Finding Tiny Faces (by Hu and Ramanan) proposes a novel approach to find small objects in an image. Our contribution consists in deeply understanding the choices of the paper together with applying and extending a similar method to a real world subject which is the counting of people in a public demonstration.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,922 papers · 148 categories
Trend · papers per month
48 results for “Tiny Objects”
xYOLO speeds up object detection on low-end hardware for humanoid soccer robots.
problem Real-time object detection on resource-constrained devices like Raspberry Pi.
method Adaptation of YOLO CNN model to achieve faster inference speed.
result Achieved 9.66 FPS on Raspberry Pi 3 B, 70x faster than Tiny-YOLO.
A new clustering algorithm considers data smoothness for better performance.
problem Clustering multi-scale data with varying cluster densities.
method Divide objects into tiny clusters, cluster centers form smooth graphs.
result Significantly outperforms state-of-the-art clustering algorithms.
TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applicationscs.LG
TrackNet tracks tiny balls in sports videos with high precision.
problem Accurately tracking tiny and fast-moving objects like tennis balls in sports videos.
method Developed a heatmap-based deep learning network, TrackNet, trained on public and additional labeled videos.
result Achieved high precision (99.7%) in ball tracking on public domain videos.
Puzzle Mix optimizes mixup by leveraging saliency and local statistics.
problem Overfitting and adversarial vulnerability of deep networks.
method Puzzle Mix alternates between multi-label and saliency-based objectives for optimal mixing masks.
result Puzzle Mix outperforms other mixup methods in generalization and adversarial robustness.
Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-g…
Tiny Eats GRU detects eating episodes on a microcontroller.
problem Automatic dietary monitoring on low-power devices.
method Shallow gated recurrent unit (GRU) architecture on Arm Cortex M0+.
result Tiny Eats GRU achieves 95.15% accuracy with 4% memory usage and 6 ms latency.
Tiny non-Leighton complexesmath.GT
Tiny complexes share 3-5 triangles in common coverings.
problem Complexes sharing common coverings with finite triangles.
method Pseudo-simplicial triangulation analysis.
result Minimum triangles in common coverings are 3, 4, or 5.
Tab-TRM uses recursive model for insurance pricing on tabular data.
problem Insurance pricing on tabular data.
method Adapts recursive latent reasoning to insurance modeling using a compact, parameter-efficient network.
result Improves insurance pricing accuracy using iterative refinement of latent tokens.
Sharp results link DLN gradient flow to basis pursuit optimization and GHA phase transitions.
problem Understanding implicit regularization in Diagonal Linear Networks.
method Sharp convergence bounds and characterization of minimizers.
result Gradient flow of DLNs with tiny initialization approximates minimizers of basis pursuit optimization problem.
This paper represents a preliminary (pre-reviewing) version of a sublinear variational algorithm for isotropic Gaussian mixture models (GMMs). Further developments of the algorithm for GMMs with diagonal covariance matrices (instead of isotropic clusters) and their corresponding benchmarking results have been published…
Tiny benchmarks reduce LLM evaluation costs by using fewer examples.
problem Expensive evaluation of LLMs with tens of thousands of examples.
method Developed evaluation tools and tiny versions of popular benchmarks.
result Accurately estimate LLM performance with just 100 curated examples.
New algorithm PRACTISE accelerates networks with tiny sets, reducing latency by 22%.
problem Accelerating networks with tiny training sets to improve performance and privacy.
method Proposes a new algorithm PRACTISE based on finetune convexity hypothesis and feature mimicking.
result PRACTISE outperforms previous methods by reducing latency by 22% on ImageNet-1k.
ThriftyNet uses a single convolutional layer recursively to maximize parameter usage.
problem Maximizing the use of parameters in deep convolutional neural networks.
method A single convolutional layer is used recursively, with normalization, non-linearities, downsampling, and shortcuts to maintain model expressivity.
result ThriftyNet achieves competitive performance with significantly fewer parameters.
