Since the cost of labeling data is getting higher and higher, we hope to make full use of the large amount of unlabeled data and improve image classification effect through adding some unlabeled samples for training. In addition, we expect to uniformly realize two tasks, namely the clustering of the unlabeled data and the recognition of the query image. We achieve the goal by designing a novel sparse model based on manifold assumption, which has been proved to work well in many tasks. Based on the assumption that images of the same class lie on a sub-manifold and an image can be approximately represented as the linear combination of its neighboring data due to the local linear property of manifold, we proposed a sparse representation model on manifold. Specifically, there are two regularizations, i.e., a variant Trace lasso norm and the manifold Laplacian regularization. The first regularization term enables the representation coefficients satisfying sparsity between groups and density within a group. And the second term is manifold Laplacian regularization by which label can be accurately propagated from labeled data to unlabeled data. Augmented Lagrange Multiplier (ALM) scheme and Gauss Seidel Alternating Direction Method of Multiplier (GS-ADMM) are given to solve the problem numerically. We conduct some experiments on three human face databases and compare the proposed work with several state-of-the-art methods. For each subject, some labeled face images are randomly chosen for training for those supervised methods, and a small amount of unlabeled images are added to form the training set of the proposed approach. All experiments show our method can get better classification results due to the addition of unlabeled samples.
more »
« less
EXPLANATION BY PROGRESSIVE EXAGGERATION
As machine learning methods see greater adoption and implementation in high-stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that
assess feature importance (e.g., saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method
that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our
method produces a progressive set of plausible variations of that query, which
gradually changes the posterior probability from its original class to its negation.
These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a “tuning knob”
to traverse a data manifold while crossing the decision boundary. Our method is
model agnostic and only requires the output value and gradient of the predictor
with respect to its input.
more »
« less
- Award ID(s):
- 1839332
- NSF-PAR ID:
- 10299295
- Date Published:
- Journal Name:
- The International Conference on Learning Representations
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Lysyanskaya, Anna ; Handschuh, Helena (Ed.)We study the black-box function inversion problem, which is the problem of finding x[N] such that f(x)=y, given as input some challenge point y in the image of a function f:[N][N], using T oracle queries to f and preprocessed advice 01S depending on f. We prove a number of new results about this problem, as follows. 1. We show an algorithm that works for any T and S satisfying TS2maxST=(N3) . In the important setting when ST, this improves on the celebrated algorithm of Fiat and Naor [STOC, 1991], which requires TS3N3. E.g., Fiat and Naor's algorithm is only non-trivial for SN23 , while our algorithm gives a non-trivial tradeoff for any SN12 . (Our algorithm and analysis are quite simple. As a consequence of this, we also give a self-contained and simple proof of Fiat and Naor's original result, with certain optimizations left out for simplicity.) 2. We show a non-adaptive algorithm (i.e., an algorithm whose ith query xi is chosen based entirely on and y, and not on the f(x1)f(xi−1)) that works for any T and S satisfying S=(Nlog(NT)) giving the first non-trivial non-adaptive algorithm for this problem. E.g., setting T=Npolylog(N) gives S=(NloglogN). This answers a question due to Corrigan-Gibbs and Kogan [TCC, 2019], who asked whether it was possible for a non-adaptive algorithm to work with parameters T and S satisfying T+SlogNo(N) . We also observe that our non-adaptive algorithm is what we call a guess-and-check algorithm, that is, it is non-adaptive and its final output is always one of the oracle queries x1xT. For guess-and-check algorithms, we prove a matching lower bound, therefore completely characterizing the achievable parameters (ST) for this natural class of algorithms. (Corrigan-Gibbs and Kogan showed that any such lower bound for arbitrary non-adaptive algorithms would imply new circuit lower bounds.) 3. We show equivalence between function inversion and a natural decision version of the problem in both the worst case and the average case, and similarly for functions f:[N][M] with different ranges. All of the above results are most naturally described in a model with shared randomness (i.e., random coins shared between the preprocessing algorithm and the online algorithm). However, as an additional contribution, we show (using a technique from communication complexity due to Newman [IPL, 1991]) how to generically convert any algorithm that uses shared randomness into one that does not.more » « less
-
