Related papers: CATrans: Context and Affinity Transformer for Few-…

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…

While large visual models (LVM) demonstrated significant potential in image understanding, due to the application of large-scale pre-training, the Segment Anything Model (SAM) has also achieved great success in the field of image…

We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective. Our method leverages relational patterns within and between images via self-correlational…

Recently, few-shot object detection~(FSOD) has received much attention from the community, and many methods are proposed to address this problem from a knowledge transfer perspective. Though promising results have been achieved, these…

Recent object detection models require large amounts of annotated data for training a new classes of objects. Few-shot object detection (FSOD) aims to address this problem by learning novel classes given only a few samples. While…

Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotated samples. To alleviate the data-hungry problem, we…

Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes…

Few-shot aerial image segmentation is a challenging task that involves precisely parsing objects in query aerial images with limited annotated support. Conventional matching methods without consideration of varying object orientations can…

Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the…

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate…

Remote sensing image change captioning (RSICC) aims to automatically generate sentences that describe content differences in remote sensing bitemporal images. Recently, attention-based transformers have become a prevalent idea for capturing…

Incremental few-shot semantic segmentation (IFSS) aims to incrementally extend a semantic segmentation model to novel classes according to only a few pixel-level annotated data, while preserving its segmentation capability on previously…

Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data…

Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud…

Semantic image synthesis aims to generate photo realistic images given a semantic segmentation map. Despite much recent progress, training them still requires large datasets of images annotated with per-pixel label maps that are extremely…

An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as in Few-Shot Adaptation (FSA), data are insufficient…

Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many…

Recently supervised learning rapidly develops in scene text segmentation. However, the lack of high-quality datasets and the high cost of pixel annotation greatly limit the development of them. Considering the well-performed few-shot…

Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses…

Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase on a set of base classes. Recent works have shown that simply fine-tuning a pre-trained Vision…