Paper proposes CNN with SIFT for rotation invariant feature extraction.
problem Max-pooling layer discards rotational information, leading to rotation invariance issues.
method Uses SIFT descriptor to capture orientation and spatial relationships.
result Improves feature extraction on MNIST and fashionMNIST datasets.
AI classifies dental X-rays using CNN, SIFT, and HOG.
problem Automating dental image analysis for efficiency and accuracy.
method Used CNN, SIFT, and HOG for image classification.
result AI algorithms accurately classified dental X-rays.
SIFT reduces training time by selecting samples with approximate losses.
problem Reducing training time by selecting samples with large approximate losses.
method Developed SIFT which uses early exiting to obtain approximate losses with intermediate layer representations for sample selection.
result SIFT achieves significant gains in training time and number of backpropagation steps without optimized implementation.
The paper matches features in images using centro-affine invariants and heat flow.
problem Feature matching in images with invariant algorithms.
method Developed an invariant algorithm using centro-affine invariants and heat flow.
result The algorithm compares favorably with existing feature matching methods.
Paper generates synthetic radar signatures for motion classification.
problem Lack of large training datasets for radar-based human activity recognition.
method Adversarial learning for synthetic data generation, kinematic sifting for consistency.
result 93% overall accuracy achieved on diverse aspect angles.
A hybrid K-NN and SVM technique improves classification accuracy.
problem Improving classification accuracy in pattern recognition.
method Discriminative nearest neighbour classification combined with SVM.
result The hybrid technique outperforms state-of-the-art methods.
Cloak identifies essential features to preserve prediction privacy without provider collaboration.
problem Discovering the subset of features necessary for a prediction task.
method Gradient-based perturbation maximization method to identify essential features, followed by suppression of the rest using utility-preserving constant values.
result Cloak reduces mutual information between input and sifted representations by 85.01% with negligible utility loss.
DeepBark improves tree bark re-identification accuracy.
problem Challenging illuminations make tree bark hard to re-identify.
method Used a large dataset of 2,400 bark images to train DeepBark and SqueezeBark.
result DeepBark achieves 87.2% mAP in retrieving relevant bark images.
Training examples are not all equally informative. Active learning strategies leverage this observation in order to massively reduce the number of examples that need to be labeled. We leverage the same observation to build a generic strategy for parallelizing learning algorithms. This strategy is effective because the …
New algorithm for robust mean estimation in high dimensions with nearly-PCA time complexity.
problem Robust mean estimation in high-dimensional data with a minority of contaminated data.
method List-decodable mean estimation algorithm using a novel soft downweighting method, SIFT, and a Ky Fan matrix multiplicative weights procedure.
result Optimal sample complexity and error rate for list-decodable mean estimation with runtime nearly matching PCA.
This paper addresses the nearest neighbor search problem under inner product similarity and introduces a compact code-based approach. The idea is to approximate a vector using the composition of several elements selected from a source dictionary and to represent this vector by a short code composed of the indices of th…
Measuring the relationship between any pair of variables is a rich and active area of research that is central to scientific practice. In contrast, characterizing the common information among any group of variables is typically a theoretical exercise with few practical methods for high-dimensional data. A promising sol…
Symmetric observations don't necessarily imply symmetric causal explanations.
problem Inferring causal models from observed correlations is challenging and computationally intensive.
method An explicit example using a tripartite probability distribution over binary events.
result Symmetries in observations cannot be used to reduce the hypothesis space of causal models.
Financial markets are notoriously complex environments, presenting vast amounts of noisy, yet potentially informative data. We consider the problem of forecasting financial time series from a wide range of information sources using online Gaussian Processes with Automatic Relevance Determination (ARD) kernels. We measu…
New loss function and training scheme improve binary hash codes for better similarity search.
problem Improving binary hash codes for better similarity search tasks.
method Log likelihood loss on Hamming distance target, novel training scheme, multi-indexing.
result Significant improvements in MAP (84%) and query cost reduction for ImageNet and SIFT 1M.
New insights into experience replay in RL algorithms.
problem Understanding the impact of replay capacity and replay ratio in Q-learning.
method Systematic and extensive analysis of experience replay in Q-learning methods, focusing on replay capacity and replay ratio.
result Greater replay capacity significantly improves performance for certain algorithms, while other techniques offer limited benefit.
A measure of dependence is said to be equitable if it gives similar scores to equally noisy relationships of different types. Equitability is important in data exploration when the goal is to identify a relatively small set of strongest associations within a dataset as opposed to finding as many non-zero associations a…
RADNET achieves radiologist-level accuracy in CT scan hemorrhage detection.
problem Automated detection of brain hemorrhages in CT scans.
method RADNET uses a 3D context-aware deep learning model with attention mechanisms.
result RADNET achieves 81.82% accuracy in hemorrhage prediction, comparable to radiologists.
Scene parsing is an important and challenging prob- lem in computer vision. It requires labeling each pixel in an image with the category it belongs to. Tradition- ally, it has been approached with hand-engineered features from color information in images. Recently convolutional neural networks (CNNs), which automatica…
Pruning FCNs reveals sub-networks that match CNNs' performance.
problem Understanding the inductive bias of pruning in neural networks.
method Iterative magnitude pruning of a simple FCN followed by analysis of the resulting architecture.
result Pruned FCNs exhibit key features of CNNs, suggesting new architectural biases.
Naive Bayes Nearest Neighbour (NBNN) is a simple and effective framework which addresses many of the pitfalls of K-Nearest Neighbour (KNN) classification. It has yielded competitive results on several computer vision benchmarks. Its central tenet is that during NN search, a query is not compared to every example in a d…
Aesthetic-based clothing recommendation improves user satisfaction.
problem Lack of aesthetic features in existing clothing recommendation methods.
method Introduce aesthetic features extracted by a neural network and incorporate them into a personalized tensor factorization model.
result Our approach significantly outperforms state-of-the-art recommendation methods.
AI model automates financial investment research tasks.
problem Manual labor-intensive tasks in financial analysis.
method Fine-tuning language models on diverse financial data.
result Improved model performance in financial tasks.
QTNet uses deep reinforcement learning to automate trading strategies.
problem Handling noisy and high-frequency financial data, balancing exploration and exploitation.
method QTNet employs deep reinforcement learning (DRL) with imitative learning to autonomously formulate trading strategies.
result QTNet demonstrates proficiency in extracting robust market features and adaptability to diverse conditions.
Twitter system detects unexpected epidemics.
problem Detecting sudden, unexpected epidemic outbreaks in Twitter.
method Dynamic classification, alert generation, and ranking/recommendation.
result Empirical evaluation and validation with domain experts.
Intel's system identifies and categorizes businesses for sales opportunities.
problem Identifying relevant new markets and customers for large enterprises.
method Mining public business web pages, enriching with external data, and using deep learning.
result Significantly boosts sales personnel's ability to discover new customers and partnerships.
We discover subgroups for Cox model survival analysis, improving model accuracy.
problem Finding interpretable subsets of data where Cox model is highly accurate.
method Developed new metrics (EPE, CRS) and algorithms to solve subgroup discovery problem.
result Our methods improve model fit and recover known nonlinearities in data.