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

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

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---8x deeper than VGG nets 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 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

We introduce algorithms to visualize feature spaces used by object detectors. Our method works by inverting a visual feature back to multiple natural images. We found that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector’s failures. For example, when we visualize the features for high scoring false alarms, we discovered that, although they are clearly wrong in image space, they often look deceptively similar to true positives in feature space. This result suggests that many of these false alarms are caused by our choice of feature space, and supports that creating a better learning algorithm or building bigger datasets is unlikely to correct these errors without improving the features. By visualizing feature spaces, we can gain a more intuitive understanding of recognition systems.

Visualizing Object Detection Features

When glancing at a magazine, or browsing the Internet, we are continuously being exposed to photographs. However, not all images are equal in memory; some stitch to our minds, while others are forgotten. In this paper we discuss the notion of image memorability and the elements that make it memorable. Our recent works have shown that image memorability is a stable and intrinsic property of images that is shared across different viewers. Given that this is the case, we discuss the possibility of modifying the memorability of images by identifying the memorability of image regions. Further, we introduce and provide evidence for the phenomenon of visual inception: can we make people believe they have seen an image they have not?

/pdf/image-memorability-and-visual-inception-346pr0x3vd.pdf

Image memorability and visual inception

We introduce algorithms to visualize feature spaces used by object detectors. Our method works by inverting a visual feature back to multiple natural images. We found that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector's failures. For example, when we visualize the features for high scoring false alarms, we discovered that, although they are clearly wrong in image space, they often look deceptively similar to true positives in feature space. This result suggests that many of these false alarms are caused by our choice of feature space, and supports that creating a better learning algorithm or building bigger datasets is unlikely to correct these errors without improving the features. By visualizing feature spaces, we can gain a more intuitive understanding of recognition systems.

Human scene recognition is a rapid multistep process evolving over time from single scene image to spatial layout processing. We used multivariate pattern analyses on magnetoencephalography (MEG) data to unravel the time course of this cortical process. Following an early signal for lower-level visual analysis of single scenes at ~100ms, we found a marker of real-world scene size, i.e. spatial layout processing, at ~250ms indexing neural representations robust to changes in unrelated scene properties and viewing conditions. For a quantitative explanation that captures the complexity of scene recognition, we compared MEG data to a deep neural network model trained on scene classification. Representations of scene size emerged intrinsically in the model, and resolved emerging neural scene size representation. Together our data provide a first description of an electrophysiological signal for layout processing in humans, and a novel quantitative model of how spatial layout representations may emerge in the human brain.

https://www.biorxiv.org/content/biorxiv/early/2015/11/23/032623.full.pdf

Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks

Exploration of time domain is now a vibrant area of research in astronomy, driven by the advent of digital synoptic sky surveys. While panoramic surveys can detect variable or transient events, typically some follow-up observations are needed; for short-lived phenomena, a rapid response is essential. Ability to automatically classify and prioritize transient events for follow-up studies becomes critical as the data rates increase. We have been developing such methods using the data streams from the Palomar-Quest survey, the Catalina Sky Survey and others, using the VOEventNet framework. The goal is to automatically classify transient events, using the new measurements, combined with archival data (previous and multi-wavelength measurements), and contextual information (e.g., Galactic or ecliptic latitude, presence of a possible host galaxy nearby, etc.); and to iterate them dynamically as the follow-up data come in (e.g., light curves or colors). We have been investigating Bayesian methodologies for classification, as well as discriminated follow-up to optimize the use of available resources, including Naive Bayesian approach, and the non-parametric Gaussian process regression. We will also be deploying variants of the traditional machine learning techniques such as Neural Nets and Support Vector Machines on datasets of reliably classified transients as they build up.

/pdf/towards-real-time-classification-of-astronomical-transients-4pv44za77c.pdf

Aditya Khosla

Papers

Visualizing Object Detection Features

Image memorability and visual inception

Visualizing Object Detection Features

Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks

Towards Real-time Classification of Astronomical Transients