Browse > Computer Vision > Image Classification

# Image Classification Edit

472 papers with code · Computer Vision

# Density estimation in representation space to predict model uncertainty

20 Aug 2019

We compare our method to several baselines and set the state-of-the art for out-of-distribution detection in the Imagenet dataset.

# Adaptative Inference Cost With Convolutional Neural Mixture Models

19 Aug 2019

Despite the outstanding performance of convolutional neural networks (CNNs) for many vision tasks, the required computational cost during inference is problematic when resources are limited.

# Adversarial Defense by Suppressing High-frequency Components

19 Aug 2019

Recent works show that deep neural networks trained on image classification dataset bias towards textures.

# NLNL: Negative Learning for Noisy Labels

19 Aug 2019

The classical method of training CNNs is by labeling images in a supervised manner as in "input image belongs to this label" (Positive Learning; PL), which is a fast and accurate method if the labels are assigned correctly to all images.

# Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation

18 Aug 2019

In this paper, we show how to combine recent works on neural network certification tools (which are mainly used in static settings such as image classification) with robust control theory to certify a neural network policy in a control loop.

# Needles in Haystacks: On Classifying Tiny Objects in Large Images

16 Aug 2019

In some computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images.

# Improved Mix-up with KL-Entropy for Learning From Noisy Labels

15 Aug 2019

On the websites, there exist a lot of image data which contains inaccurate annotations, but training on these datasets may make networks easier to over-fit the noisy labels and cause performance degradation.

# DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation

14 Aug 2019

Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human.

# Benchmarking the Robustness of Semantic Segmentation Models

14 Aug 2019

While there are recent robustness studies for full-image classification, we are the first to present an exhaustive study for semantic segmentation, based on the state-of-the-art model DeepLabv3$+$.

# Space-time error estimates for deep neural network approximations for differential equations

11 Aug 2019

It is the subject of the main result of this article to provide space-time error estimates for DNN approximations of Euler approximations of certain perturbed differential equations.