Related papers: AlignDet: Aligning Pre-training and Fine-tuning in…

Landmark detection for clothes is a fundamental problem for many applications. In this paper, a new training scheme for clothes landmark detection: $\textit{Aggregation and Finetuning}$, is proposed. We investigate the homogeneity among…

Fine-tuning object detection (OD) models on combined datasets assumes annotation compatibility, yet datasets often encode conflicting spatial definitions for semantically equivalent categories. We propose an agentic label harmonization…

Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Therefore, high efficiency object detectors on CPU-only devices…

The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time,…

Recent advancements in LiDAR-based 3D object detection have significantly accelerated progress toward the realization of fully autonomous driving in real-world environments. Despite achieving high detection performance, most of the…

As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the…

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Multi-modal object detection in autonomous driving has achieved great breakthroughs due to the usage of fusing complementary information from different sensors. The calibration in fusion between sensors such as LiDAR and camera was always…

Accurate prediction of protein-ligand interactions is essential for computer-aided drug discovery. However, existing methods often fail to capture solvent-dependent conformational changes and lack the ability to jointly learn multiple…

Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large…

Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors (e.g., RGB, SAR, Infrared). Existing approaches largely adopt a late alignment paradigm, in which modality alignment and…

Object detection in Unmanned Aerial Vehicle (UAV) images poses significant challenges due to complex scale variations and class imbalance among objects. Existing methods often address these challenges separately, overlooking the intricate…

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…

Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar…

Open-set logo recognition is commonly solved by first detecting possible logo regions and then matching the detected parts against an ever-evolving dataset of cropped logo images. The matching model, a metric learning problem, is especially…

Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance…

State-of-the-art deep learning approaches for skin lesion recognition often require pretraining on larger and more varied datasets, to overcome the generalization limitations derived from the reduced size of the skin lesion imaging…

Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors…

Existing multimodal UAV object detection methods often overlook the impact of semantic gaps between modalities, which makes it difficult to achieve accurate semantic and spatial alignments, limiting detection performance. To address this…

Dense prediction tasks such as segmentation and detection of pathological entities hold crucial clinical value in computational pathology workflows. However, obtaining dense annotations on large cohorts is usually tedious and expensive.…