DeepAI AI Chat
Log In Sign Up

Reducing Label Noise in Anchor-Free Object Detection

by   Nermin Samet, et al.

Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these positively labeled features may be on the background or an occluder object, or they are simply not discriminative features. In this paper, we propose a new labeling strategy aimed to reduce the label noise in anchor-free detectors. We sum-pool predictions stemming from individual features into a single prediction. This allows the model to reduce the contributions of non-discriminatory features during training. We develop a new one-stage, anchor-free object detector, PPDet, to employ this labeling strategy during training and a similar prediction pooling method during inference. On the COCO dataset, PPDet achieves the best performance among anchor-free top-down detectors and performs on-par with the other state-of-the-art methods. It also outperforms all state-of-the-art methods in the detection of small objects (AP_S 31.4). Code is available at


page 2

page 4

page 5

page 10


ObjectBox: From Centers to Boxes for Anchor-Free Object Detection

We present ObjectBox, a novel single-stage anchor-free and highly genera...

iffDetector: Inference-aware Feature Filtering for Object Detection

Modern CNN-based object detectors focus on feature configuration during ...

Logit Normalization for Long-tail Object Detection

Real-world data exhibiting skewed distributions pose a serious challenge...

AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy

Colorectal cancer (CRC) is a common and lethal disease. Globally, CRC is...

EPP-Net: Extreme-Point-Prediction-Based Object Detection

Object detection can be regarded as a pixel clustering task, and its bou...

Feature Selective Anchor-Free Module for Single-Shot Object Detection

We motivate and present feature selective anchor-free (FSAF) module, a s...

Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark

Tiny object detection (TOD) in aerial images is challenging since a tiny...