Proceedings Article•
Very Deep Convolutional Networks for Large-Scale Image Recognition
04 Sep 2014-
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small 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.
Abstract: 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.
Citations
More filters
08 Sep 2018
TL;DR: This work makes the first attempt to explore a detection-free Part Grouping Network (PGN) for efficiently parsing multiple people in an image in a single pass and outperforms all state-of-the-art methods on PASCAL-Person-Part dataset.
Abstract: Instance-level human parsing towards real-world human analysis scenarios is still under-explored due to the absence of sufficient data resources and technical difficulty in parsing multiple instances in a single pass. Several related works all follow the “parsing-by-detection” pipeline that heavily relies on separately trained detection models to localize instances and then performs human parsing for each instance sequentially. Nonetheless, two discrepant optimization targets of detection and parsing lead to suboptimal representation learning and error accumulation for final results. In this work, we make the first attempt to explore a detection-free Part Grouping Network (PGN) for efficiently parsing multiple people in an image in a single pass. Our PGN reformulates instance-level human parsing as two twinned sub-tasks that can be jointly learned and mutually refined via a unified network: (1) semantic part segmentation for assigning each pixel as a human part (e.g., face, arms); (2) instance-aware edge detection to group semantic parts into distinct person instances. Thus the shared intermediate representation would be endowed with capabilities in both characterizing fine-grained parts and inferring instance belongings of each part. Finally, a simple instance partition process is employed to get final results during inference. We conducted experiments on PASCAL-Person-Part dataset and our PGN outperforms all state-of-the-art methods. Furthermore, we show its superiority on a newly collected multi-person parsing dataset (CIHP) including 38,280 diverse images, which is the largest dataset so far and can facilitate more advanced human analysis. The CIHP benchmark and our source code are available at http://sysu-hcp.net/lip/.
293 citations
Cites background from "Very Deep Convolutional Networks fo..."
...Driven by the advance of fully convolutional networks (FCNs) [29], human parsing, or semantic part segmentation has recently witnessed great progress thanks to deeply learned features [37,14], large-scale annotations [24,11], and advanced reasoning over graphical models [45,3]....
[...]
TL;DR: A novel spatially variant recurrent neural network (RNN) is proposed as an edge stream to model edge details, with the guidance of another auto-encoder, to enhance the visibility of degraded images.
Abstract: Camera sensors often fail to capture clear images or videos in a poorly lit environment. In this paper, we propose a trainable hybrid network to enhance the visibility of such degraded images. The proposed network consists of two distinct streams to simultaneously learn the global content and the salient structures of the clear image in a unified network. More specifically, the content stream estimates the global content of the low-light input through an encoder–decoder network. However, the encoder in the content stream tends to lose some structure details. To remedy this, we propose a novel spatially variant recurrent neural network (RNN) as an edge stream to model edge details, with the guidance of another auto-encoder. The experimental results show that the proposed network favorably performs against the state-of-the-art low-light image enhancement algorithms.
293 citations
Cites background from "Very Deep Convolutional Networks fo..."
...The perceptual loss is defined as the Euclidean distance between the feature representations of a reconstructed image G(R) and the reference image I from the ReLU activation layers of the pre-trained 16 layer VGG network [55]....
[...]
Posted Content•
TL;DR: This article proposed a multi-resolution reconstruction architecture based on a Laplacian pyramid that uses skip connections from higher resolution feature maps and multiplicative gating to successively refine segment boundaries reconstructed from lower-resolution maps.
Abstract: CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling. This paper makes two contributions: (1) We demonstrate that while the apparent spatial resolution of convolutional feature maps is low, the high-dimensional feature representation contains significant sub-pixel localization information. (2) We describe a multi-resolution reconstruction architecture based on a Laplacian pyramid that uses skip connections from higher resolution feature maps and multiplicative gating to successively refine segment boundaries reconstructed from lower-resolution maps. This approach yields state-of-the-art semantic segmentation results on the PASCAL VOC and Cityscapes segmentation benchmarks without resorting to more complex random-field inference or instance detection driven architectures.
