Papers Long-tailed Object Detection
“Long-tailed Object Detection” 태그가 달린 논문 26편 · 필터 해제
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+2Fractal Calibration for long-tailed object detection
Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and re-sampling methods, that uti…
Instance SegmentationLong-tailed Object DetectionObjectobject-detection+2Rectify the Regression Bias in Long-Tailed Object Detection
Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss function design, while ignoring the subtle i…
Long-tailed Object DetectionObjectobject-detectionObject Detection+1Consensus Focus for Object Detection and minority classes
Ensemble methods exploit the availability of a given number of classifiers or detectors trained in single or multiple source domains and tasks to address machine learning problems such as domain adaptation or multi-sourc…
Domain AdaptationLong-tailed Object DetectionObjectobject-detection+2Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to explore extra data with image-level labels, …
Long-tailed Object Detectionobject-detectionObject DetectionBalanced Classification: A Unified Framework for Long-Tailed Object Detection
Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. In this paper, we contend that the learning bias originates…
HallucinationLong-tailed Object DetectionObject DetectionSemi-Supervised and Long-Tailed Object Detection with CascadeMatch
This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detect…
Long-tailed Object DetectionObjectobject-detectionObject Detection+1Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data
Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise lea…
AllLong-tailed Object Detectionobject-detectionObject DetectionInstance-Aware Repeat Factor Sampling for Long-Tailed Object Detection
We propose an embarrassingly simple method -- instance-aware repeat factor sampling (IRFS) to address the problem of imbalanced data in long-tailed object detection. Imbalanced datasets in real-world object detection oft…
Long-tailed Object DetectionObjectobject-detectionObject DetectionLong-tail Detection with Effective Class-Margins
Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets. However, at test-time, we expect a detector tha…
Binary ClassificationInstance SegmentationLong-tailed Object DetectionObject+3Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
To effectively exploit the potential of large-scale models, various pre-training strategies supported by massive data from different sources are proposed, including supervised pre-training, weakly-supervised pre-training…
AllImage ClassificationLong-tailed Object Detectionobject-detection+2Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning
Data in real-world object detection often exhibits the long-tailed distribution. Existing solutions tackle this problem by mitigating the competition between the head and tail categories. However, due to the scarcity of …
ClassificationContrastive Learningimage-classificationImage Classification+3The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Long-tail distribution is widely spread in real-world applications. Due to the extremely small ratio of instances, tail categories often show inferior accuracy. In this paper, we find such performance bottleneck is mainl…
image-classificationImage ClassificationLong-tailed Object Detectionobject-detection+3Equalized Focal Loss for Dense Long-Tailed Object Detection
Despite the recent success of long-tailed object detection, almost all long-tailed object detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more prevalent in the industry becau…
Long-tailed Object DetectionObjectobject-detectionObject DetectionAdaptive Hierarchical Representation Learning for Long-Tailed Object Detection
General object detectors are always evaluated on hand-designed datasets, e.g., MS COCO and Pascal VOC, which tend to maintain balanced data distribution over different classes. However, it goes against the practical …
Long-tailed Object DetectionMetric LearningObjectobject-detection+2