Related papers: Cost Aggregation Is All You Need for Few-Shot Segm…

Vision transformers have gained significant attention and achieved state-of-the-art performance in various computer vision tasks, including image classification, instance segmentation, and object detection. However, challenges remain in…

The primary aim of Audio-Visual Segmentation (AVS) is to precisely identify and locate auditory elements within visual scenes by accurately predicting segmentation masks at the pixel level. Achieving this involves comprehensively…

The goal of Audio-Visual Segmentation (AVS) is to localize and segment the sounding source objects from video frames. Research on AVS suffers from data scarcity due to the high cost of fine-grained manual annotations. Recent works attempt…

Despite the remarkable progress made by learning based stereo matching algorithms, one key challenge remains unsolved. Current state-of-the-art stereo models are mostly based on costly 3D convolutions, the cubic computational complexity and…

We present a new deep learning-based approach for dense stereo matching. Compared to previous works, our approach does not use deep learning of pixel appearance descriptors, employing very fast classical matching scores instead. At the same…

Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects…

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we…

A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels). Most existing methods meta-learn all three model components for fast…

Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have…

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…

Class-agnostic counting (CAC) aims to count objects of interest from a query image given few exemplars. This task is typically addressed by extracting the features of query image and exemplars respectively and then matching their feature…

In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on…

Despite the prevalence of tabular datasets, few-shot learning remains under-explored within this domain. Existing few-shot methods are not directly applicable to tabular datasets due to varying column relationships, meanings, and…

Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining. However, their direct application to the Segment Anything…

Video Object Segmentation (VOS) has emerged as an increasingly important problem with availability of larger datasets and more complex and realistic settings, which involve long videos with global motion (e.g, in egocentric settings),…

The VAT method is a visual technique for determining the potential cluster structure and the possible number of clusters in numerical data. Its improved version, iVAT, uses a path-based distance transform to improve the effectiveness of VAT…

We present Agglomerative Token Clustering (ATC), a novel token merging method that consistently outperforms previous token merging and pruning methods across image classification, image synthesis, and object detection & segmentation tasks.…

Cost aggregation is a key component of stereo matching for high-quality depth estimation. Most methods use multi-scale processing to downsample cost volume for proper context information, but will cause loss of details when upsampling. In…

State-of-the-art stereo matching methods typically use costly 3D convolutions to aggregate a full cost volume, but their computational demands make mobile deployment challenging. Directly applying 2D convolutions for cost aggregation often…

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an…