Browse SoTA > Computer Vision > Object Detection

Object Detection

1005 papers with code ยท Computer Vision

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 )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers without code

Multi-scale Network Architecture Search for Object Detection

ICLR 2021

Many commonly-used detection frameworks aim to handle the multi-scale object detection problem.

FEATURE SELECTION OBJECT DETECTION

Benchmarking Unsupervised Object Representations for Video Sequences

ICLR 2021

Our results suggest that architectures with unconstrained latent representations and full-image object masks such as ViMON and OP3 are able to learn more powerful representations in terms of object detection, segmentation and tracking than the explicitly parameterized spatial transformer based architecture of TBA and SCALOR.

CLUSTERING OBJECT DETECTION SCENE UNDERSTANDING

MSFM: Multi-Scale Fusion Module for Object Detection

ICLR 2021

Specifically, the input of the module will be resized into different scales on which position and semantic information will be processed, and then they will be rescaled back and combined with the module input.

OBJECT DETECTION

FOC OSOD: Focus on Classification One-Shot Object Detection

ICLR 2021

This paper analyzes the serious false positive problem in OSOD and proposes a Focus on Classification One-Shot Object Detection (FOC OSOD) framework, which is improved in two important aspects: (1) classification cascade head with the fixed IoU threshold can enhance the robustness of classification by comparing multiple close regions; (2) classification region deformation on the query feature and the reference feature to obtain a more effective comparison region.

ONE-SHOT OBJECT DETECTION

PolarNet: Learning to Optimize Polar Keypoints for Keypoint Based Object Detection

ICLR 2021

Despite achieving promising performance at par with anchor-based detectors, the existing anchor-free detectors such as FCOS or CenterNet predict objects based on standard Cartesian coordinates, which often yield poor quality keypoints.

OBJECT DETECTION

Negative Data Augmentation

ICLR 2021

Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.

ACTION RECOGNITION ANOMALY DETECTION CONTRASTIVE LEARNING DATA AUGMENTATION IMAGE CLASSIFICATION IMAGE GENERATION OBJECT DETECTION REPRESENTATION LEARNING

Predictive Uncertainty in Deep Object Detectors: Estimation and Evaluation

ICLR 2021

We show that in the context of object detection, training variance networks with negative log likelihood (NLL) can lead to high entropy predictive distributions regardless of the correctness of the output mean.

OBJECT DETECTION

Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search

ICLR 2021

Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models.

FACE RECOGNITION IMAGE CLASSIFICATION OBJECT DETECTION