LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detection
This work addresses the problem of balancing accuracy and computational efficiency for real-time dense object detection, offering an incremental improvement over existing methods.
The paper tackled the trade-off between accuracy and speed in real-time single-stage object detectors by introducing LapNet, which achieved competitive performance with faster inference times, as demonstrated by experiments showing improved detection accuracy on standard benchmarks.
Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to efficiently learn a single-shot detector which offers a very good compromise between these two objectives. To this end, we introduce LapNet, an anchor based detector, trained end-to-end without any sampling strategy. Our approach aims to overcome two important problems encountered in training an anchor based detector: (1) ambiguity in the assignment of anchor to ground truth and (2) class and object size imbalance. To address the first limitation, we propose a soft positive/negative anchor assignment procedure based on a new overlapping function called "Per-Object Normalized Overlap" (PONO). This soft assignment can be self-corrected by the network itself to avoid ambiguity between close objects. To cope with the second limitation, we propose to learn additional weights, that are not used at inference, to efficiently manage sample imbalance. These two contributions make the detector learning more generic whatever the training dataset. Various experiments show the effectiveness of the proposed approach.