Related papers: ERVD: An Efficient and Robust ViT-Based Distillati…

With the rapid development of vision tasks and the scaling on datasets and models, redundancy reduction in vision datasets has become a key area of research. To address this issue, dataset distillation (DD) has emerged as a promising…

Camera-based 3D object detection and tracking are essential for perception in autonomous driving. Current state-of-the-art approaches often rely exclusively on either perspective-view (PV) or bird's-eye-view (BEV) features, limiting their…

Knowledge distillation has become a cornerstone technique in deep learning, facilitating the transfer of knowledge from complex models to lightweight counterparts. Traditional distillation approaches focus on transferring knowledge at the…

Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance. Although distilling precise 3D…

Efficient Image Super-Resolution (SR) aims to accelerate SR network inference by minimizing computational complexity and network parameters while preserving performance. Existing state-of-the-art Efficient Image Super-Resolution methods are…

In this paper, a novel approach to visual salience detection via Neural Response Divergence (NeRD) is proposed, where synaptic portions of deep neural networks, previously trained for complex object recognition, are leveraged to compute low…

Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill…

When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that accelerates learning beyond what proprioception alone can achieve. However, vision-enabled policies tend to…

Dataset distillation (DD) aims to synthesize compact training sets that enable models to achieve high accuracy with significantly fewer samples. Recent diffusion-based DD methods commonly introduce semantic guidance through late-stage…

Open-vocabulary object detection (OVD) aims to detect objects beyond the training annotations, where detectors are usually aligned to a pre-trained vision-language model, eg, CLIP, to inherit its generalizable recognition ability so that…

This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We propose two major enhancements. First,…

Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. However, these approaches typically require tens or even hundreds of…

Grouping images into semantically meaningful categories using low-level visual feature is a challenging and important problem in content-based image retrieval. The groupings can be used to build effective indices for an image database.…

Dataset distillation aims to synthesize a compact dataset from the original large-scale one, enabling highly efficient learning while preserving competitive model performance. However, traditional techniques primarily capture low-level…

Remote sensing change detection aims to localize and characterize scene changes between two time points and is central to applications such as environmental monitoring and disaster assessment. Meanwhile, visual autoregressive models (VARs)…

Person re-identification (re-id) aims to retrieve images of same identities across different camera views. Resolution mismatch occurs due to varying distances between person of interest and cameras, this significantly degrades the…

Large-scale fine-grained image retrieval (FGIR) aims to retrieve images belonging to the same subcategory as a given query by capturing subtle differences in a large-scale setting. Recently, Vision Transformers (ViT) have been employed in…

Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…

The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve…

Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D regions. Existing sparsity methods, designed mainly for 2D…