The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

/pdf/imagenet-large-scale-visual-recognition-challenge-caky5nmmix.pdf

ImageNet Large Scale Visual Recognition Challenge

On robust estimation of the location parameter

Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. These pixel contributions can be visualized as heatmaps and are provided to a human expert who can intuitively not only verify the validity of the classification decision, but also focus further analysis on regions of potential interest. We evaluate our method for classifiers trained on PASCAL VOC 2009 images, synthetic image data containing geometric shapes, the MNIST handwritten digits data set and for the pre-trained ImageNet model available as part of the Caffe open source package.

/pdf/on-pixel-wise-explanations-for-non-linear-classifier-4j59r9tlxm.pdf

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation.

The PASCAL Visual Object Classes Challenge

Even though human movement and mobility patterns have a high degree of freedom and variation, they also exhibit structural patterns due to geographic and social constraints. Using cell phone location data, as well as data from two online location-based social networks, we aim to understand what basic laws govern human motion and dynamics. We find that humans experience a combination of periodic movement that is geographically limited and seemingly random jumps correlated with their social networks. Short-ranged travel is periodic both spatially and temporally and not effected by the social network structure, while long-distance travel is more influenced by social network ties. We show that social relationships can explain about 10% to 30% of all human movement, while periodic behavior explains 50% to 70%. Based on our findings, we develop a model of human mobility that combines periodic short range movements with travel due to the social network structure. We show that our model reliably predicts the locations and dynamics of future human movement and gives an order of magnitude better performance than present models of human mobility.

/pdf/friendship-and-mobility-user-movement-in-location-based-2u0rrxuc9l.pdf

Friendship and mobility: user movement in location-based social networks

This paper considers the person verification problem in modern surveillance and video retrieval systems. The problem is to identify whether a pair of face or human body images is about the same person, even if the person is not seen before. Traditional methods usually look for a distance (or similarity) measure between images (e.g., by metric learning algorithms), and make decisions based on a fixed threshold. We show that this is nevertheless insufficient and sub-optimal for the verification problem. This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule. We further formulate the inference on our decision function as a second-order large-margin regularization problem, and provide an efficient algorithm in its dual from. We evaluate our algorithm on both human body verification and face verification problems. Our method outperforms not only the classical metric learning algorithm including LMNN and ITML, but also the state-of-the-art in the computer vision community.

/pdf/learning-locally-adaptive-decision-functions-for-person-4fyunv59os.pdf

Learning Locally-Adaptive Decision Functions for Person Verification

The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, label noise has been treated as statistical outliers, and techniques such as importance re-weighting and bootstrapping have been proposed to alleviate the problem. According to our observation, the real-world noisy labels exhibit multimode characteristics as the true labels, rather than behaving like independent random outliers. In this work, we propose a unified distillation framework to use “side” information, including a small clean dataset and label relations in knowledge graph, to “hedge the risk” of learning from noisy labels. Unlike the traditional approaches evaluated based on simulated label noises, we propose a suite of new benchmark datasets, in Sports, Species and Artifacts domains, to evaluate the task of learning from noisy labels in the practical setting. The empirical study demonstrates the effectiveness of our proposed method in all the domains.

Learning from Noisy Labels with Distillation

Most research efforts on image classification so far have been focused on medium-scale datasets, which are often defined as datasets that can fit into the memory of a desktop (typically 4G∼48G). There are two main reasons for the limited effort on large-scale image classification. First, until the emergence of ImageNet dataset, there was almost no publicly available large-scale benchmark data for image classification. This is mostly because class labels are expensive to obtain. Second, large-scale classification is hard because it poses more challenges than its medium-scale counterparts. A key challenge is how to achieve efficiency in both feature extraction and classifier training without compromising performance. This paper is to show how we address this challenge using ImageNet dataset as an example. For feature extraction, we develop a Hadoop scheme that performs feature extraction in parallel using hundreds of mappers. This allows us to extract fairly sophisticated features (with dimensions being hundreds of thousands) on 1.2 million images within one day. For SVM training, we develop a parallel averaging stochastic gradient descent (ASGD) algorithm for training one-against-all 1000-class SVM classifiers. The ASGD algorithm is capable of dealing with terabytes of training data and converges very fast–typically 5 epochs are sufficient. As a result, we achieve state-of-the-art performance on the ImageNet 1000-class classification, i.e., 52.9% in classification accuracy and 71.8% in top 5 hit rate.

/pdf/large-scale-image-classification-fast-feature-extraction-and-4rn5vyc0bs.pdf

Large-scale image classification: Fast feature extraction and SVM training

We present a novel generative model for simultaneously recognizing and segmenting object and scene classes. Our model is inspired by the traditional bag of words representation of texts and images as well as a number of related generative models, including probabilistic latent semantic analysis (pLSA) and latent Dirichlet allocation (LDA). A major drawback of the pLSA and LDA models is the assumption that each patch in the image is independently generated given its corresponding latent topic. While such representation provides an efficient computational method, it lacks the power to describe the visually coherent images and scenes. Instead, we propose a spatially coherent latent topic model (spatial-LTM). Spatial-LTM represents an image containing objects in a hierarchical way by over-segmented image regions of homogeneous appearances and the salient image patches within the regions. Only one single latent topic is assigned to the image patches within each region, enforcing the spatial coherency of the model. This idea gives rise to the following merits of spatial-LTM: (1) spatial-LTM provides a unified representation for spatially coherent bag of words topic models; (2) spatial-LTM can simultaneously segment and classify objects, even in the case of occlusion and multiple instances; and (3) spatial-LTM can be trained either unsupervised or supervised, as well as when partial object labels are provided. We verify the success of our model in a number of segmentation and classification experiments.

Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes

This paper studies the problem of discovering and comparing geographical topics from GPS-associated documents. GPS-associated documents become popular with the pervasiveness of location-acquisition technologies. For example, in Flickr, the geo-tagged photos are associated with tags and GPS locations. In Twitter, the locations of the tweets can be identified by the GPS locations from smart phones. Many interesting concepts, including cultures, scenes, and product sales, correspond to specialized geographical distributions. In this paper, we are interested in two questions: (1) how to discover different topics of interests that are coherent in geographical regions? (2) how to compare several topics across different geographical locations? To answer these questions, this paper proposes and compares three ways of modeling geographical topics: location-driven model, text-driven model, and a novel joint model called LGTA (Latent Geographical Topic Analysis) that combines location and text. To make a fair comparison, we collect several representative datasets from Flickr website including Landscape, Activity, Manhattan, National park, Festival, Car, and Food. The results show that the first two methods work in some datasets but fail in others. LGTA works well in all these datasets at not only finding regions of interests but also providing effective comparisons of the topics across different locations. The results confirm our hypothesis that the geographical distributions can help modeling topics, while topics provide important cues to group different geographical regions.

/pdf/geographical-topic-discovery-and-comparison-48xmhfi7xp.pdf

Liangliang Cao

Papers

Learning Locally-Adaptive Decision Functions for Person Verification

Learning from Noisy Labels with Distillation

Large-scale image classification: Fast feature extraction and SVM training

Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes

Geographical topic discovery and comparison