Browse SoTA > Computer Vision > Object Recognition

Object Recognition

196 papers with code · Computer Vision

Object recognition is a computer vision technique for detecting + classifying objects in images or videos. Since this is a combined task of object detection plus image classification, the state-of-the-art tables are recorded for each component task here and here.

( Image credit: Tensorflow Object Detection API )

Leaderboards

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

Latest papers with code

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

CVPR 2020 FishYuLi/BalancedGroupSoftmax

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.

IMAGE CLASSIFICATION INSTANCE SEGMENTATION OBJECT DETECTION OBJECT RECOGNITION SEMANTIC SEGMENTATION

118
18 Jun 2020

Noise or Signal: The Role of Image Backgrounds in Object Recognition

17 Jun 2020MadryLab/backgrounds_challenge

We assess the tendency of state-of-the-art object recognition models to depend on signals from image backgrounds.

OBJECT RECOGNITION

22
17 Jun 2020

Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition

CVPR 2020 Hanzy1996/RRF-GZSL

We achieve our motivation by projecting the original visual features into a new (redundancy-free) feature space and then restricting the statistical dependence between these two feature spaces.

OBJECT RECOGNITION ZERO-SHOT LEARNING

5
16 Jun 2020

Computing the Testing Error Without a Testing Set

CVPR 2020 cipriancorneanu/dnn-topology

Here, we derive an algorithm to estimate the performance gap between training and testing without the need of a testing dataset.

OBJECT RECOGNITION SEMANTIC SEGMENTATION

27
01 Jun 2020

Adaptive Subspaces for Few-Shot Learning

CVPR 2020 chrysts/dsn_fewshot

In this paper, we provide a framework for few-shot learning by introducing dynamic classifiers that are constructed from few samples.

FEW-SHOT IMAGE CLASSIFICATION OBJECT RECOGNITION

15
01 Jun 2020

Traditional Method Inspired Deep Neural Network for Edge Detection

28 May 2020jannctu/TIN

Therefore, we propose a traditional method inspired framework to produce good edges with minimal complexity.

EDGE DETECTION OBJECT RECOGNITION SEMANTIC SEGMENTATION

16
28 May 2020

Computing the Testing Error without a Testing Set

1 May 2020cipriancorneanu/dnn-topology

Here, we derive an algorithm to estimate the performance gap between training and testing that does not require any testing dataset.

OBJECT RECOGNITION SEMANTIC SEGMENTATION

27
01 May 2020

When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition

26 Apr 2020acaglayan/CNN_randRNN

The second stage maps these features into high level representations with a fully randomized structure of recursive neural networks (RNNs) efficiently.

OBJECT RECOGNITION SCENE RECOGNITION

0
26 Apr 2020

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

arXiv 2020 garygsw/smooth-taylor

Integrated gradients as an attribution method for deep neural network models offers simple implementability.

IMAGE CLASSIFICATION OBJECT RECOGNITION

5
22 Apr 2020

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

arXiv 2020 garygsw/smooth-taylor

Integrated gradients as an attribution method for deep neural network models offers simple implementability.

IMAGE CLASSIFICATION OBJECT RECOGNITION

5
22 Apr 2020