292 citations
TL;DR: Studies that explore the relationship between motor variability and motor learning in both humans and animal models are reviewed and neural circuit mechanisms that underlie the generation and regulation of motor variability are discussed.
Abstract: Trial-to-trial variability in the execution of movements and motor skills is ubiquitous and widely considered to be the unwanted consequence of a noisy nervous system. However, recent studies have suggested that motor variability may also be a feature of how sensorimotor systems operate and learn. This view, rooted in reinforcement learning theory, equates motor variability with purposeful exploration of motor space that, when coupled with reinforcement, can drive motor learning. Here we review studies that explore the relationship between motor variability and motor learning in both humans and animal models. We discuss neural circuit mechanisms that underlie the generation and regulation of motor variability and consider the implications that this work has for our understanding of motor learning.
292 citations
Cites background from "Very Deep Convolutional Networks fo..."
...…and classification problems has, in large part, been due to the use of convolutional network architectures that reduce dramatically the dimensionality of the solution space by enforcing highly symmetric patterns in the weights to be learned (LeCun et al. 1998, 2015; Simonyan & Zisserman 2014)....
[...]
23 Oct 2017
TL;DR: This paper proposes an end-to-end model which gradually refines its attention over the appearance and motion features of the video using the question as guidance and demonstrates the effectiveness of the model by analyzing the refined attention weights during the question answering procedure.
Abstract: Recently image question answering (ImageQA) has gained lots of attention in the research community. However, as its natural extension, video question answering (VideoQA) is less explored. Although both tasks look similar, VideoQA is more challenging mainly because of the complexity and diversity of videos. As such, simply extending the ImageQA methods to videos is insufficient and suboptimal. Particularly, working with the video needs to model its inherent temporal structure and analyze the diverse information it contains. In this paper, we consider exploiting the appearance and motion information resided in the video with a novel attention mechanism. More specifically, we propose an end-to-end model which gradually refines its attention over the appearance and motion features of the video using the question as guidance. The question is processed word by word until the model generates the final optimized attention. The weighted representation of the video, as well as other contextual information, are used to generate the answer. Extensive experiments show the advantages of our model compared to other baseline models. We also demonstrate the effectiveness of our model by analyzing the refined attention weights during the question answering procedure.
292 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...The image is processed by VGG network [23] and the activations in the last pooling layer are extracted as features for image regions....
[...]
...In our model, we select to use VGG network [23] as the frame-level appearance feature extractor because it is widely used and shows promising results in the literature....
[...]
References
More filters
20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Abstract: 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.
49,639 citations
23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Abstract: 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 present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
21,729 citations
Posted Content•
TL;DR: It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Abstract: Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-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, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a novel 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 state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image.
9,803 citations
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Abstract: The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
9,775 citations
TL;DR: A review of the Pascal Visual Object Classes challenge from 2008-2012 and an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.
Abstract: The Pascal Visual Object Classes (VOC) challenge consists of two components: (i) a publicly available dataset of images together with ground truth annotation and standardised evaluation software; and (ii) an annual competition and workshop. There are five challenges: classification, detection, segmentation, action classification, and person layout. In this paper we provide a review of the challenge from 2008---2012. The paper is intended for two audiences: algorithm designers, researchers who want to see what the state of the art is, as measured by performance on the VOC datasets, along with the limitations and weak points of the current generation of algorithms; and, challenge designers, who want to see what we as organisers have learnt from the process and our recommendations for the organisation of future challenges. To analyse the performance of submitted algorithms on the VOC datasets we introduce a number of novel evaluation methods: a bootstrapping method for determining whether differences in the performance of two algorithms are significant or not; a normalised average precision so that performance can be compared across classes with different proportions of positive instances; a clustering method for visualising the performance across multiple algorithms so that the hard and easy images can be identified; and the use of a joint classifier over the submitted algorithms in order to measure their complementarity and combined performance. We also analyse the community's progress through time using the methods of Hoiem et al. (Proceedings of European Conference on Computer Vision, 2012) to identify the types of occurring errors. We conclude the paper with an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.
6,061 citations