YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
By Chien-Yao Wang, I-Hau Yeh, Hongpeng Liao. European Conference on Computer Vision, 2024
4,085 citations recorded by the source corpus.
Today's deep learning methods focus on how to design the most appropriate objective functions so that the prediction results of the model can be closest to the ground truth. Meanwhile, an appropriate architecture that can facilitate acquisition of enough information for prediction has to be designed. Existing methods ignore a fact that when input data undergoes layer-by-layer feature extraction and spatial transformation, large amount of information will be lost. This paper will delve into the important issues of data loss when data is transmitted through deep networks, namely information bottleneck and reversible functions. We proposed the concept of programmable gradient information (PGI) to cope with the various changes required by deep networks to achieve multiple objectives. PGI can provide complete input information for the target task to calculate objective function, so that reliable gradient information can be obtained to update network weights. In addition, a new lightweight network architecture -- Generalized Efficient Layer Aggregation Network (GELAN), based on gradient path planning is designed. GELAN's architecture confirms that PGI has gained superior results on lightweight models. We verified the proposed GELAN and PGI on MS COCO dataset based object detection. The results show that GELAN only uses conventional convolution operators to achieve better parameter utilization than the state-of-the-art methods developed based on depth-wise convolution. PGI can be used for variety of models from lightweight to large. It can be used to obtain complete information, so that train-from-scratch models can achieve better results than state-of-the-art models pre-trained using large datasets, the comparison results are shown in Figure 1. The source codes are at: https://github.com/WongKinYiu/yolov9.
Subfields: Radiology, Nuclear Medicine and Imaging
View Paper: https://www.semanticscholar.org/paper/cf70392a3b1ae92fdb1b70448aaddcbd03726d3d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Radiology, Nuclear Medicine and Imaging
Citations in the corpus
- YOLOv12: Attention-Centric Real-Time Object Detectors (2025, neutral): “We use several of its proposed C3K2 blocks (that is a special case of GELAN [58]).”
- Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation (2024, positive): “In contrast, YOLO methods [1], [2], [3], [4], [5], [7], [8], [22] have become widely favored in industrial applications due to their impressive speed, solid performance, and mature deployment frameworks.”
- YOLOv10: Real-Time End-to-End Object Detection (2024, methodology): “During training, YOLOs [21, 65, 29, 70] usually leverage TAL [15] to allocate multiple positive samples for each instance.”
- SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention (2024, neutral): “However, numerous studies have shown that relying solely on the convolutional branch for feature extraction can lead to distorted gradient flows [54], resulting in the loss of critical information or redundancy of similar features [4, 17, 66, 35].”
- YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception (2025, neutral): “YOLOv9 [15] and YOLOv10 [16] then focused on lightweight backbones and streamlined end-to-end deployment.”
- The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection (2024, positive): “In response to the challenges encountered by earlier models, YOLOv9 introduced several groundbreaking techniques designed to improve gradient flow, handle error accumulation, and facilitate better convergence during training.”