On the variety of Lie algebras endowed with complex structures: degenerations and deformationsmath.RT
Study Lie algebras with complex structures, focusing on degenerations and deformations.
problem Understanding the space of Lie algebras with complex structures and their transformations.
method Identifying invariants that remain consistent under degenerations and applying to four-dimensional case.
result Found invariants that help in understanding the behavior of Lie algebras under complex structures.
EAST compresses deep ConvNets for tiny memory nodes.
problem Memory constraints in tiny devices for deep ConvNets.
method Encoding-Aware Sparse Training (EAST) with adaptive group pruning and LZ4 weight encoding.
result EAST achieves deep memory compression with lower sparsity and higher accuracy.
Flat space for manifolds with tiny curvature.
problem Understanding manifolds with curvature concentration.
method Analyzing non-compact manifolds with non-negative Ricci curvature and small curvature concentration.
result Manifolds with curvature concentration are flat.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
problem Memory limitations prevent accurate deployment of DNN models on tiny MCUs.
method Automated mixed-precision quantization using Reinforcement Learning for MCU constraints.
result Mixed-precision models achieve high accuracy with uniform quantization policies.
The state of the art lung nodule detection studies rely on computationally expensive multi-stage frameworks to detect nodules from CT scans. To address this computational challenge and provide better performance, in this paper we propose S4ND, a new deep learning based method for lung nodule detection. Our approach use…
New method certifies global robustness of neural networks efficiently.
problem Adversarial examples threaten certifiably robust neural networks.
method Formalized global robustness, adapted widely-used architectures with efficient global Lipschitz bounds.
result Certifiable robust models achieve state-of-the-art verifiable accuracy with negligible costs.
Generative model improves scene graph prediction for rare compositions.
problem Challenges in inferring unseen or rare scene graph compositions.
method Synthesizing rare scene graphs by perturbing real ones, using conditional GANs.
result Marginal but consistent improvements in zero- and few-shot metrics.
TEAM generates more powerful adversarial examples for DNNs.
problem Vulnerability of DNNs to imperceptible adversarial examples.
method TEAM uses Taylor expansion and Lagrangian multiplier method to craft adversarial examples.
result TEAM generates adversarial examples with 100% attack success rate using smaller perturbations.
This work analyzes how frequency components affect CNN predictions and robustness.
problem Lack of frequency-based explanation for CNNs leading to vulnerabilities.
method Frequency component analysis and quantification of their contribution to CNN predictions.
result Adversarial attacks exploit high-frequency features, while robustness comes from low-frequency associations.
Softmax is found ineffective for NL block, leading to improved performance.
problem Inefficiency of softmax in NL block for global context modeling.
method Empirical analysis and replacement of softmax with scaling factor.
result Improved performance on various datasets with reduced computational cost.
ALCORE tensor decomposition reduces computational cost for sparse count data.
problem Efficiently decompose sparse count data matrices.
method Probabilistic Tucker decomposition with -norm constraint.
result ALCORE achieves similar results to full Tucker decomposition at a fraction of the cost.
POET enables large neural network training on tiny devices with reduced energy.
problem Training large neural networks on memory-limited edge devices.
method Jointly optimizes rematerialization and paging for memory reduction, formulating an MILP for energy-efficient training.
result POET trains ResNet-18 and BERT within Cortex-M memory constraints, outperforming current methods in energy efficiency.
Improved bound for optimal Moebius band aspect ratio.
problem Finding the optimal aspect ratio of a Moebius band.
method Optimization problem to find the smallest possible aspect ratio of a smoothly embedded Moebius band.
result The new bound is at least , significantly improving on previous bounds.
In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform …
ALPS improves neural network robustness and generalization.
problem Challenges in designing effective regularization schemes for adversarial robustness.
method Adversarial Labelling of Perturbed Samples (ALPS) using synthetic samples and min-max formulation.
result ALPS achieves state-of-the-art regularization performance and adversarial robustness.
Survey tackles continual learning in classification tasks to prevent forgetting.
problem Prevent catastrophic forgetting in neural networks across multiple tasks.
method Taxonomy, stability-plasticity trade-off framework, comprehensive comparison of methods.
result Empirical evaluation of continual learning methods on various benchmarks.
