Localizing From Classification: Self-Directed Weakly Supervised Object Localization for Remote Sensing Images.

In recent years, object localization and detection methods in remote sensing images (RSIs) have received increasing attention due to their broad applications. However, most previous fully supervised methods require a large number of time-consuming and labor-intensive instance-level annotations. Compared with those fully supervised methods, weakly supervised object localization (WSOL) aims to recognize object instances using only image-level labels, which greatly saves the labeling costs of RSIs.

Low temperature and short daylength interact to affect the leaf senescence of two temperate tree species.

Temperature and photoperiod are two major environmental cues shaping the leaf senescence of temperate tree species. However, how the control of leaf senescence is split between photoperiod and temperature is unknown for many ecologically important species. Here, we conducted a growth chamber experiment to test the effects of temperature (6, 9, 18 and 21°C) and photoperiod (8 and 16 h daylength) on leaf senescence of two temperate tree species (Quercus mongolica Fisch.