Related papers: WeedRepFormer: Reparameterizable Vision Transforme…

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…

Methane emissions from livestock, particularly cattle, significantly contribute to climate change. Effective methane emission mitigation strategies are crucial as the global population and demand for livestock products increase. We…

Dense image segmentation tasks e.g., semantic, panoptic) are useful for image editing, but existing methods can hardly generalize well in an in-the-wild setting where there are unrestricted image domains, classes, and image resolution and…

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…

Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The…

Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the Encoder-side Transformer for feature extraction. We further…

Balancing performance and interpretability in multivariate time series classification is a significant challenge due to data complexity and high dimensionality. This paper introduces PHeatPruner, a method integrating persistent homology and…

Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present Panoptic SegFormer, a general framework for panoptic…

Both fine-grained discriminative details and global semantic features can contribute to solving person re-identification challenges, such as occlusion and pose variations. Vision foundation models (\textit{e.g.}, DINO) excel at mining local…

Recent advances in vision transformers (ViTs) have achieved great performance in visual recognition tasks. Convolutional neural networks (CNNs) exploit spatial inductive bias to learn visual representations, but these networks are spatially…

We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction. Our approach unifies a broad range of tasks, from image segmentation, to novel view synthesis and video interpolation. We…

Plant phenotyping refers to a quantitative description of the plants properties, however in image-based phenotyping analysis, our focus is primarily on the plants anatomical, ontogenetical and physiological properties.This technique…

In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at…

Ophthalmologists have used fundus images to screen and diagnose eye diseases. However, different equipments and ophthalmologists pose large variations to the quality of fundus images. Low-quality (LQ) degraded fundus images easily lead to…

Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, recent methods have achieved promising results. However, these…

Segmentation is a crucial step in microscopy image analysis. Numerous approaches have been developed over the past years, ranging from classical segmentation algorithms to advanced deep learning models. While U-Net remains one of the most…

Video object detection has made significant progress in recent years thanks to convolutional neural networks (CNNs) and vision transformers (ViTs). Typically, CNNs excel at capturing local features but struggle to model global…

Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, \textit{e.g.}, attention mechanism,…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Organ segmentation of plant point clouds is a prerequisite for the high-resolution and accurate extraction of organ-level phenotypic traits. Although the fast development of deep learning has boosted much research on segmentation of plant…