. & Ponce, J. (2006). Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. IEEE Comp. Vis. Patt. Recog. Loschky, L. C., Sethi, A., Simons, D. J., Pydimarri, T. N.,Ochs, D., & Corbeille, J. L. (2007). The importanceof information localization in scene gist recognition. Journal Of Experimental Psychology: Human Per-ception & Performance, 33, 1431–1450. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision, 60 (2), 91-110. Oliva, A., & Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. Int. Journal of Computer Vision, 42, 145-175. Thorpe, S., Fize, D., & Marlot, C. (1996). Speed of processing in the human visual system. Nature, 381, 520-522. Torralbo, A., Chai, B., Caddigan, E., Walther, D., Beck, D., & Fei-Fei, L. (2009). Categorization of good and bad examples of natural scene categories. Presented at the 9th annual meeting of the Vision Sciences Society. Tversky, B., & Hemenway, K. (1983). Categories of Environmental Scenes. Cognitive Psychology, 15, 121-149. Feature localization • All features benefit from some localization • No improvement for any feature beyond level 6

Finding “good” features for natural scene classification

: The ability to interactively learn skills from human guidance and adjust behavior according to human preference is crucial to accelerating robot learning. But human guidance is an expensive resource, calling for methods that can learn efﬁciently. In this work, we argue that learning is more efﬁcient if the agent is equipped with a high-level, symbolic representation. We propose a dual representation framework for robot learning from human guidance. The dual representation used by the robotic agent includes one for learning a sensorimotor control policy, and the other, in the form of a symbolic scene graph, for encoding the task-relevant information that motivates human input. We propose two novel learning algorithms based on this framework for learning from human evaluative feedback and from preference. In ﬁve continuous control tasks in simulation and in the real world, we demonstrate that our algorithms lead to signiﬁcant improvement in task performance and learning speed. Additionally, these algorithms require less human effort and are qualitatively preferred by users. Project website: https://sites.google.com/view/dr-hrl .

A Dual Representation Framework for Robot Learning with Human Guidance

: We deal with the problem of recognizing social roles played by people in an event. Social roles are governed by human interactions, and form a fundamental component of human event description. We focus on a weakly supervised setting, where we are provided different videos belonging to an event class, without training role labels. Since social roles are described by the interaction between people in an event, we propose a Conditional Random Field to model the inter-role interactions, along with person specific social descriptors. We develop tractable variational inference to simultaneously infer model weights, as well as role assignment to all people in the videos. We also present a novel YouTube social roles dataset with ground truth role annotations, and introduce annotations on a subset of videos from the TRECVID-MED11 event kits for evaluation purposes. The performance of the model is compared against different baseline methods on these datasets.

Li Fei-Fei

Papers

Visual Intelligence through Human Interaction

Solvent-exfoliated Cu-TCPP nanosheets: electrochemistry and sensing application in simultaneous determination of 4-aminophenol and acetaminophen

Finding “good” features for natural scene classification

A Dual Representation Framework for Robot Learning with Human Guidance

Social Role Discovery in Human Events (Open Access)