Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection
نویسندگان
چکیده
Human-Object Interaction (HOI) detection plays a core role in activity understanding. As compositional learning problem (human-verb-object), studying its generalization matters. However, widely-used metric mean average precision (mAP) fails to model the well. Thus, we propose novel metric, mPD (mean Performance Degradation), as complementary of mAP evaluate performance gap among compositions different objects and same verb. Surprisingly, reveals that previous methods usually generalize poorly. With cue, Object Category (OC) Immunity boost HOI generalization. The idea is prevent from spurious object-verb correlations short-cut over-fit train set. To achieve OC-immunity, an OC-immune network decouples inputs OC, extracts representations, leverages uncertainty quantification unseen objects. In both conventional zero-shot experiments, our method achieves decent improvements. fully generalization, design new more difficult benchmark, on which present significant advantage. code available at https://github.com/Foruck/OC-Immunity.
منابع مشابه
Transfer learning for object category detection
Object category detection, the task of determining if one or more instances of a category are present in an image with their corresponding locations, is one of the fundamental problems of computer vision. The task is very challenging because of the large variations in imaged object appearance, particularly due to the changes in viewpoint, illumination and intra-class variance. Although successf...
متن کاملThe Object Detection Efficiency in Synthetic Aperture Radar Systems
The main purpose of this paper is to develop the method of characteristic functions for calculating the detection characteristics in the case of the object surrounded by rough surfaces. This method is to be implemented in synthetic aperture radar (SAR) systems using optimal resolution algorithms. By applying the specified technique, the expressions have been obtained for the false alarm and cor...
متن کاملObject Category Detection Using Audio-Visual Cues
Categorization is one of the fundamental building blocks of cognitive systems. Object categorization has traditionally been addressed in the vision domain, even though cognitive agents are intrinsically multimodal. Indeed, biological systems combine several modalities in order to achieve robust categorization. In this paper we propose a multimodal approach to object category detection, using au...
متن کاملHuman Computation for Object Detection
Object detection is a key component of many computer vision systems. This paper investigates human computation as a platform for object detection. We investigate and report on the quality of raw labels obtained from several sources of human labor. We find that the performance is not the same in all cases. We investigate and report on the quality of a simple aggregation algorithm. Finally, we co...
متن کاملFusing Shape and Appearance Information for Object Category Detection
We present a method which is able to combine various feature types (e.g. image patches and edge boundaries) to learn models for object categories. Our objective is to detect object instances in an image, as opposed to the easier task of image categorization. We investigate two algorithms for learning and detecting object categories. Both algorithms benefit from combining features. The first use...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2022
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v36i2.20075