Object Detection

LION: Linear Group RNNs conquer 3D object detection in sparse point clouds by enabling efficient long-range feature interaction, significantly outperforming transformer-based methods.

DebLoRA: A novel unsupervised learning approach debiases LoRA for remote sensing imagery, boosting minor class performance without sacrificing major class accuracy.

Boost 3D object detection accuracy by augmenting pseudo-LiDAR point clouds!

PASTA: A novel modular framework boosts MOT tracker generalization by using parameter-efficient fine-tuning and avoiding negative interference through specialized modules for various scenario attribut…

Researchers developed Full Distance Attack (FDA) to generate adversarial patterns effective against pedestrian detectors across all distances, resolving the appearance gap issue between simulated and …

Frozen-DETR boosts object detection accuracy by integrating frozen foundation models as feature enhancers, achieving significant performance gains without the computational cost of fine-tuning.

DCOD, a novel two-stage framework (Fetch & Forge), efficiently condenses object detection datasets, achieving comparable performance to full datasets at extremely low compression rates, significantly …

EGSST: a novel framework for event-based object detection, uses graph structures and transformers to efficiently process event data, achieving high accuracy and speed in dynamic scenes.

E2E-MFD: A novel end-to-end multimodal fusion detection algorithm achieves state-of-the-art performance by synchronously optimizing image fusion and object detection.

KGD: a novel knowledge graph distillation technique empowers large-vocabulary object detectors with superior cross-domain object classification, achieving state-of-the-art performance.

DiPEx: a novel self-supervised prompt expansion method dramatically boosts class-agnostic object detection by progressively learning non-overlapping hyperspherical prompts, surpassing existing methods…

DINTR: A novel diffusion-based object tracker surpasses existing methods by using efficient interpolation, achieving superior performance across diverse benchmarks.

DI-MaskDINO: Novel model significantly boosts object detection & instance segmentation accuracy by addressing performance imbalance using a De-Imbalance module and Balance-Aware Tokens Optimization.

DeTrack revolutionizes visual object tracking with an in-model latent denoising learning process, achieving real-time speed and state-of-the-art accuracy.

DA-Ada enhances domain adaptive object detection by using a novel domain-aware adapter that leverages both domain-invariant and domain-specific knowledge for improved accuracy and generalization acros…

COUNTGD: A new multi-modal model counts objects in images using text or visual examples, significantly improving open-world counting accuracy.

Researchers developed CNCA, a novel method that generates realistic and customizable adversarial camouflage for vehicle detectors by leveraging a pre-trained diffusion model, surpassing existing metho…

COIN: A novel method for Cloud Object Detector Adaptation that integrates knowledge from cloud models and CLIP to train highly accurate target detectors, achieving state-of-the-art performance.

This paper introduces a novel object-centric learning (OCL) framework that enhances slot attention with a self-modulating top-down pathway, significantly improving object representation and achieving …

RFPAR: A novel reinforcement learning-based attack enhances black-box pixel attacks by minimizing randomness and patch dependency, achieving state-of-the-art results in both image classification and o…