Messinger, David W. ; Velez-Reyes, Miguel (Ed.)Recent advances in data fusion provide the capability to obtain enhanced hyperspectral data with high spatial and spectral information content, thus allowing for an improved classification accuracy. Although hyperspectral image classification is a highly investigated topic in remote sensing, each classification technique presents different advantages and disadvantages. For example; methods based on morphological filtering are particularly good at classifying human-made structures with basic geometrical spatial shape, like houses and buildings. On the other hand, methods based on spectral information tend to perform better classification in natural scenery with more shape diversity such as vegetation and soil areas. Even more, for those classes with mixed pixels, small training data or objects with similar re ectance values present a higher challenge to obtain high classification accuracy. Therefore, it is difficult to find just one technique that provides the highest accuracy of classification for every class present in an image. This work proposes a decision fusion approach aiming to increase classification accuracy of enhanced hyperspectral images by integrating the results of multiple classifiers. Our approach is performed in two-steps: 1) the use of machine learning algorithms such as Support Vector Machines (SVM), Deep Neural Networks (DNN) and Class-dependent Sparse Representation will generate initial classification data, then 2) the decision fusion scheme based on a Convolutional Neural Network (CNN) will integrate all the classification results into a unified classification rule. In particular, the CNN receives as input the different probabilities of pixel values from each implemented classifier, and using a softmax activation function, the final decision is estimated. We present results showing the performance of our method using different hyperspectral image datasets.more » « less
-
Several recent works have demonstrated highly effective model stealing (MS) attacks on Deep Neural Networks (DNNs) in black-box settings, even when the training data is unavailable. These attacks typically use some form of Out of Distribution (OOD) data to query the target model and use the predictions obtained to train a clone model. Such a clone model learns to approximate the decision boundary of the target model, achieving high accuracy on in-distribution examples. We propose Ensemble of Diverse Models (EDM) to defend against such MS attacks. EDM is made up of models that are trained to produce dissimilar predictions for OOD inputs. By using a different member of the ensemble to service different queries, our defense produces predictions that are highly discontinuous in the input space for the adversary's OOD queries. Such discontinuities cause the clone model trained on these predictions to have poor generalization on in-distribution examples. Our evaluations on several image classification tasks demonstrate that EDM defense can severely degrade the accuracy of clone models (up to 39.7%). Our defense has minimal impact on the target accuracy, negligible computational costs during inference, and is compatible with existing defenses for MS attacks.more » « less
-
Flooding is one of the leading threats of natural disasters to human life and property, especially in densely populated urban areas. Rapid and precise extraction of the flooded areas is key to supporting emergency-response planning and providing damage assessment in both spatial and temporal measurements. Unmanned Aerial Vehicles (UAV) technology has recently been recognized as an efficient photogrammetry data acquisition platform to quickly deliver high-resolution imagery because of its cost-effectiveness, ability to fly at lower altitudes, and ability to enter a hazardous area. Different image classification methods including SVM (Support Vector Machine) have been used for flood extent mapping. In recent years, there has been a significant improvement in remote sensing image classification using Convolutional Neural Networks (CNNs). CNNs have demonstrated excellent performance on various tasks including image classification, feature extraction, and segmentation. CNNs can learn features automatically from large datasets through the organization of multi-layers of neurons and have the ability to implement nonlinear decision functions. This study investigates the potential of CNN approaches to extract flooded areas from UAV imagery. A VGG-based fully convolutional network (FCN-16s) was used in this research. The model was fine-tuned and a k-fold cross-validation was applied to estimate the performance of the model on the new UAV imagery dataset. This approach allowed FCN-16s to be trained on the datasets that contained only one hundred training samples, and resulted in a highly accurate classification. Confusion matrix was calculated to estimate the accuracy of the proposed method. The image segmentation results obtained from FCN-16s were compared from the results obtained from FCN-8s, FCN-32s and SVMs. Experimental results showed that the FCNs could extract flooded areas precisely from UAV images compared to the traditional classifiers such as SVMs. The classification accuracy achieved by FCN-16s, FCN-8s, FCN-32s, and SVM for the water class was 97.52%, 97.8%, 94.20% and 89%, respectively.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
