Object Detection

1727 papers with code • 54 benchmarks • 165 datasets

Object detection is the task of detecting instances of objects of a certain class within an image. The state-of-the-art methods can be categorized into two main types: one-stage methods and two stage-methods. One-stage methods prioritize inference speed, and example models include YOLO, SSD and RetinaNet. Two-stage methods prioritize detection accuracy, and example models include Faster R-CNN, Mask R-CNN and Cascade R-CNN.

The most popular benchmark is the MSCOCO dataset. Models are typically evaluated according to a Mean Average Precision metric.

( Image credit: Detectron )

Latest papers without code

Memory-efficient Patch-based Inference for Tiny Deep Learning

no code yet • NeurIPS 2021

We further propose receptive field redistribution to shift the receptive field and FLOPs to the later stage and reduce the computation overhead.

Image Classification Neural Architecture Search +1

Center Smoothing: Certified Robustness for Networks with Structured Outputs

no code yet • NeurIPS 2021

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs.

Adversarial Robustness Object Detection +1

Dynamic Grained Encoder for Vision Transformers

no code yet • NeurIPS 2021

Specifically, we propose a Dynamic Grained Encoder for vision transformers, which can adaptively assign a suitable number of queries to each spatial region.

Image Classification Language Modelling +1

An Empirical Study of Adder Neural Networks for Object Detection

no code yet • NeurIPS 2021

Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications.

Autonomous Driving Face Detection +2

Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection

no code yet • NeurIPS 2021

As a by-product, a CapS dataset is constructed by augmenting existing benchmark training set with additional image tags and captions.

RGB-D Salient Object Detection Saliency Detection +1

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency

no code yet • NeurIPS 2021

The observations gathered by this exploration policy are labelled using 3D consistency and used to improve the perception model.

Active Learning Instance Segmentation +2

Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction

no code yet • NeurIPS 2021

In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection.

RGB-D Salient Object Detection Saliency Prediction +1

Recurrent Bayesian Classifier Chains for Exact Multi-Label Classification

no code yet • NeurIPS 2021

In this work we propose Recurrent Bayesian Classifier Chains (RBCCs), which learn a Bayesian network of class dependencies and leverage this network in order to condition the prediction of child nodes only on their parents.

Autonomous Vehicles Classification +2

Searching Parameterized AP Loss for Object Detection

no code yet • NeurIPS 2021

In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.

Object Detection

SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection

no code yet • NeurIPS 2021

In this paper, we propose to leverage model’s predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.

Object Detection