Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
This method reduces the need for candidate proposals in object localization, benefiting computer vision applications, but it is incremental as it builds on existing temporal classification techniques.
The paper tackles weakly supervised object detection by using a novel 'learning from counting' strategy that serializes images into sequences and applies an LSTM-CCTC network to localize objects based on counts, achieving state-of-the-art performance on PASCAL VOC datasets.
This paper reports a new solution of leveraging temporal classification to support weakly supervised object detection (WSOD). Specifically, we introduce raster scan-order techniques to serialize 2D images into 1D sequence data, and then leverage a combined LSTM (Long, Short-Term Memory) and CTC (Connectionist Temporal Classification) network to achieve object localization based on a total count (of interested objects). We term our proposed network LSTM-CCTC (Count-based CTC). This "learning from counting" strategy differs from existing WSOD methods in that our approach automatically identifies critical points on or near a target object. This strategy significantly reduces the need of generating a large number of candidate proposals for object localization. Experiments show that our method yields state-of-the-art performance based on an evaluation on PASCAL VOC datasets.