Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly improve tail classes through re-balancing, represent...
arXiv:2503. 09399v4 Announce Type: replace-cross Abstract: Large-scale image classification datasets exhibit strong compositional biases: objects tend to be centered, appear at characteristic scales, and co-occur with class-specific context.
arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...
ProCAP introduces a probabilistic cross-attentive prompt learning framework for vision-language models like CLIP, enabling improved cross-modal interaction without updating the backbone. It jointly learns visual and textual prompt tokens, linking them via stacked bidirectional multi-head cross-attention to refine each branch across prompt depth. The method incorporates Gaussian parameterization of prompt tokens, lightweight KL and L2 regularization, and a compact symmetric InfoNCE head to align image features with class-level text representations, achieving strong few-shot base-to-novel performance and competitive transfer results across multiple datasets and benchmarks.
arXiv:2604. 02327v2 Announce Type: replace-cross Abstract: Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation.
arXiv:2606. 32018v1 Announce Type: cross Abstract: Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations, i.
arXiv:2607. 09832v1 Announce Type: new Abstract: Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes.
arXiv:2606. 02526v1 Announce Type: cross Abstract: Long-tailed recognition poses a significant challenge for deep learning.
The paper introduces the concept of information density to explain category bias in visual object detection. It finds a strong negative correlation between a category’s information density and its detection accuracy, showing that instance count alone does not account for bias. By incorporating information density into three advanced loss functions, the authors demonstrate significant bias reduction and overall performance gains on Pascal VOC, COCO‑LT, and LVIS datasets.
arXiv:2609.16365v1 Announce Type: cross Abstract: Real-world datasets often exhibit long-tailed class distributions, where a few head classes contain a large number of training samples while a large...
arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...
The paper introduces the concept of information density to explain category bias in visual object detection. It finds a strong negative correlation between a category’s information density and its detection accuracy, showing that instance count alone does not account for bias. By incorporating information density into three advanced loss functions, the authors demonstrate reduced model bias and improved overall performance on Pascal VOC, COCO‑LT, and LVIS datasets.