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.
New mechanisms from primate vision improve neural network robustness.
The current leading computer vision models are typically feed forward neural models, in which the output of one computational block is passed to the next one sequentially. This is in sharp contrast to the organization of the primate visual cortex, in which feedback and lateral connections are abundant. In this work, we…
Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual systems were the only ones capable of this remarkable computational feat. This has changed with the rise of a class of computer vision algo…
Local Hebbian learning is believed to be inferior in performance to end-to-end training using a backpropagation algorithm. We question this popular belief by designing a local algorithm that can learn convolutional filters at scale on large image datasets. These filters combined with patch normalization and very steep …
Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to how humans categorize objects, these approaches have not yet made use of any tax…
Method estimates network connectivity and dimensionality from multiple networks.
Machine learning methods struggle with geometric data, but shape space analysis provides a framework for studying and analyzing geometric variability.
Tensor-EM method learns MoLDS from complex, noisy data.
In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations. Inspired by a recent neuroscience discovery revealing t…
A major hurdle to clinical translation of brain-machine interfaces (BMIs) is that current decoders, which are trained from a small quantity of recent data, become ineffective when neural recording conditions subsequently change. We tested whether a decoder could be made more robust to future neural variability by train…
Sparse Vision MoE matches dense networks in image recognition while using less compute.
Robust CLIP improves vision models' resistance to attacks.
Gaussian processes are the leading class of distributions on random functions, but they suffer from well known issues including difficulty scaling and inflexibility with respect to certain shape constraints (such as nonnegativity). Here we propose Deep Random Splines, a flexible class of random functions obtained by tr…
Neural circuits contain heterogeneous groups of neurons that differ in type, location, connectivity, and basic response properties. However, traditional methods for dimensionality reduction and clustering are ill-suited to recovering the structure underlying the organization of neural circuits. In particular, they do n…
The Kalman filter (KF) is used in a variety of applications for computing the posterior distribution of latent states in a state space model. The model requires a linear relationship between states and observations. Extensions to the Kalman filter have been proposed that incorporate linear approximations to nonlinear m…
Top 8 robotic vision systems tackled lifelong object recognition challenges.
Computer vision SSL methods show effectiveness on time series data.
Quantum hybrid vision transformers improve event classification in high energy physics.
Mobile V-MoEs scale down ViTs for resource-constrained vision tasks.
The NIPS 2018 Adversarial Vision Challenge is a competition to facilitate measurable progress towards robust machine vision models and more generally applicable adversarial attacks. This document is an updated version of our competition proposal that was accepted in the competition track of 32nd Conference on Neural In…
GSA-Nets apply group equivariance to self-attention for vision tasks.
3DB framework tests and debugs computer vision models using photorealistic simulation.
The study combines social interaction data into a single network, identifying stable groups of chimpanzees.
CViT learns complex physical systems using vision transformer techniques.
Computer vision models are unstable due to task symmetries and labelling issues.
This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and development of intelligent vision and speech systems. With avai…
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recen…
Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image formation process as a function of latent variables with prior beliefs. Baye…
Visual object detection is a computer vision-based artificial intelligence (AI) technique which has many practical applications (e.g., fire hazard monitoring). However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored lar…
ViLT is a faster vision-and-language model without convolution or region supervision.
Framework simplifies vision-based control and goal discovery.
New framework segments 3D scenes using neural algorithms and sub-Riemannian geometry.
Real-time uncertainty estimation for computer vision tasks.
3D good continuation model explains stereo vision using neurogeometry.
Meta Omnium benchmarks few-shot learning across diverse vision tasks.
The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over…
Detects anomalies in autonomous mobile robots using vision.
The growing role that artificial intelligence and specifically machine learning is playing in shaping the future of wireless communications has opened up many new and intriguing research directions. This paper motivates the research in the novel direction of \textit{vision-aided wireless communications}, which aims at …
This work characterizes benign overfitting in Vision Transformers.
A model predicts visual motion by learning from natural videos.
Vision transformers benefit from non-smooth components in adaptation.
Introduces PCG for better counterfactual explanations in vision models.
A recent Cell paper [Chang and Tsao, 2017] reports an interesting discovery. For the face stimuli generated by a pre-trained active appearance model (AAM), the responses of neurons in the areas of the primate brain that are responsible for face recognition exhibit strong linear relationship with the shape variables and…
ADAPT improves robustness of Vision Transformers without full model fine-tuning.
Study proposes a statistical test for Vision Transformer's attention mechanisms.
An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular…
B-cos transformers explain Vision Transformers' decisions.
Vision Transformers show different internal representations compared to CNNs.