Unsupervised training improves adversarial robustness.
problem Training robust models requires large labeled datasets, which are expensive.
method Used unlabeled data to train adversarially robust models.
result Unsupervised Adversarial Training improves robust accuracy by 21.7%.
How simple regulations can greatly reduce inequalityphysics.soc-ph
Many models of market dynamics make use of the idea of wealth exchanges among economic agents. A simple analogy compares the wealth in a society with the energy in a physical system, and the trade between agents to the energy exchange between molecules during collisions. However, while in physical systems the equiparti…
STORM enables edge computing for empirical risk minimization.
problem Training models on edge devices for streaming data.
method Online sketching for empirical risk minimization.
result STORM can estimate least-squares objective accurately.
Improved robustness of machine learning models with controlled Lipschitz constants.
problem Vulnerability of state-of-the-art models to adversarial attacks.
method Proposes a CLL loss that calibrates the margin and Lipschitz constant penalties, improving robustness certificates.
result Consistently outperforms other losses on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets.
RobNets improve robustness of deep neural networks against adversarial attacks.
problem Vulnerability of deep neural networks to adversarial attacks.
method One-shot neural architecture search, finetuning sub-networks, and analyzing robustness indicators.
result RobNets achieve superior robustness performance across various datasets.
This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have incre…
We show that in a variety of large-scale deep learning scenarios the gradient dynamically converges to a very small subspace after a short period of training. The subspace is spanned by a few top eigenvectors of the Hessian (equal to the number of classes in the dataset), and is mostly preserved over long periods of tr…
A new mutual information optimization method using self-supervised binary contrastive learning.
problem Improving self-supervised contrastive learning for better model performance.
method Proposes a novel loss function for contrastive learning that optimizes mutual information in positive and negative pairs.
result The proposed method outperforms state-of-the-art self-supervised contrastive frameworks on various benchmark datasets.
Review of efficient neural networks for TinyML on resource-constrained devices.
problem Resource constraints on ultra-low power MCUs for deep learning models.
method Model compression, quantization, low-rank factorization, model pruning, hardware acceleration, algorithm-architecture co-design.
result Optimized neural network architectures for minimal resource utilization on MCUs.
Paper trains a Transformer to add numbers of any length.
problem Training Transformers to handle arbitrary-length addition.
method Autoregressive generation from right to left.
result Trains a Transformer to generalize addition of numbers of any length.
New algorithm accelerates optimization in non-convex problems with heavy-tailed noise.
problem Optimizing non-convex functions with heavy-tailed noise.
method Proposes a variance-reduced accelerated algorithm for optimization problems in the form of .
result Achieves a high-probability convergence rate of , faster than the lower bound .
Guided Dropoutcs.LG
Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the tra…
Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification models, including deep learning models, are highly vulnerable to adversarial attacks.…
New framework explains adversarial examples in neural nets.
problem Adversarial examples in deep neural networks are counterintuitive and hard to explain.
method Introduces Dimpled Manifold Model to explain training phases and adversarial examples.
result Shows how adversarial examples arise from training dynamics and dimpling phase.
In this short article we investigate the topology of the moduli space of two-convex embedded tori . We prove that for this moduli space is path-connected, and that for the connected components of the moduli space are in bijective correspondence with the knot…
New methods improve anomaly detection in deep networks by leveraging hierarchical likelihoods and multi-scale features.
problem Challenges in detecting anomalies in high-level features due to model bias and domain prior.
method Two methods: 1) Log likelihood ratios between in-distribution and general distribution models, 2) Multi-scale likelihood contribution.
result Strong anomaly detection performance in unsupervised setting, slightly underperforming supervised methods.
Hash codes are efficient data representations for coping with the ever growing amounts of data. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees. We s…
Sparse modeling approach to analytical continuation of imaginary-time quantum Monte Carlo datacond-mat.str-el
A new approach of solving the ill-conditioned inverse problem for analytical continuation is proposed. The root of the problem lies in the fact that even tiny noise of imaginary-time input data has a serious impact on the inferred real-frequency spectra. By means of a modern regularization technique, we eliminate redun…