Learning to decompose for object detection and instance segmentation

By Eunbyung Park, Alexander C. Berg. 2015

25 citations recorded by the source corpus.

Although deep convolutional neural networks(CNNs) have achieved remarkable results on object detection and segmentation, pre- and post-processing steps such as region proposals and non-maximum suppression(NMS), have been required. These steps result in high computational complexity and sensitivity to hyperparameters, e.g. thresholds for NMS. In this work, we propose a novel end-to-end trainable deep neural network architecture, which consists of convolutional and recurrent layers, that generates the correct number of object instances and their bounding boxes (or segmentation masks) given an image, using only a single network evaluation without any pre- or post-processing steps. We have tested on detecting digits in multi-digit images synthesized using MNIST, automatically segmenting digits in these images, and detecting cars in the KITTI benchmark dataset. The proposed approach outperforms a strong CNN baseline on the synthesized digits datasets and shows promising results on KITTI car detection.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

Citations in the corpus

End-to-End Object Detection with Transformers (2020, neutral): “Closest to our approach are end-to-end set predictions for object detection [43] and instance segmentation [41,30,36,42].”
Recurrent Neural Networks for Semantic Instance Segmentation (2017, background): “Park & Berg [31] present a model composed of different RNN units (one per class) that receive a spatial class score map and learn to separate the different instances that are included in the input.”
Pix2seq: A Language Modeling Framework for Object Detection (2021, background): “Our work is also related to recurrent models in object detection (Stewart et al., 2016; Park & Berg, 2015; Romera-Paredes & Torr, 2016; Salvador et al., 2017; Ren & Zemel, 2017), in which the system learns to predict one object at a time.”
Semantic Instance Segmentation with a Discriminative Loss Function (2017, methodology): “Two popular approaches introduce a multi-stage pipeline with object proposals [17, 9, 28, 29, 12, 13, 42, 4], or train a recurrent network end-to-end with a custom loss function that outputs instances sequentially [26, 31, 30].”
Unknown Object Segmentation from Stereo Images (2021, background): “an autoregressive or recurrent structure to process scenes instance-by-instance [17]–[21].”
End-to-End Instance Segmentation with Recurrent Attention (2016, methodology): “, [39, 31, 35] employs end-to-end recurrent neural networks (RNN) to perform object detection and segmentation.”