Class-agnostic Object Detection

28 Nov 2020  ·  Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Premkumar Natarajan ·

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a limited number of object types with unknown objects treated as background content. This hinders the adoption of conventional detectors in real-world applications like large-scale object matching, visual grounding, visual relation prediction, obstacle detection (where it is more important to determine the presence and location of objects than to find specific types), etc. We propose class-agnostic object detection as a new problem that focuses on detecting objects irrespective of their object-classes. Specifically, the goal is to predict bounding boxes for all objects in an image but not their object-classes. The predicted boxes can then be consumed by another system to perform application-specific classification, retrieval, etc. We propose training and evaluation protocols for benchmarking class-agnostic detectors to advance future research in this domain. Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions. Experimental results show that adversarial learning improves class-agnostic detection efficacy.

PDF Abstract

Results from the Paper

Ranked #99 on Image Classification on ObjectNet (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Image Classification ObjectNet ResNet-152 (FRCNN-ag-ad, VOC) Top-5 Accuracy 29.7 # 35
Top-1 Accuracy 13.2 # 99


No methods listed for this paper. Add relevant methods here