Browse SoTA > Computer Vision > Object Classification

Object Classification

81 papers with code ยท Computer Vision

Benchmarks

Latest papers without code

A Comparative Study on Polyp Classification using Convolutional Neural Networks

12 Jul 2020

In this work, we compare the performance of the state-of-the-art general object classification models for polyp classification.

OBJECT CLASSIFICATION

Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN

3 Jul 2020

Unsupervised domain adaptive object detection is proposed recently to reduce the disparity between domains, where the source domain is label-rich while the target domain is label-agnostic.

OBJECT CLASSIFICATION OBJECT DETECTION

Terahertz Pulse Shaping Using Diffractive Legos

30 Jun 2020

Recent advances in deep learning have been providing non-intuitive solutions to various inverse problems in optics.

OBJECT CLASSIFICATION TRANSFER LEARNING

Zero-Shot Learning with Common Sense Knowledge Graphs

18 Jun 2020

To capture the knowledge in the graph, we introduce ZSL-KG, a framework based on graph neural networks with non-linear aggregators to generate class representations.

COMMON SENSE REASONING KNOWLEDGE GRAPHS OBJECT CLASSIFICATION ZERO-SHOT LEARNING

Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances

17 Jun 2020

Object detection algorithms for Lidar data have seen numerous publications in recent years, reporting good results on dataset benchmarks oriented towards automotive requirements.

OBJECT CLASSIFICATION OBJECT DETECTION PANOPTIC SEGMENTATION

Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses

2 Jun 2020

Object detection is an important task in computer vision which serves a lot of real-world applications such as autonomous driving, surveillance and robotics.

AUTONOMOUS DRIVING OBJECT CLASSIFICATION OBJECT DETECTION

ColorFool: Semantic Adversarial Colorization

CVPR 2020

Instead, adversarial attacks that generate unrestricted perturbations are more robust to defenses, are generally more successful in black-box settings and are more transferable to unseen classifiers.

ADVERSARIAL ATTACK ADVERSARIAL TRAINING COLORIZATION DENOISING OBJECT CLASSIFICATION

FPConv: Learning Local Flattening for Point Convolution

CVPR 2020

We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis.

3D OBJECT CLASSIFICATION OBJECT CLASSIFICATION SCENE SEGMENTATION

Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds

CVPR 2020

Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision.

3D OBJECT CLASSIFICATION OBJECT CLASSIFICATION UNSUPERVISED REPRESENTATION LEARNING

Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics

CVPR 2020

Based on this criterion, we introduce a novel image transformation that we call limited context inpainting (LCI).

OBJECT CLASSIFICATION