Long-tailed Object Detection
1개 벤치마크 · 논문 26편 · 이 태스크의 논문 보기 →
Benchmarks
LVIS v1.0 val
Most implemented
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection
Fractal Calibration for long-tailed object detection
Consensus Focus for Object Detection and minority classes
Papers
Improving Long-Tailed Object Detection with Balanced Group Softmax and Metric Learning
Object detection has been widely explored for class-balanced datasets such as COCO. However, real-world scenarios introduce the challenge of long-tailed distributions, where numerous categories contain only a few instanc…
Long-tailed Object Detection2D Object DetectionMetric LearningExponentially Weighted Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection Model Training in Unmanned Aerial Vehicles Surveillance Scenarios
Object detection models often struggle with class imbalance, where rare categories appear significantly less frequently than common ones. Existing sampling-based rebalancing strategies, such as Repeat Factor Sampling (RF…
Long-tailed Object Detectionobject-detectionObject DetectionPursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
In object detection, the instance count is typically used to define whether a dataset exhibits a long-tail distribution, implicitly assuming that models will underperform on categories with fewer instances. This assumpti…
Long-tailed Object Detectionobject-detectionObject DetectionSimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection
Recent years have witnessed tremendous advances on modern visual recognition systems. Despite such progress, many vision models still struggle with the open problem of learning from few exemplars. This paper focuses on t…
Few-Shot Object DetectionLong-tailed Object DetectionObject DetectionSemi-Supervised Object Detection+1DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encod…
Long-tailed Object DetectionObjectobject-detectionObject Detection+3Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions …
Contrastive LearningLong-tailed Object DetectionObjectobject-detection+2